System

Abstract

A system is provided.SOLUTION: A system includes means for collecting user data, analysis means including generative artificial intelligence for analyzing the collected user data, recommendation means for recommending an optimal product to a user on the basis of an analysis result, means for notifying the user of recommendation content via an external communication tool, and chat means for answering a question from the user in real time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional online shopping recommendation systems generally recommend products based on purchase and browsing history, but in many cases, they fail to provide a personalized experience to users. Current systems also lack real-time communication and are unable to respond quickly to user questions or additional suggestions. This reduces users' purchasing motivation and creates a poor online shopping experience. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting user data, an analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, a recommendation means for recommending optimal products to users based on the analysis results, a means for notifying users of the recommendations via external communication tools, and a chat means for answering questions from users in real time. This system makes it possible to provide more personalized recommendations to users and realize real-time communication, thereby significantly improving the user's online shopping experience.

[0006] "User Data" refers to data relating to a user's online shopping behavior, such as their purchase history, browsing history, click history, and user ID.

[0007] "Generative artificial intelligence (AI)" is an artificial intelligence technology that analyzes large amounts of data, recognizes trends and patterns, and generates optimal recommendations based on user preferences.

[0008] "Analysis means" refers to the means of analyzing collected user data using artificial intelligence (AI) to extract user preferences and behavioral patterns.

[0009] The "recommendation means" is a means for selecting the most suitable product for the user and generating the recommendation content based on the results obtained by the analysis means.

[0010] "External communication tools" are external tools that enable real-time communication with users, such as messaging applications and social media platforms.

[0011] The "notification means" is a means for notifying the user's terminal of the recommendation content generated by the recommendation means via an external communication tool.

[0012] A "chat means" is a means for generating answers in real time to questions and additional suggestions from users and replying to them. [Brief explanation of the drawings]

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

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

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

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

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

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

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

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

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0030] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

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

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0034] The present invention is a personalized recommendation system for improving a user's online shopping experience, which is implemented as follows.

[0035] System Configuration

[0036] 1. Collection of User Data

[0037] When a user accesses an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history.

[0038] 2. Data Analysis

[0039] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[0040] Generative AI analyzes user data and recognizes user preferences and purchasing patterns. For example, it determines that a user who frequently purchases shoes from a particular brand will prefer that brand's products.

[0041] 3. Generating Recommendations

[0042] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0043] The generative AI generates specific recommendations for the selected products, which are presented in the form of empathetic and logical text, images, videos, etc.

[0044] 4. Notification

[0045] The server sends the recommendations created by the AI ​​to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[0046] 5. Chat integration

[0047] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[0048] The server receives messages from users and sends the contents to the generation AI.

[0049] The generative AI analyzes the user's question, generates appropriate answers and additional recommendations, and sends them back to the user's device in real time via the server.

[0050] Example: System behavior when user A purchases running shoes

[0051] As an example, we will explain the system flow when user A purchases running shoes on an online shopping site.

[0052] 1. The server collects user A's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[0053] 2. The server also sends User A's past purchasing history and browsing history to the generation AI.

[0054] 3. The generation AI analyzes User A's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[0055] 4. The generative AI generates recommendations consisting of empathetic and logical text and images, such as, "How about the perfect running socks to go with your new shoes?"

[0056] 5. The server notifies User A's device of this recommendation via the API of the external communication tool. User A receives this recommendation via a messaging application such as LINE.

[0057] 6. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[0058] 7. The server receives the question and sends it to the generating AI.

[0059] 8. The generation AI generates appropriate size information in response to User A's question and returns it to User A's device in real time via the server.

[0060] In this way, the system according to the present invention analyzes user purchasing behavior data and provides personalized product recommendations in real time, thereby improving the online shopping experience.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The device accesses an online shopping site, where the user browses or purchases products.

[0064] Step 2:

[0065] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[0066] Step 3:

[0067] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[0068] Step 4:

[0069] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[0070] Step 5:

[0071] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0072] Step 6:

[0073] The generative AI generates specific recommendations (e.g., text, images, and videos that are both empathetic and logical) for the selected products. Specifically, it creates content such as, "How about the perfect running socks to go with your new shoes?"

[0074] Step 7:

[0075] The server sends the recommendations created by the generation AI to the user's device via the API of an external communication tool (e.g., a messaging application).

[0076] Step 8:

[0077] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[0078] Step 9:

[0079] The server receives questions from users and sends the content to the generation AI.

[0080] Step 10:

[0081] The generative AI analyzes the user's question and generates an appropriate answer (e.g., sock size information).

[0082] Step 11:

[0083] The server sends the answers generated by the generation AI back to the user's device in real time via the API of an external communication tool.

[0084] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] In conventional online shopping systems, product recommendations to users are made in a general and inefficient manner, making it difficult to make personalized recommendations based on individual users' preferences and purchasing behavior patterns. Furthermore, few systems have the ability to accurately respond to user questions in real time, which can lead to a poor user experience. To address these issues, a system is needed that can effectively collect and analyze user data, generate personalized recommendations, and notify users promptly and appropriately.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes means for collecting user data, means for periodically or upon the occurrence of a specific trigger event, transmitting the collected user data to the generative AI model for analysis, means for selecting the most suitable product for the user based on the analysis results of the generative AI model and creating recommendations, means for notifying the user of the created recommendations via the API of an external communication tool, and means for accepting questions from users, transmitting them to the generative AI model, and returning the answers generated by the generative AI model to the user in real time. This enables accurate collection and analysis of user data, and the creation and notification of personalized recommendations, improving the user experience.

[0090] "User data" refers to data such as a user's access, browsing, purchase, and click history on an online shopping site, as well as user ID, purchase date and time, and payment information.

[0091] A "generative AI model" is an artificial intelligence model that analyzes user data and recognizes user preferences and purchasing behavior patterns.

[0092] "Trigger Event" means a specific event or condition that causes data to be analyzed or transmitted, such as the moment a user purchases a product or after a certain period of time has passed.

[0093] "External communication tools" are tools, including messaging applications and social networking platforms, used to transmit information between servers and users.

[0094] "API" stands for Application Programming Interface, an interface that enables data exchange between different software systems.

[0095] "Real-time" means that information is processed and provided to users immediately, without delay.

[0096] "Recommendation content" refers to information about products and services that the generative AI model suggests to users based on the results of analyzing user data, and is provided in the form of text, images, videos, etc.

[0097] This invention is a personalized recommendation system for improving users' online shopping experiences. The system collects user data through multiple means, analyzes the data using a generative AI model, recommends optimal products, and provides the ability to interact with users in real time.

[0098] User Data Collection

[0099] When a user visits an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history. This includes monitoring and collecting user behavior in real time using technologies such as JavaScript and tracking pixels. For example, when a user views or clicks on a particular product page, that data is immediately sent to the server.

[0100] Data analysis

[0101] The server stores the collected user data in a database. The stored data is automatically sent to the generative AI model periodically or when a specific trigger event occurs. The generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. This allows for advanced analysis of user preferences and purchasing behavior patterns.

[0102] Recommendation generation

[0103] The generative AI model uses analyzed user data to select the most suitable products for each user and generate specific recommendations. These recommendations can include text, images, videos, and other formats, and are both empathetic and logical. For example, if a user purchases new running shoes, the model generates empathetic messages suggesting related products (e.g., running socks, running apparel, etc.).

[0104] Notification of recommendation

[0105] The server sends the generated recommendation to the user's device via the API of an external communication tool (e.g., LINE or Facebook Messenger). This allows the user to receive the recommendation in real time. For example, a LINE notification might display a message such as, "How about finding the perfect running socks to go with your new shoes?"

[0106] Chat function integration

[0107] After receiving the recommendations, users can ask additional questions or make suggestions. When a question is sent through a messaging application, the server sends it to the generative AI model. The generative AI model analyzes the user's question and generates an appropriate answer or additional recommendations. The generated answer is immediately sent back to the user's device via the server. For example, if a user asks, "What size are these socks?", a real-time answer such as, "These running socks are available in S, M, and L sizes" is provided.

[0108] Specific examples

[0109] An example of a specific prompt might be, "A user has purchased running shoes. Please generate text and images that recommend products related to this user."

[0110] Thus, the present invention aims to collect and analyze user purchasing behavior data, provide personalized product recommendations in real time, and improve user experience.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1: Collect user data

[0113] When a user visits an online shopping site, the server automatically starts a session and collects the user ID, browsing history, and click history. Specifically, it records the product pages the user viewed and the links they clicked using JavaScript and tracking pixels.

[0114] Input: Behavioral data when users visit the site

[0115] Output: Collected user ID, browsing history, click history

[0116] Step 2: Collect your purchase history

[0117] When a user purchases a product, the server collects data such as the purchased product, purchase date and time, and payment information. This data is obtained through the confirmation page displayed when the purchase is completed and through APIs.

[0118] Input: Product information purchased by the user

[0119] Output: Collected purchased items, purchase date and time, payment information

[0120] Step 3: Save your data

[0121] The server stores the collected user behavior and purchase data in a main database, and organizes the data using a database management system (e.g., MySQL, PostgreSQL).

[0122] Input: Collected user behavior and purchase data

[0123] Output: Saved database records

[0124] Step 4: Prepare and send data

[0125] The server converts the stored data into a format suitable for the generative AI model and transmits the data periodically or when a specific trigger event occurs.

[0126] Input: User data stored in the database

[0127] Output: Formatted data sent to a generative AI model

[0128] Step 5: Data analysis

[0129] Generative AI models analyze the data they receive and learn user preferences and purchasing behavior patterns. They are built using machine learning libraries (e.g., TensorFlow, PyTorch) and trained on the data.

[0130] Input: Formatted user data

[0131] Output: Analysis results on user preferences and purchasing behavior

[0132] Step 6: Selecting recommended products

[0133] The generative AI model then selects the best products for the user based on the analysis results. For example, if a user purchases running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0134] Input: Analysis results

[0135] Output: A list of products that are best suited for the user

[0136] Step 7: Generate recommendations

[0137] The generative AI model generates recommendations based on the selected products. Recommendations can take the form of text, images, videos, etc. For example, it might generate a message like, "How about the perfect running socks to go with your new shoes?"

[0138] Input: Selected product list

[0139] Output: Generated recommendation content (text, images, videos)

[0140] Step 8: Notification of recommendation

[0141] The server sends the generated recommendations to the user's device via the API of the external communication tool, securely communicating using an API key or token.

[0142] Input: Generated recommendation

[0143] Output: Recommendation notification sent to the user's device

[0144] Step 9: Accepting user questions

[0145] After receiving a recommendation, users can ask additional questions or make suggestions by sending a text message through the messaging app.

[0146] Input: User question

[0147] Output: User's question received by the server

[0148] Step 10: Parsing the question and generating an answer

[0149] The server sends the user's question to the generative AI model, which analyzes the question and generates an appropriate answer or additional recommendations. For example, it generates an answer such as, "These running socks are available in sizes S, M, and L."

[0150] Input: User question

[0151] Output: Generated answers and additional recommendations

[0152] Step 11: Submit your response

[0153] The server sends the generated answer back to the user's device in real time, and the user receives the answer via a messaging application.

[0154] Input: The answer generated by the generative AI model

[0155] Output: The answer sent to the user's device

[0156] The above processing steps enable accurate collection and analysis of user purchasing behavior data, enabling personalized product recommendations and real-time dialogue.

[0157] (Application example 1)

[0158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] Traditional online shopping systems are limited to a single form of product recommendation for users and are unable to adapt to the environment in which the user is shopping. Furthermore, when users shop in a virtual reality environment, traditional systems lack real-time personalized recommendations and direct chat functionality, limiting the user experience. This makes it difficult for users to enjoy shopping as efficiently and effectively as they would in a physical store.

[0160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0161] In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, recommendation means for recommending optimal products to the user based on the analysis results, means for displaying products in a virtual reality environment, means for notifying the user of the recommended content via an external communication tool, and chat means for answering questions from the user in real time. This allows the user to receive personalized product recommendations in the virtual reality environment and further enables efficient shopping through real-time dialogue.

[0162] "User Data" means information related to a user's behavior on an online shopping site or virtual store, including, for example, purchase history, browsing history, and click history.

[0163] "Analytical means" means means, including artificial intelligence (AI), for analyzing collected user data, which is used to understand user preferences and purchasing patterns.

[0164] A "recommendation means" is a means for recommending optimal products to users based on analyzed data, and specifically provides recommended content to users in a format that includes text, images, videos, etc.

[0165] A "virtual reality environment" is an environment in which users shop in a virtual space using dedicated headsets or devices.

[0166] "External communication tools" are tools used to notify users of recommendations, and specifically include messaging applications.

[0167] The "chat tool" is a means for providing answers to user questions in real time, and works in conjunction with the generation AI to generate appropriate responses to user questions.

[0168] A system for implementing this invention enhances the online shopping experience by collecting user data, analyzing it, and providing personalized product recommendations in a virtual reality environment. The system includes the following components:

[0169] Hardware and Software Usage

[0170] Hardware:

[0171] VR headset: To realize the virtual reality environment, we use a general-purpose VR headset (e.g., Oculus Quest 2) as an example.

[0172] Smartphone: Use a standard smartphone (iPhone, Android) to receive notifications of recommendations.

[0173] software:

[0174] Generative AI (AI models): Use generative AI models, such as OpenAI GPT-4, to analyze user data and recommend products based on user preferences.

[0175] Server: A standard web server is used to collect, store, analyze, and notify data.

[0176] External communication tool: To notify the recommendation content, we use the API of a messaging application. In this example, we use a general-purpose messaging application.

[0177] Processing Description

[0178] Data collection and analysis

[0179] When a user accesses a virtual store, the server automatically collects user data (user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The collected data is sent to the generation AI for analysis, either periodically or when a specific trigger event occurs. The generation AI analyzes the user data and recognizes the user's preferences and purchasing behavior patterns.

[0180] Recommendation generation and notification

[0181] The AI ​​then selects the most suitable product for the user based on the analysis results and generates recommendations. These recommendations are provided in the form of text, images, and videos. The server then notifies the user of the recommendations created by the AI ​​via the API of an external communication tool.

[0182] Chat feature

[0183] If a user has a question about the recommended content, they can send it in chat format through a messaging application. This question is then sent to the AI ​​via the server, and the AI ​​generates an appropriate answer and sends it back to the user in real time via the server.

[0184] Specific examples

[0185] For example, if User A purchases running shoes in a virtual reality environment, the system operates as follows: The server collects User A's purchase information and stores it in a database. The collected data is then sent to the generation AI, which analyzes User A's preferences. The generation AI uses "running" as a keyword to select related products (e.g., running socks, running wear), and generates a recommendation message containing text and an image saying, "How about the perfect running socks to go with your new shoes?" The server notifies User A's device via the messaging application's API, and User A can receive the recommendation message on their smartphone or in the VR environment.

[0186] Example prompts for generative AI models

[0187] User's purchase history: {"item": "Running shoes", "date": "2023-01-15"}

[0188] User's browsing history: {"item": "Running wear", "date": "2023-01-14"}

[0189] User click history: {"item": "Running socks", "date": "2023-01-13"}

[0190] Recommend the best product for this user.

[0191] In this way, the system of the present invention can analyze user data and provide real-time personalized product recommendations in a virtual reality environment, allowing users to enjoy a more efficient and effective shopping experience.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] When a user accesses a virtual store, the server automatically collects user data (e.g., user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The input data is various user behavioral data, and based on this, the server manages the storage volume as database entries. At the same time, a timestamp of user activity is also recorded.

[0195] Step 2:

[0196] The server sends the collected user data to the generation AI for analysis periodically or when a specific trigger event occurs. The input for this process is the user data saved in step 1, and the output is the analysis results such as user preferences, purchasing behavior patterns, and purchase predictions recognized by the generation AI. The generation AI uses prompt statements to perform data analysis and returns the analysis results in text format to the server.

[0197] Step 3:

[0198] The server uses the generation AI to select the most suitable product for the user based on the analysis results from the generation AI. At this time, the generation AI is instructed to "recommend the most suitable product based on the user's purchase history, browsing history, and click history" using specific prompts. The output provided to the server is a list of candidate products and text and image links related to the recommended content.

[0199] Step 4:

[0200] The server uses the recommendation means to notify the user's device of the recommendation content created by the generation AI via the API of the external communication tool. At this time, the recommendation content obtained from the generation AI is used as input, and the recommendation information is notified in real time to the user's smartphone or VR headset as output. Specifically, the server generates an API request and pushes the recommendation content to the user's device.

[0201] Step 5:

[0202] The user checks the recommendations sent to their device and, if they have any questions, sends them in chat format using a messaging application. The input is a text message from the user, which is sent to the server via the messaging application. The server receives this message and forwards the question to the generation AI.

[0203] Step 6:

[0204] The generation AI generates appropriate answers based on questions received from users. The input is the user's question, and the output is the generated answer text. The generation AI analyzes past user data and the content of the question to generate an appropriate answer.

[0205] Step 7:

[0206] The server notifies the user of the answer generated by the AI ​​by sending the reply to the user's device in real time using an external communication tool. The input is the answer text from the AI, and the output is a text message displayed on the user's device. Specifically, the server generates an API request and sends a text message to the messaging application.

[0207] Through these seven steps, user data collection, analysis, personalized product recommendations, and real-time chat support are achieved, allowing users to enjoy an efficient and effective shopping experience even in a virtual reality environment.

[0208] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0209] The present invention is a personalized recommendation system for improving a user's online shopping experience, and is characterized in that it incorporates an emotion engine that recognizes the user's emotions. Embodiments of the present invention are described below.

[0210] System Configuration

[0211] 1. Collection of User Data

[0212] When a user accesses an online shopping site, the server automatically collects data such as the user ID, browsing history, purchase history, and click history, and stores it in a database.

[0213] 2. Data Analysis

[0214] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[0215] Generative AI analyzes user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that that brand's products are likely to be preferred.

[0216] 3. Emotional Data Collection and Analysis

[0217] The server collects sentiment data from users' real-time text messages and reviews.

[0218] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[0219] 4. Generating Recommendations

[0220] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[0221] The generative AI takes into account the user's emotional state and generates recommendations with an appropriate tone and content. For example, if the user is expressing joy, the recommendations will include positive messages.

[0222] 5. Notification

[0223] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[0224] 6. Chat integration

[0225] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[0226] The server receives messages from users and sends the content to the generation AI and emotion engine.

[0227] The generative AI and emotion engine analyze the user's questions and emotions, generate appropriate answers and additional recommendations, and send them back to the user's device in real time via the server.

[0228] Example: System behavior when user B purchases running shoes

[0229] As an example, we will explain the system flow when User B purchases running shoes on an online shopping site.

[0230] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[0231] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[0232] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[0233] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[0234] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[0235] 6. The server notifies User B of this recommendation via the API of the external communication tool. User B receives this recommendation via a messaging application such as LINE.

[0236] 7. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[0237] 8. The server receives the question and sends it to the generative AI and emotion engine.

[0238] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[0239] In this way, the system according to the present invention analyzes user purchasing behavior data and emotional data and provides personalized product recommendations in real time, thereby significantly improving the online shopping experience.

[0240] The processing flow will be explained below.

[0241] Step 1:

[0242] The device accesses an online shopping site, where the user browses or purchases products.

[0243] Step 2:

[0244] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[0245] Step 3:

[0246] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[0247] Step 4:

[0248] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[0249] Step 5:

[0250] The server retrieves users' real-time text messages and reviews and sends them to the emotion engine.

[0251] Step 6:

[0252] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[0253] Step 7:

[0254] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[0255] Step 8:

[0256] The AI ​​generator generates recommendations with appropriate tone and content, taking into account the user's emotional state. For example, if the user is expressing joy, the recommendation will include positive messages.

[0257] Step 9:

[0258] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application).

[0259] Step 10:

[0260] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[0261] Step 11:

[0262] The server receives questions from users and sends them to the generative AI and emotion engine.

[0263] Step 12:

[0264] The generative AI and emotion engine analyzes the user's question and emotion, generating appropriate answers and emotionally sensitive explanations.

[0265] Step 13:

[0266] The server sends the generated answers back to the user's device in real time via the API of the external communication tool.

[0267] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[0268] Example 2

[0269] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0270] Conventional online shopping systems sometimes recommend products based on a user's preferences and purchasing patterns, but they fail to consider the user's emotional state. As a result, recommendations are sometimes made at inappropriate times or with inappropriate tones, leading to a loss of motivation or dissatisfaction. Furthermore, the lack of a means to quickly and appropriately respond to questions or additional suggestions leads to a poor user experience.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0272] In this invention, the server includes means for collecting user online activity data, means for storing the collected user data in a database, and analysis means including a generative artificial intelligence (AI) for analyzing the stored user data, which enables means for collecting emotion data from the analyzed user data, means for analyzing the collected emotion data, means for recommending optimal products taking the user's emotions into consideration based on the analysis results, means for notifying the user of the recommended content via the API of an external communication tool, and chat means for answering questions from users in real time.

[0273] "User online activity data" refers to data such as user ID, browsing history, purchase history, and click history that is recorded when a user accesses an online shopping site.

[0274] A "database" is a data storage device that systematically stores collected user data, making it easy to analyze and search later.

[0275] "Generative artificial intelligence (AI)" is a system that uses advanced analytical algorithms to analyze user data and recognize and understand user preferences and purchasing patterns.

[0276] "Emotional Data" means data that indicates a user's emotional state (e.g., joy, sadness, surprise, etc.) extracted from a user's real-time text messages or reviews.

[0277] An "emotion engine" is a software or hardware system for analyzing collected emotion data and identifying a user's emotional state.

[0278] The "means for recommending optimal products" is a system that has the function of selecting and recommending the most suitable products for users based on analyzed user data and emotional data.

[0279] An "API for external communication tools" is an interface for communicating data between the system and the user's device using a messaging application or other external communication tool.

[0280] A "chat means" is a system with a communication function that responds in real time to questions and additional suggestions from users and provides appropriate answers and additional recommendations.

[0281] This invention provides a personalized recommendation system that utilizes generative AI models and emotion engines to improve users' online shopping experience. By collecting and analyzing users' online activity data and emotion data, the system can recommend the most suitable products to users, significantly improving the user experience.

[0282] System Configuration

[0283] The system includes the following main hardware and software:

[0284] 1. Server:

[0285] It has the ability to collect users' online activity data (e.g., user ID, browsing history, purchase history, click history, etc.) and store it in a database.

[0286] The collected data is sent to and analyzed by Generative Artificial Intelligence (AI), which identifies user preferences and purchasing patterns.

[0287] 2. Database:

[0288] Systematically store collected online activity data, which can then be accessed and analyzed by the generative AI and emotion engine.

[0289] 3. Generation AI:

[0290] By analyzing user data and learning about user preferences and purchasing behavior patterns, the Generative AI generates personalized product recommendations based on the user's purchase and browsing history.

[0291] 4. Emotion Engine:

[0292] It collects sentiment data from users' real-time text messages and reviews and analyzes that data.

[0293] The emotion engine identifies whether the user is expressing emotions such as happiness, sadness, or surprise, and provides this emotional information to the generative AI.

[0294] 5. API for external communication tools:

[0295] It acts as an interface to notify users of the recommended content. As a result, the recommendations generated by the generative AI and emotion engine are sent to the user's device via an external messaging application (e.g., LINE or WhatsApp).

[0296] 6. User Device:

[0297] The device through which users receive recommendations and send questions or additional suggestions. Devices include smartphones, tablets, and PCs.

[0298] Specific examples

[0299] Here is a specific example where User B purchases running shoes on an online shopping site.

[0300] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[0301] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[0302] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[0303] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[0304] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[0305] 6. The server notifies User B of the recommendation via the API of the external communication tool. User B receives the recommendation via a messaging application.

[0306] 7. The user is interested in the recommendation and sends a message asking, "What size are these socks?"

[0307] 8. The server receives the question and sends it to the generative AI and emotion engine.

[0308] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[0309] Prompt Sentence Examples

[0310] "After User B purchases running shoes, recommend the best running socks as the next product with a positive message."

[0311] Thus, the present invention is a system that significantly improves the online shopping experience by analyzing users' purchasing behavior and emotions and providing personalized product recommendations in real time.

[0312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0313] Step 1:

[0314] Input: User ID, browsing history, purchase history, click history when the user accesses an online shopping site

[0315] Operation:

[0316] When a user accesses an online shopping site, the server collects data in real time, such as the user ID, browsing history, purchase history, click history, etc. For example, if a user views a page for "running shoes," that information will be recorded.

[0317] Output: Collected user data is stored in a database.

[0318] Step 2:

[0319] Input: User data stored in the database

[0320] Operation:

[0321] The server sends the stored user data to the generation AI periodically or in response to a specific trigger event (e.g., product purchase).

[0322] Output: User data is provided to the generative AI for analysis.

[0323] Step 3:

[0324] Input: User data provided to the generative AI

[0325] Operation:

[0326] The Generative AI analyzes the provided user data and recognizes the user's preferences and purchasing behavior patterns. Specifically, it learns the trends of frequently purchased brands and products. For example, if User B has purchased "running shoes" multiple times in the past, it can identify their preferences.

[0327] Output: Analysis of user preferences and purchasing patterns

[0328] Step 4:

[0329] Input: Real-time text messages and reviews

[0330] Operation:

[0331] The server collects real-time text messages and reviews posted by users. For example, if a user posts a review saying, "These running shoes are great!", the server records the text data.

[0332] Output: Collected text data

[0333] Step 5:

[0334] Input: Collected text data

[0335] Operation:

[0336] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.). For example, it identifies positive emotions from the keyword "great."

[0337] Output: Parsed user sentiment data

[0338] Step 6:

[0339] Input: Preference analysis results from generative AI and emotional data from the emotion engine

[0340] Operation:

[0341] The generative AI and emotion engine work together to select the best products for the user based on the analysis results and generate recommendations. For example, if a user purchases running shoes, related running socks and apparel will be recommended. If the user expresses positive emotions, the recommendation message will also be positive.

[0342] Output: Generated recommendations

[0343] Step 7:

[0344] Input: Generated recommendation

[0345] Operation:

[0346] The server then sends the generated recommendations to the user's device via the API of an external communication tool, for example, by sending a message about the recommended products using LINE or WhatsApp.

[0347] Output: Recommendations sent to the user's device

[0348] Step 8:

[0349] Input: User message with questions or additional suggestions

[0350] Operation:

[0351] If a user has questions or additional suggestions after receiving a recommendation, they can send a chat question through a messaging application, such as "What size are these socks?"

[0352] Output: A message from the user is sent to the server.

[0353] Step 9:

[0354] Input: Message sent by the user

[0355] Operation:

[0356] The server receives the user's question and sends it to the generative AI and emotion engine.

[0357] Output: Data is provided to the generative AI and emotion engine for analysis.

[0358] Step 10:

[0359] Input: User question and sentiment data

[0360] Operation:

[0361] The generative AI and emotion engine analyze the user's question and emotion to generate appropriate answers and additional recommendations, such as, "These socks fit you perfectly in size medium. We also recommend the same series of running wear."

[0362] Output: Generated answers and additional recommendations

[0363] Step 11:

[0364] Input: Generated answers and additional recommendations

[0365] Operation:

[0366] The server sends the generated answers to the user's device in real time.

[0367] Output: The appropriate answer and additional recommendations sent to the user's device

[0368] Through this series of processing steps, personalized product recommendations based on users' purchasing behavior and emotions can be provided in real time, greatly improving the online shopping experience.

[0369] (Application example 2)

[0370] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0371] In online shopping, it is difficult to recommend products that fully take into account the user's individual needs and emotional state. Current systems mainly make simple recommendations based on the user's purchase and browsing history, which does not improve user satisfaction. It is also difficult to provide immediate and appropriate responses to user questions and requests.

[0372] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, means for collecting and analyzing user emotion data, recommendation means for recommending optimal products to the user based on the analysis results and the emotion data, means for notifying the user of the recommendation content via an external communication tool, and chat means for answering questions from the user in real time. This makes it possible to provide personalized recommendations based on the user's preferences and emotional state, and to provide immediate and appropriate responses.

[0373] "User data" refers to information related to online shopping, such as user ID, browsing history, purchase history, and click history.

[0374] "Generative artificial intelligence (AI)" refers to an artificial intelligence technology that analyzes user preferences and purchasing behavior patterns based on large amounts of data and makes optimal recommendations.

[0375] "Analysis Means" means a system or device for analyzing collected User Data.

[0376] "Emotional data" refers to information about a user's emotional state (such as joy, sadness, or surprise) obtained from their text messages, reviews, etc.

[0377] "Recommendation Means" means a system or function for selecting and recommending optimal products to a user based on analyzed user data and emotional data.

[0378] "External communication tools" refers to tools such as messaging applications and emails used to notify users of recommendations.

[0379] "Notification Means" means a system or function for sending recommendations to users via external communication tools.

[0380] "Chat means" means a system or function that provides real-time responses to user questions.

[0381] The present invention is a personalized recommendation system for improving a user's online shopping experience, and in particular, incorporates an emotion engine that recognizes a user's emotions. Specific embodiments of the present invention are described below.

[0382] First, the server collects user data, including user ID, browsing history, purchase history, click history, etc. This data is stored in Amazon RDS.

[0383] The server then periodically sends the data to the Generator AI, either periodically or upon specific trigger events (such as when a product is purchased). The Generator AI uses OpenAI GPT-4 to analyze the user data and recognize their preferences and purchasing patterns.

[0384] The server then collects sentiment data from user reviews and in-app messages, and uses IBM Watson Tone Analyzer as an emotion engine to analyze the collected text data and identify the user's emotional state (e.g., joy, sadness, surprise).

[0385] Based on the analyzed user preferences and emotional data, the generative AI and emotion engine work together to recommend the most suitable products to the user.The recommendations are generated with an appropriate tone and content and sent to the user's smartphone using an external communication tool (such as Twilio API for SMS or LINE Messaging API).

[0386] Users may receive a notification, become interested in the content, and submit a follow-up question. In this case, the server receives the question and sends it to the generation AI and emotion engine. The generation AI and emotion engine analyze the question, generate an appropriate answer, and send it back to the user's smartphone in real time.

[0387] As a concrete example, consider a situation where a user asks a question on LINE, such as "Tell me more about this product." An example of a prompt sentence for this situation would be as follows:

[0388] A user asked a question about a specific product. Product ID:

[12345] Question: "Tell me more about this product"

[0389] An example of the generated AI's response is as follows:

[0390] Hello! These are our latest running shoes, made with lightweight, breathable materials. They fit particularly well and are ideal for long-distance running. They are available in sizes from 22cm to 30cm and in a wide range of colors. If you're interested, you can purchase them here.

[0391] In this way, the system according to the present invention can analyze users' purchasing behavior data and emotional data and provide personalized recommendations in real time, thereby significantly improving the online shopping experience.

[0392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0393] Step 1:

[0394] User Data Collection

[0395] The server collects user data (user ID, browsing history, purchase history, click history, etc.) every time a user logs in and performs an operation, and stores the data in Amazon RDS. The input is the user operation data, and the output is the stored data.

[0396] Step 2:

[0397] Regular analysis of user data

[0398] The server sends the collected data to OpenAI GPT-4 periodically or upon specific trigger events (e.g., when a product is purchased). The input is user data stored in Amazon RDS, and the output is the analyzed user preferences and purchasing behavior patterns.

[0399] Step 3:

[0400] Collecting Emotional Data

[0401] The server collects sentiment data from user reviews and in-app messages. The input is the reviews and messages posted by users, and the output is the text data.

[0402] Step 4:

[0403] Emotional Data Analysis

[0404] The server sends the collected text data to IBM Watson Tone Analyzer to identify the user's emotional state. The input is the text data of reviews and messages, and the output is the analyzed emotional data (e.g., joy, sadness, surprise, etc.).

[0405] Step 5:

[0406] Recommendation generation

[0407] The generative AI (OpenAI GPT-4) and the emotion engine (IBM Watson Tone Analyzer) work together to select the best products for users based on user data and emotion data. The input is analyzed user preferences and emotion data, and the output is personalized recommendations.

[0408] Step 6:

[0409] Notification of recommendation

[0410] The server uses the Twilio API or LINE Messaging API to notify the user of the generated recommendation content on their smartphone. The input is the generated recommendation content, and the output is a notification sent to the user's smartphone.

[0411] Step 7:

[0412] Receiving and sending user questions

[0413] When a user submits a question in response to a recommendation, the server receives it and sends the question to OpenAI GPT-4 and IBM Watson Tone Analyzer. The input is the question from the user, and the output is sent to the generative AI and emotion engine.

[0414] Step 8:

[0415] Generate answers to questions

[0416] The generative AI and emotion engine analyze the question, generate an appropriate answer, and send it to the server. The input is the user's question, past data, and emotional state, and the output is the generated answer.

[0417] Step 9:

[0418] Notification of response

[0419] The server notifies the user's smartphone of the answers generated by the generative AI and emotion engine via the Twilio API or LINE Messaging API. The input is the generated answer, and the output is the notification sent to the user's smartphone.

[0420] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0421] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0422] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0426] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0427] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0428] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0429] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0430] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0431] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0432] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0433] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0434] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0435] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0436] The present invention is a personalized recommendation system for improving a user's online shopping experience, which is implemented as follows.

[0437] System Configuration

[0438] 1. Collection of User Data

[0439] When a user accesses an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history.

[0440] 2. Data Analysis

[0441] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[0442] Generative AI analyzes user data and recognizes user preferences and purchasing patterns. For example, it determines that a user who frequently purchases shoes from a particular brand will prefer that brand's products.

[0443] 3. Generating Recommendations

[0444] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0445] The generative AI generates specific recommendations for the selected products, which are presented in the form of empathetic and logical text, images, videos, etc.

[0446] 4. Notification

[0447] The server sends the recommendations created by the AI ​​to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[0448] 5. Chat integration

[0449] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[0450] The server receives messages from users and sends the contents to the generation AI.

[0451] The generative AI analyzes the user's question, generates appropriate answers and additional recommendations, and sends them back to the user's device in real time via the server.

[0452] Example: System behavior when user A purchases running shoes

[0453] As an example, we will explain the system flow when user A purchases running shoes on an online shopping site.

[0454] 1. The server collects user A's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[0455] 2. The server also sends User A's past purchasing history and browsing history to the generation AI.

[0456] 3. The generation AI analyzes User A's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[0457] 4. The generative AI generates recommendations consisting of empathetic and logical text and images, such as, "How about the perfect running socks to go with your new shoes?"

[0458] 5. The server notifies User A's device of this recommendation via the API of the external communication tool. User A receives this recommendation via a messaging application such as LINE.

[0459] 6. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[0460] 7. The server receives the question and sends it to the generating AI.

[0461] 8. The generation AI generates appropriate size information in response to User A's question and returns it to User A's device in real time via the server.

[0462] In this way, the system according to the present invention analyzes user purchasing behavior data and provides personalized product recommendations in real time, thereby improving the online shopping experience.

[0463] The processing flow will be explained below.

[0464] Step 1:

[0465] The device accesses an online shopping site, where the user browses or purchases products.

[0466] Step 2:

[0467] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[0468] Step 3:

[0469] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[0470] Step 4:

[0471] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[0472] Step 5:

[0473] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0474] Step 6:

[0475] The generative AI generates specific recommendations (e.g., text, images, and videos that are both empathetic and logical) for the selected products. Specifically, it creates content such as, "How about the perfect running socks to go with your new shoes?"

[0476] Step 7:

[0477] The server sends the recommendations created by the generation AI to the user's device via the API of an external communication tool (e.g., a messaging application).

[0478] Step 8:

[0479] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[0480] Step 9:

[0481] The server receives questions from users and sends the content to the generation AI.

[0482] Step 10:

[0483] The generative AI analyzes the user's question and generates an appropriate answer (e.g., sock size information).

[0484] Step 11:

[0485] The server sends the answers generated by the generation AI back to the user's device in real time via the API of an external communication tool.

[0486] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[0487] Example 1

[0488] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] In conventional online shopping systems, product recommendations to users are made in a general and inefficient manner, making it difficult to make personalized recommendations based on individual users' preferences and purchasing behavior patterns. Furthermore, few systems have the ability to accurately respond to user questions in real time, which can lead to a poor user experience. To address these issues, a system is needed that can effectively collect and analyze user data, generate personalized recommendations, and notify users promptly and appropriately.

[0490] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0491] In this invention, the server includes means for collecting user data, means for periodically or upon the occurrence of a specific trigger event, transmitting the collected user data to the generative AI model for analysis, means for selecting the most suitable product for the user based on the analysis results of the generative AI model and creating recommendations, means for notifying the user of the created recommendations via the API of an external communication tool, and means for accepting questions from users, transmitting them to the generative AI model, and returning the answers generated by the generative AI model to the user in real time. This enables accurate collection and analysis of user data, and the creation and notification of personalized recommendations, improving the user experience.

[0492] "User data" refers to data such as a user's access, browsing, purchase, and click history on an online shopping site, as well as user ID, purchase date and time, and payment information.

[0493] A "generative AI model" is an artificial intelligence model that analyzes user data and recognizes user preferences and purchasing behavior patterns.

[0494] "Trigger Event" means a specific event or condition that causes data to be analyzed or transmitted, such as the moment a user purchases a product or after a certain period of time has passed.

[0495] "External communication tools" are tools, including messaging applications and social networking platforms, used to transmit information between servers and users.

[0496] "API" stands for Application Programming Interface, an interface that enables data exchange between different software systems.

[0497] "Real-time" means that information is processed and provided to users immediately, without delay.

[0498] "Recommendation content" refers to information about products and services that the generative AI model suggests to users based on the results of analyzing user data, and is provided in the form of text, images, videos, etc.

[0499] This invention is a personalized recommendation system for improving users' online shopping experiences. The system collects user data through multiple means, analyzes the data using a generative AI model, recommends optimal products, and provides the ability to interact with users in real time.

[0500] User Data Collection

[0501] When a user visits an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history. This includes monitoring and collecting user behavior in real time using technologies such as JavaScript and tracking pixels. For example, when a user views or clicks on a particular product page, that data is immediately sent to the server.

[0502] Data analysis

[0503] The server stores the collected user data in a database. The stored data is automatically sent to the generative AI model periodically or when a specific trigger event occurs. The generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. This allows for advanced analysis of user preferences and purchasing behavior patterns.

[0504] Recommendation generation

[0505] The generative AI model uses analyzed user data to select the most suitable products for each user and generate specific recommendations. These recommendations can include text, images, videos, and other formats, and are both empathetic and logical. For example, if a user purchases new running shoes, the model generates empathetic messages suggesting related products (e.g., running socks, running apparel, etc.).

[0506] Notification of recommendation

[0507] The server sends the generated recommendation to the user's device via the API of an external communication tool (e.g., LINE or Facebook Messenger). This allows the user to receive the recommendation in real time. For example, a LINE notification might display a message such as, "How about finding the perfect running socks to go with your new shoes?"

[0508] Chat function integration

[0509] After receiving the recommendations, users can ask additional questions or make suggestions. When a question is sent through a messaging application, the server sends it to the generative AI model. The generative AI model analyzes the user's question and generates an appropriate answer or additional recommendations. The generated answer is immediately sent back to the user's device via the server. For example, if a user asks, "What size are these socks?", a real-time answer such as, "These running socks are available in S, M, and L sizes" is provided.

[0510] Specific examples

[0511] An example of a specific prompt might be, "A user has purchased running shoes. Please generate text and images that recommend products related to this user."

[0512] Thus, the present invention aims to collect and analyze user purchasing behavior data, provide personalized product recommendations in real time, and improve user experience.

[0513] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0514] Step 1: Collect user data

[0515] When a user visits an online shopping site, the server automatically starts a session and collects the user ID, browsing history, and click history. Specifically, it records the product pages the user viewed and the links they clicked using JavaScript and tracking pixels.

[0516] Input: Behavioral data when users visit the site

[0517] Output: Collected user ID, browsing history, click history

[0518] Step 2: Collect your purchase history

[0519] When a user purchases a product, the server collects data such as the purchased product, purchase date and time, and payment information. This data is obtained through the confirmation page displayed when the purchase is completed and through APIs.

[0520] Input: Product information purchased by the user

[0521] Output: Collected purchased items, purchase date and time, payment information

[0522] Step 3: Save your data

[0523] The server stores the collected user behavior and purchase data in a main database, and organizes the data using a database management system (e.g., MySQL, PostgreSQL).

[0524] Input: Collected user behavior and purchase data

[0525] Output: Saved database records

[0526] Step 4: Prepare and send data

[0527] The server converts the stored data into a format suitable for the generative AI model and transmits the data periodically or when a specific trigger event occurs.

[0528] Input: User data stored in the database

[0529] Output: Formatted data sent to a generative AI model

[0530] Step 5: Data analysis

[0531] Generative AI models analyze the data they receive and learn user preferences and purchasing behavior patterns. They are built using machine learning libraries (e.g., TensorFlow, PyTorch) and trained on the data.

[0532] Input: Formatted user data

[0533] Output: Analysis results on user preferences and purchasing behavior

[0534] Step 6: Selecting recommended products

[0535] The generative AI model then selects the best products for the user based on the analysis results. For example, if a user purchases running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0536] Input: Analysis results

[0537] Output: A list of products that are best suited for the user

[0538] Step 7: Generate recommendations

[0539] The generative AI model generates recommendations based on the selected products. Recommendations can take the form of text, images, videos, etc. For example, it might generate a message like, "How about the perfect running socks to go with your new shoes?"

[0540] Input: Selected product list

[0541] Output: Generated recommendation content (text, images, videos)

[0542] Step 8: Notification of recommendation

[0543] The server sends the generated recommendations to the user's device via the API of the external communication tool, securely communicating using an API key or token.

[0544] Input: Generated recommendation

[0545] Output: Recommendation notification sent to the user's device

[0546] Step 9: Accepting user questions

[0547] After receiving a recommendation, users can ask additional questions or make suggestions by sending a text message through the messaging app.

[0548] Input: User question

[0549] Output: User's question received by the server

[0550] Step 10: Parsing the question and generating an answer

[0551] The server sends the user's question to the generative AI model, which analyzes the question and generates an appropriate answer or additional recommendations. For example, it generates an answer such as, "These running socks are available in sizes S, M, and L."

[0552] Input: User question

[0553] Output: Generated answers and additional recommendations

[0554] Step 11: Submit your response

[0555] The server sends the generated answer back to the user's device in real time, and the user receives the answer via a messaging application.

[0556] Input: The answer generated by the generative AI model

[0557] Output: The answer sent to the user's device

[0558] The above processing steps enable accurate collection and analysis of user purchasing behavior data, enabling personalized product recommendations and real-time dialogue.

[0559] (Application example 1)

[0560] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0561] Traditional online shopping systems are limited to a single form of product recommendation for users and are unable to adapt to the environment in which the user is shopping. Furthermore, when users shop in a virtual reality environment, traditional systems lack real-time personalized recommendations and direct chat functionality, limiting the user experience. This makes it difficult for users to enjoy shopping as efficiently and effectively as they would in a physical store.

[0562] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0563] In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, recommendation means for recommending optimal products to the user based on the analysis results, means for displaying products in a virtual reality environment, means for notifying the user of the recommended content via an external communication tool, and chat means for answering questions from the user in real time. This allows the user to receive personalized product recommendations in the virtual reality environment and further enables efficient shopping through real-time dialogue.

[0564] "User Data" means information related to a user's behavior on an online shopping site or virtual store, including, for example, purchase history, browsing history, and click history.

[0565] "Analytical means" means means, including artificial intelligence (AI), for analyzing collected user data, which is used to understand user preferences and purchasing patterns.

[0566] A "recommendation means" is a means for recommending optimal products to users based on analyzed data, and specifically provides recommended content to users in a format that includes text, images, videos, etc.

[0567] A "virtual reality environment" is an environment in which users shop in a virtual space using dedicated headsets or devices.

[0568] "External communication tools" are tools used to notify users of recommendations, and specifically include messaging applications.

[0569] The "chat tool" is a means for providing answers to user questions in real time, and works in conjunction with the generation AI to generate appropriate responses to user questions.

[0570] A system for implementing this invention enhances the online shopping experience by collecting user data, analyzing it, and providing personalized product recommendations in a virtual reality environment. The system includes the following components:

[0571] Hardware and Software Usage

[0572] Hardware:

[0573] VR headset: To realize the virtual reality environment, we use a general-purpose VR headset (e.g., Oculus Quest 2) as an example.

[0574] Smartphone: Use a standard smartphone (iPhone, Android) to receive notifications of recommendations.

[0575] software:

[0576] Generative AI (AI models): Use generative AI models, such as OpenAI GPT-4, to analyze user data and recommend products based on user preferences.

[0577] Server: A standard web server is used to collect, store, analyze, and notify data.

[0578] External communication tool: To notify the recommendation content, we use the API of a messaging application. In this example, we use a general-purpose messaging application.

[0579] Processing Description

[0580] Data collection and analysis

[0581] When a user accesses a virtual store, the server automatically collects user data (user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The collected data is sent to the generation AI for analysis, either periodically or when a specific trigger event occurs. The generation AI analyzes the user data and recognizes the user's preferences and purchasing behavior patterns.

[0582] Recommendation generation and notification

[0583] The AI ​​then selects the most suitable product for the user based on the analysis results and generates recommendations. These recommendations are provided in the form of text, images, and videos. The server then notifies the user of the recommendations created by the AI ​​via the API of an external communication tool.

[0584] Chat feature

[0585] If a user has a question about the recommended content, they can send it in chat format through a messaging application. This question is then sent to the AI ​​via the server, and the AI ​​generates an appropriate answer and sends it back to the user in real time via the server.

[0586] Specific examples

[0587] For example, if User A purchases running shoes in a virtual reality environment, the system operates as follows: The server collects User A's purchase information and stores it in a database. The collected data is then sent to the generation AI, which analyzes User A's preferences. The generation AI uses "running" as a keyword to select related products (e.g., running socks, running wear), and generates a recommendation message containing text and an image saying, "How about the perfect running socks to go with your new shoes?" The server notifies User A's device via the messaging application's API, and User A can receive the recommendation message on their smartphone or in the VR environment.

[0588] Example prompts for generative AI models

[0589] User's purchase history: {"item": "Running shoes", "date": "2023-01-15"}

[0590] User's browsing history: {"item": "Running wear", "date": "2023-01-14"}

[0591] User click history: {"item": "Running socks", "date": "2023-01-13"}

[0592] Recommend the best product for this user.

[0593] In this way, the system of the present invention can analyze user data and provide real-time personalized product recommendations in a virtual reality environment, allowing users to enjoy a more efficient and effective shopping experience.

[0594] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0595] Step 1:

[0596] When a user accesses a virtual store, the server automatically collects user data (e.g., user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The input data is various user behavioral data, and based on this, the server manages the storage volume as database entries. At the same time, a timestamp of user activity is also recorded.

[0597] Step 2:

[0598] The server sends the collected user data to the generation AI for analysis periodically or when a specific trigger event occurs. The input for this process is the user data saved in step 1, and the output is the analysis results such as user preferences, purchasing behavior patterns, and purchase predictions recognized by the generation AI. The generation AI uses prompt statements to perform data analysis and returns the analysis results in text format to the server.

[0599] Step 3:

[0600] The server uses the generation AI to select the most suitable product for the user based on the analysis results from the generation AI. At this time, the generation AI is instructed to "recommend the most suitable product based on the user's purchase history, browsing history, and click history" using specific prompts. The output provided to the server is a list of candidate products and text and image links related to the recommended content.

[0601] Step 4:

[0602] The server uses the recommendation means to notify the user's device of the recommendation content created by the generation AI via the API of the external communication tool. At this time, the recommendation content obtained from the generation AI is used as input, and the recommendation information is notified in real time to the user's smartphone or VR headset as output. Specifically, the server generates an API request and pushes the recommendation content to the user's device.

[0603] Step 5:

[0604] The user checks the recommendations sent to their device and, if they have any questions, sends them in chat format using a messaging application. The input is a text message from the user, which is sent to the server via the messaging application. The server receives this message and forwards the question to the generation AI.

[0605] Step 6:

[0606] The generation AI generates appropriate answers based on questions received from users. The input is the user's question, and the output is the generated answer text. The generation AI analyzes past user data and the content of the question to generate an appropriate answer.

[0607] Step 7:

[0608] The server notifies the user of the answer generated by the AI ​​by sending the reply to the user's device in real time using an external communication tool. The input is the answer text from the AI, and the output is a text message displayed on the user's device. Specifically, the server generates an API request and sends a text message to the messaging application.

[0609] Through these seven steps, user data collection, analysis, personalized product recommendations, and real-time chat support are achieved, allowing users to enjoy an efficient and effective shopping experience even in a virtual reality environment.

[0610] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0611] The present invention is a personalized recommendation system for improving a user's online shopping experience, and is characterized in that it incorporates an emotion engine that recognizes the user's emotions. Embodiments of the present invention are described below.

[0612] System Configuration

[0613] 1. Collection of User Data

[0614] When a user accesses an online shopping site, the server automatically collects data such as the user ID, browsing history, purchase history, and click history, and stores it in a database.

[0615] 2. Data Analysis

[0616] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[0617] Generative AI analyzes user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that that brand's products are likely to be preferred.

[0618] 3. Emotional Data Collection and Analysis

[0619] The server collects sentiment data from users' real-time text messages and reviews.

[0620] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[0621] 4. Generating Recommendations

[0622] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[0623] The generative AI takes into account the user's emotional state and generates recommendations with an appropriate tone and content. For example, if the user is expressing joy, the recommendations will include positive messages.

[0624] 5. Notification

[0625] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[0626] 6. Chat integration

[0627] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[0628] The server receives messages from users and sends the content to the generation AI and emotion engine.

[0629] The generative AI and emotion engine analyze the user's questions and emotions, generate appropriate answers and additional recommendations, and send them back to the user's device in real time via the server.

[0630] Example: System behavior when user B purchases running shoes

[0631] As an example, we will explain the system flow when User B purchases running shoes on an online shopping site.

[0632] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[0633] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[0634] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[0635] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[0636] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[0637] 6. The server notifies User B of this recommendation via the API of the external communication tool. User B receives this recommendation via a messaging application such as LINE.

[0638] 7. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[0639] 8. The server receives the question and sends it to the generative AI and emotion engine.

[0640] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[0641] In this way, the system according to the present invention analyzes user purchasing behavior data and emotional data and provides personalized product recommendations in real time, thereby significantly improving the online shopping experience.

[0642] The processing flow will be explained below.

[0643] Step 1:

[0644] The device accesses an online shopping site, where the user browses or purchases products.

[0645] Step 2:

[0646] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[0647] Step 3:

[0648] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[0649] Step 4:

[0650] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[0651] Step 5:

[0652] The server retrieves users' real-time text messages and reviews and sends them to the emotion engine.

[0653] Step 6:

[0654] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[0655] Step 7:

[0656] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[0657] Step 8:

[0658] The AI ​​generator generates recommendations with appropriate tone and content, taking into account the user's emotional state. For example, if the user is expressing joy, the recommendation will include positive messages.

[0659] Step 9:

[0660] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application).

[0661] Step 10:

[0662] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[0663] Step 11:

[0664] The server receives questions from users and sends them to the generative AI and emotion engine.

[0665] Step 12:

[0666] The generative AI and emotion engine analyzes the user's question and emotion, generating appropriate answers and emotionally sensitive explanations.

[0667] Step 13:

[0668] The server sends the generated answers back to the user's device in real time via the API of the external communication tool.

[0669] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[0670] Example 2

[0671] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0672] Conventional online shopping systems sometimes recommend products based on a user's preferences and purchasing patterns, but they fail to consider the user's emotional state. As a result, recommendations are sometimes made at inappropriate times or with inappropriate tones, leading to a loss of motivation or dissatisfaction. Furthermore, the lack of a means to quickly and appropriately respond to questions or additional suggestions leads to a poor user experience.

[0673] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0674] In this invention, the server includes means for collecting user online activity data, means for storing the collected user data in a database, and analysis means including a generative artificial intelligence (AI) for analyzing the stored user data, which enables means for collecting emotion data from the analyzed user data, means for analyzing the collected emotion data, means for recommending optimal products taking the user's emotions into consideration based on the analysis results, means for notifying the user of the recommended content via the API of an external communication tool, and chat means for answering questions from users in real time.

[0675] "User online activity data" refers to data such as user ID, browsing history, purchase history, and click history that is recorded when a user accesses an online shopping site.

[0676] A "database" is a data storage device that systematically stores collected user data, making it easy to analyze and search later.

[0677] "Generative artificial intelligence (AI)" is a system that uses advanced analytical algorithms to analyze user data and recognize and understand user preferences and purchasing patterns.

[0678] "Emotional Data" means data that indicates a user's emotional state (e.g., joy, sadness, surprise, etc.) extracted from a user's real-time text messages or reviews.

[0679] An "emotion engine" is a software or hardware system for analyzing collected emotion data and identifying a user's emotional state.

[0680] The "means for recommending optimal products" is a system that has the function of selecting and recommending the most suitable products for users based on analyzed user data and emotional data.

[0681] An "API for external communication tools" is an interface for communicating data between the system and the user's device using a messaging application or other external communication tool.

[0682] A "chat means" is a system with a communication function that responds in real time to questions and additional suggestions from users and provides appropriate answers and additional recommendations.

[0683] This invention provides a personalized recommendation system that utilizes generative AI models and emotion engines to improve users' online shopping experience. By collecting and analyzing users' online activity data and emotion data, the system can recommend the most suitable products to users, significantly improving the user experience.

[0684] System Configuration

[0685] The system includes the following main hardware and software:

[0686] 1. Server:

[0687] It has the ability to collect users' online activity data (e.g., user ID, browsing history, purchase history, click history, etc.) and store it in a database.

[0688] The collected data is sent to and analyzed by Generative Artificial Intelligence (AI), which identifies user preferences and purchasing patterns.

[0689] 2. Database:

[0690] Systematically store collected online activity data, which can then be accessed and analyzed by the generative AI and emotion engine.

[0691] 3. Generation AI:

[0692] By analyzing user data and learning about user preferences and purchasing behavior patterns, the Generative AI generates personalized product recommendations based on the user's purchase and browsing history.

[0693] 4. Emotion Engine:

[0694] It collects sentiment data from users' real-time text messages and reviews and analyzes that data.

[0695] The emotion engine identifies whether the user is expressing emotions such as happiness, sadness, or surprise, and provides this emotional information to the generative AI.

[0696] 5. API for external communication tools:

[0697] It acts as an interface to notify users of the recommended content. As a result, the recommendations generated by the generative AI and emotion engine are sent to the user's device via an external messaging application (e.g., LINE or WhatsApp).

[0698] 6. User Device:

[0699] The device through which users receive recommendations and send questions or additional suggestions. Devices include smartphones, tablets, and PCs.

[0700] Specific examples

[0701] Here is a specific example where User B purchases running shoes on an online shopping site.

[0702] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[0703] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[0704] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[0705] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[0706] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[0707] 6. The server notifies User B of the recommendation via the API of the external communication tool. User B receives the recommendation via a messaging application.

[0708] 7. The user is interested in the recommendation and sends a message asking, "What size are these socks?"

[0709] 8. The server receives the question and sends it to the generative AI and emotion engine.

[0710] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[0711] Prompt Sentence Examples

[0712] "After User B purchases running shoes, recommend the best running socks as the next product with a positive message."

[0713] Thus, the present invention is a system that significantly improves the online shopping experience by analyzing users' purchasing behavior and emotions and providing personalized product recommendations in real time.

[0714] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0715] Step 1:

[0716] Input: User ID, browsing history, purchase history, click history when the user accesses an online shopping site

[0717] Operation:

[0718] When a user accesses an online shopping site, the server collects data in real time, such as the user ID, browsing history, purchase history, click history, etc. For example, if a user views a page for "running shoes," that information will be recorded.

[0719] Output: Collected user data is stored in a database.

[0720] Step 2:

[0721] Input: User data stored in the database

[0722] Operation:

[0723] The server sends the stored user data to the generation AI periodically or in response to a specific trigger event (e.g., product purchase).

[0724] Output: User data is provided to the generative AI for analysis.

[0725] Step 3:

[0726] Input: User data provided to the generative AI

[0727] Operation:

[0728] The Generative AI analyzes the provided user data and recognizes the user's preferences and purchasing behavior patterns. Specifically, it learns the trends of frequently purchased brands and products. For example, if User B has purchased "running shoes" multiple times in the past, it can identify their preferences.

[0729] Output: Analysis of user preferences and purchasing patterns

[0730] Step 4:

[0731] Input: Real-time text messages and reviews

[0732] Operation:

[0733] The server collects real-time text messages and reviews posted by users. For example, if a user posts a review saying, "These running shoes are great!", the server records the text data.

[0734] Output: Collected text data

[0735] Step 5:

[0736] Input: Collected text data

[0737] Operation:

[0738] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.). For example, it identifies positive emotions from the keyword "great."

[0739] Output: Parsed user sentiment data

[0740] Step 6:

[0741] Input: Preference analysis results from generative AI and emotional data from the emotion engine

[0742] Operation:

[0743] The generative AI and emotion engine work together to select the best products for the user based on the analysis results and generate recommendations. For example, if a user purchases running shoes, related running socks and apparel will be recommended. If the user expresses positive emotions, the recommendation message will also be positive.

[0744] Output: Generated recommendations

[0745] Step 7:

[0746] Input: Generated recommendation

[0747] Operation:

[0748] The server then sends the generated recommendations to the user's device via the API of an external communication tool, for example, by sending a message about the recommended products using LINE or WhatsApp.

[0749] Output: Recommendations sent to the user's device

[0750] Step 8:

[0751] Input: User message with questions or additional suggestions

[0752] Operation:

[0753] If a user has questions or additional suggestions after receiving a recommendation, they can send a chat question through a messaging application, such as "What size are these socks?"

[0754] Output: A message from the user is sent to the server.

[0755] Step 9:

[0756] Input: Message sent by the user

[0757] Operation:

[0758] The server receives the user's question and sends it to the generative AI and emotion engine.

[0759] Output: Data is provided to the generative AI and emotion engine for analysis.

[0760] Step 10:

[0761] Input: User question and sentiment data

[0762] Operation:

[0763] The generative AI and emotion engine analyze the user's question and emotion to generate appropriate answers and additional recommendations, such as, "These socks fit you perfectly in size medium. We also recommend the same series of running wear."

[0764] Output: Generated answers and additional recommendations

[0765] Step 11:

[0766] Input: Generated answers and additional recommendations

[0767] Operation:

[0768] The server sends the generated answers to the user's device in real time.

[0769] Output: The appropriate answer and additional recommendations sent to the user's device

[0770] Through this series of processing steps, personalized product recommendations based on users' purchasing behavior and emotions can be provided in real time, greatly improving the online shopping experience.

[0771] (Application example 2)

[0772] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0773] In online shopping, it is difficult to recommend products that fully take into account the user's individual needs and emotional state. Current systems mainly make simple recommendations based on the user's purchase and browsing history, which does not improve user satisfaction. It is also difficult to provide immediate and appropriate responses to user questions and requests.

[0774] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, means for collecting and analyzing user emotion data, recommendation means for recommending optimal products to the user based on the analysis results and the emotion data, means for notifying the user of the recommendation content via an external communication tool, and chat means for answering questions from the user in real time. This makes it possible to provide personalized recommendations based on the user's preferences and emotional state, and to provide immediate and appropriate responses.

[0775] "User data" refers to information related to online shopping, such as user ID, browsing history, purchase history, and click history.

[0776] "Generative artificial intelligence (AI)" refers to an artificial intelligence technology that analyzes user preferences and purchasing behavior patterns based on large amounts of data and makes optimal recommendations.

[0777] "Analysis Means" means a system or device for analyzing collected User Data.

[0778] "Emotional data" refers to information about a user's emotional state (such as joy, sadness, or surprise) obtained from their text messages, reviews, etc.

[0779] "Recommendation Means" means a system or function for selecting and recommending optimal products to a user based on analyzed user data and emotional data.

[0780] "External communication tools" refers to tools such as messaging applications and emails used to notify users of recommendations.

[0781] "Notification Means" means a system or function for sending recommendations to users via external communication tools.

[0782] "Chat means" means a system or function that provides real-time responses to user questions.

[0783] The present invention is a personalized recommendation system for improving a user's online shopping experience, and in particular, incorporates an emotion engine that recognizes a user's emotions. Specific embodiments of the present invention are described below.

[0784] First, the server collects user data, including user ID, browsing history, purchase history, click history, etc. This data is stored in Amazon RDS.

[0785] The server then periodically sends the data to the Generator AI, either periodically or upon specific trigger events (such as when a product is purchased). The Generator AI uses OpenAI GPT-4 to analyze the user data and recognize their preferences and purchasing patterns.

[0786] The server then collects sentiment data from user reviews and in-app messages, and uses IBM Watson Tone Analyzer as an emotion engine to analyze the collected text data and identify the user's emotional state (e.g., joy, sadness, surprise).

[0787] Based on the analyzed user preferences and emotional data, the generative AI and emotion engine work together to recommend the most suitable products to the user.The recommendations are generated with an appropriate tone and content and sent to the user's smartphone using an external communication tool (such as Twilio API for SMS or LINE Messaging API).

[0788] Users may receive a notification, become interested in the content, and submit a follow-up question. In this case, the server receives the question and sends it to the generation AI and emotion engine. The generation AI and emotion engine analyze the question, generate an appropriate answer, and send it back to the user's smartphone in real time.

[0789] As a concrete example, consider a situation where a user asks a question on LINE, such as "Tell me more about this product." An example of a prompt sentence for this situation would be as follows:

[0790] A user asked a question about a specific product. Product ID:

[12345] Question: "Tell me more about this product"

[0791] An example of the generated AI's response is as follows:

[0792] Hello! These are our latest running shoes, made with lightweight, breathable materials. They fit particularly well and are ideal for long-distance running. They are available in sizes from 22cm to 30cm and in a wide range of colors. If you're interested, you can purchase them here.

[0793] In this way, the system according to the present invention can analyze users' purchasing behavior data and emotional data and provide personalized recommendations in real time, thereby significantly improving the online shopping experience.

[0794] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0795] Step 1:

[0796] User Data Collection

[0797] The server collects user data (user ID, browsing history, purchase history, click history, etc.) every time a user logs in and performs an operation, and stores the data in Amazon RDS. The input is the user operation data, and the output is the stored data.

[0798] Step 2:

[0799] Regular analysis of user data

[0800] The server sends the collected data to OpenAI GPT-4 periodically or upon specific trigger events (e.g., when a product is purchased). The input is user data stored in Amazon RDS, and the output is the analyzed user preferences and purchasing behavior patterns.

[0801] Step 3:

[0802] Collecting Emotional Data

[0803] The server collects sentiment data from user reviews and in-app messages. The input is the reviews and messages posted by users, and the output is the text data.

[0804] Step 4:

[0805] Emotional Data Analysis

[0806] The server sends the collected text data to IBM Watson Tone Analyzer to identify the user's emotional state. The input is the text data of reviews and messages, and the output is the analyzed emotional data (e.g., joy, sadness, surprise, etc.).

[0807] Step 5:

[0808] Recommendation generation

[0809] The generative AI (OpenAI GPT-4) and the emotion engine (IBM Watson Tone Analyzer) work together to select the best products for users based on user data and emotion data. The input is analyzed user preferences and emotion data, and the output is personalized recommendations.

[0810] Step 6:

[0811] Notification of recommendation

[0812] The server uses the Twilio API or LINE Messaging API to notify the user of the generated recommendation content on their smartphone. The input is the generated recommendation content, and the output is a notification sent to the user's smartphone.

[0813] Step 7:

[0814] Receiving and sending user questions

[0815] When a user submits a question in response to a recommendation, the server receives it and sends the question to OpenAI GPT-4 and IBM Watson Tone Analyzer. The input is the question from the user, and the output is sent to the generative AI and emotion engine.

[0816] Step 8:

[0817] Generate answers to questions

[0818] The generative AI and emotion engine analyze the question, generate an appropriate answer, and send it to the server. The input is the user's question, past data, and emotional state, and the output is the generated answer.

[0819] Step 9:

[0820] Notification of response

[0821] The server notifies the user's smartphone of the answers generated by the generative AI and emotion engine via the Twilio API or LINE Messaging API. The input is the generated answer, and the output is the notification sent to the user's smartphone.

[0822] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0823] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0824] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0825] [Third embodiment]

[0826] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0827] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0828] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0829] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0830] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0831] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0832] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0833] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0834] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0835] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0836] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0837] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0838] The present invention is a personalized recommendation system for improving a user's online shopping experience, which is implemented as follows.

[0839] System Configuration

[0840] 1. Collection of User Data

[0841] When a user accesses an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history.

[0842] 2. Data Analysis

[0843] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[0844] Generative AI analyzes user data and recognizes user preferences and purchasing patterns. For example, it determines that a user who frequently purchases shoes from a particular brand will prefer that brand's products.

[0845] 3. Generating Recommendations

[0846] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0847] The generative AI generates specific recommendations for the selected products, which are presented in the form of empathetic and logical text, images, videos, etc.

[0848] 4. Notification

[0849] The server sends the recommendations created by the AI ​​to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[0850] 5. Chat integration

[0851] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[0852] The server receives messages from users and sends the contents to the generation AI.

[0853] The generative AI analyzes the user's question, generates appropriate answers and additional recommendations, and sends them back to the user's device in real time via the server.

[0854] Example: System behavior when user A purchases running shoes

[0855] As an example, we will explain the system flow when user A purchases running shoes on an online shopping site.

[0856] 1. The server collects user A's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[0857] 2. The server also sends User A's past purchasing history and browsing history to the generation AI.

[0858] 3. The generation AI analyzes User A's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[0859] 4. The generative AI generates recommendations consisting of empathetic and logical text and images, such as, "How about the perfect running socks to go with your new shoes?"

[0860] 5. The server notifies User A's device of this recommendation via the API of the external communication tool. User A receives this recommendation via a messaging application such as LINE.

[0861] 6. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[0862] 7. The server receives the question and sends it to the generating AI.

[0863] 8. The generation AI generates appropriate size information in response to User A's question and returns it to User A's device in real time via the server.

[0864] In this way, the system according to the present invention analyzes user purchasing behavior data and provides personalized product recommendations in real time, thereby improving the online shopping experience.

[0865] The processing flow will be explained below.

[0866] Step 1:

[0867] The device accesses an online shopping site, where the user browses or purchases products.

[0868] Step 2:

[0869] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[0870] Step 3:

[0871] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[0872] Step 4:

[0873] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[0874] Step 5:

[0875] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0876] Step 6:

[0877] The generative AI generates specific recommendations (e.g., text, images, and videos that are both empathetic and logical) for the selected products. Specifically, it creates content such as, "How about the perfect running socks to go with your new shoes?"

[0878] Step 7:

[0879] The server sends the recommendations created by the generation AI to the user's device via the API of an external communication tool (e.g., a messaging application).

[0880] Step 8:

[0881] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[0882] Step 9:

[0883] The server receives questions from users and sends the content to the generation AI.

[0884] Step 10:

[0885] The generative AI analyzes the user's question and generates an appropriate answer (e.g., sock size information).

[0886] Step 11:

[0887] The server sends the answers generated by the generation AI back to the user's device in real time via the API of an external communication tool.

[0888] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[0889] Example 1

[0890] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0891] In conventional online shopping systems, product recommendations to users are made in a general and inefficient manner, making it difficult to make personalized recommendations based on individual users' preferences and purchasing behavior patterns. Furthermore, few systems have the ability to accurately respond to user questions in real time, which can lead to a poor user experience. To address these issues, a system is needed that can effectively collect and analyze user data, generate personalized recommendations, and notify users promptly and appropriately.

[0892] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0893] In this invention, the server includes means for collecting user data, means for periodically or upon the occurrence of a specific trigger event, transmitting the collected user data to the generative AI model for analysis, means for selecting the most suitable product for the user based on the analysis results of the generative AI model and creating recommendations, means for notifying the user of the created recommendations via the API of an external communication tool, and means for accepting questions from users, transmitting them to the generative AI model, and returning the answers generated by the generative AI model to the user in real time. This enables accurate collection and analysis of user data, and the creation and notification of personalized recommendations, improving the user experience.

[0894] "User data" refers to data such as a user's access, browsing, purchase, and click history on an online shopping site, as well as user ID, purchase date and time, and payment information.

[0895] A "generative AI model" is an artificial intelligence model that analyzes user data and recognizes user preferences and purchasing behavior patterns.

[0896] "Trigger Event" means a specific event or condition that causes data to be analyzed or transmitted, such as the moment a user purchases a product or after a certain period of time has passed.

[0897] "External communication tools" are tools, including messaging applications and social networking platforms, used to transmit information between servers and users.

[0898] "API" stands for Application Programming Interface, an interface that enables data exchange between different software systems.

[0899] "Real-time" means that information is processed and provided to users immediately, without delay.

[0900] "Recommendation content" refers to information about products and services that the generative AI model suggests to users based on the results of analyzing user data, and is provided in the form of text, images, videos, etc.

[0901] This invention is a personalized recommendation system for improving users' online shopping experiences. The system collects user data through multiple means, analyzes the data using a generative AI model, recommends optimal products, and provides the ability to interact with users in real time.

[0902] User Data Collection

[0903] When a user visits an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history. This includes monitoring and collecting user behavior in real time using technologies such as JavaScript and tracking pixels. For example, when a user views or clicks on a particular product page, that data is immediately sent to the server.

[0904] Data analysis

[0905] The server stores the collected user data in a database. The stored data is automatically sent to the generative AI model periodically or when a specific trigger event occurs. The generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. This allows for advanced analysis of user preferences and purchasing behavior patterns.

[0906] Recommendation generation

[0907] The generative AI model uses analyzed user data to select the most suitable products for each user and generate specific recommendations. These recommendations can include text, images, videos, and other formats, and are both empathetic and logical. For example, if a user purchases new running shoes, the model generates empathetic messages suggesting related products (e.g., running socks, running apparel, etc.).

[0908] Notification of recommendation

[0909] The server sends the generated recommendation to the user's device via the API of an external communication tool (e.g., LINE or Facebook Messenger). This allows the user to receive the recommendation in real time. For example, a LINE notification might display a message such as, "How about finding the perfect running socks to go with your new shoes?"

[0910] Chat function integration

[0911] After receiving the recommendations, users can ask additional questions or make suggestions. When a question is sent through a messaging application, the server sends it to the generative AI model. The generative AI model analyzes the user's question and generates an appropriate answer or additional recommendations. The generated answer is immediately sent back to the user's device via the server. For example, if a user asks, "What size are these socks?", a real-time answer such as, "These running socks are available in S, M, and L sizes" is provided.

[0912] Specific examples

[0913] An example of a specific prompt might be, "A user has purchased running shoes. Please generate text and images that recommend products related to this user."

[0914] Thus, the present invention aims to collect and analyze user purchasing behavior data, provide personalized product recommendations in real time, and improve user experience.

[0915] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0916] Step 1: Collect user data

[0917] When a user visits an online shopping site, the server automatically starts a session and collects the user ID, browsing history, and click history. Specifically, it records the product pages the user viewed and the links they clicked using JavaScript and tracking pixels.

[0918] Input: Behavioral data when users visit the site

[0919] Output: Collected user ID, browsing history, click history

[0920] Step 2: Collect your purchase history

[0921] When a user purchases a product, the server collects data such as the purchased product, purchase date and time, and payment information. This data is obtained through the confirmation page displayed when the purchase is completed and through APIs.

[0922] Input: Product information purchased by the user

[0923] Output: Collected purchased items, purchase date and time, payment information

[0924] Step 3: Save your data

[0925] The server stores the collected user behavior and purchase data in a main database, and organizes the data using a database management system (e.g., MySQL, PostgreSQL).

[0926] Input: Collected user behavior and purchase data

[0927] Output: Saved database records

[0928] Step 4: Prepare and send data

[0929] The server converts the stored data into a format suitable for the generative AI model and transmits the data periodically or when a specific trigger event occurs.

[0930] Input: User data stored in the database

[0931] Output: Formatted data sent to a generative AI model

[0932] Step 5: Data analysis

[0933] Generative AI models analyze the data they receive and learn user preferences and purchasing behavior patterns. They are built using machine learning libraries (e.g., TensorFlow, PyTorch) and trained on the data.

[0934] Input: Formatted user data

[0935] Output: Analysis results on user preferences and purchasing behavior

[0936] Step 6: Selecting recommended products

[0937] The generative AI model then selects the best products for the user based on the analysis results. For example, if a user purchases running shoes, it will select related products (e.g., running socks, running wear, etc.).

[0938] Input: Analysis results

[0939] Output: A list of products that are best suited for the user

[0940] Step 7: Generate recommendations

[0941] The generative AI model generates recommendations based on the selected products. Recommendations can take the form of text, images, videos, etc. For example, it might generate a message like, "How about the perfect running socks to go with your new shoes?"

[0942] Input: Selected product list

[0943] Output: Generated recommendation content (text, images, videos)

[0944] Step 8: Notification of recommendation

[0945] The server sends the generated recommendations to the user's device via the API of the external communication tool, securely communicating using an API key or token.

[0946] Input: Generated recommendation

[0947] Output: Recommendation notification sent to the user's device

[0948] Step 9: Accepting user questions

[0949] After receiving a recommendation, users can ask additional questions or make suggestions by sending a text message through the messaging app.

[0950] Input: User question

[0951] Output: User's question received by the server

[0952] Step 10: Parsing the question and generating an answer

[0953] The server sends the user's question to the generative AI model, which analyzes the question and generates an appropriate answer or additional recommendations. For example, it generates an answer such as, "These running socks are available in sizes S, M, and L."

[0954] Input: User question

[0955] Output: Generated answers and additional recommendations

[0956] Step 11: Submit your response

[0957] The server sends the generated answer back to the user's device in real time, and the user receives the answer via a messaging application.

[0958] Input: The answer generated by the generative AI model

[0959] Output: The answer sent to the user's device

[0960] The above processing steps enable accurate collection and analysis of user purchasing behavior data, enabling personalized product recommendations and real-time dialogue.

[0961] (Application example 1)

[0962] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0963] Traditional online shopping systems are limited to a single form of product recommendation for users and are unable to adapt to the environment in which the user is shopping. Furthermore, when users shop in a virtual reality environment, traditional systems lack real-time personalized recommendations and direct chat functionality, limiting the user experience. This makes it difficult for users to enjoy shopping as efficiently and effectively as they would in a physical store.

[0964] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0965] In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, recommendation means for recommending optimal products to the user based on the analysis results, means for displaying products in a virtual reality environment, means for notifying the user of the recommended content via an external communication tool, and chat means for answering questions from the user in real time. This allows the user to receive personalized product recommendations in the virtual reality environment and further enables efficient shopping through real-time dialogue.

[0966] "User Data" means information related to a user's behavior on an online shopping site or virtual store, including, for example, purchase history, browsing history, and click history.

[0967] "Analytical means" means means, including artificial intelligence (AI), for analyzing collected user data, which is used to understand user preferences and purchasing patterns.

[0968] A "recommendation means" is a means for recommending optimal products to users based on analyzed data, and specifically provides recommended content to users in a format that includes text, images, videos, etc.

[0969] A "virtual reality environment" is an environment in which users shop in a virtual space using dedicated headsets or devices.

[0970] "External communication tools" are tools used to notify users of recommendations, and specifically include messaging applications.

[0971] The "chat tool" is a means for providing answers to user questions in real time, and works in conjunction with the generation AI to generate appropriate responses to user questions.

[0972] A system for implementing this invention enhances the online shopping experience by collecting user data, analyzing it, and providing personalized product recommendations in a virtual reality environment. The system includes the following components:

[0973] Hardware and Software Usage

[0974] Hardware:

[0975] VR headset: To realize the virtual reality environment, we use a general-purpose VR headset (e.g., Oculus Quest 2) as an example.

[0976] Smartphone: Use a standard smartphone (iPhone, Android) to receive notifications of recommendations.

[0977] software:

[0978] Generative AI (AI models): Use generative AI models, such as OpenAI GPT-4, to analyze user data and recommend products based on user preferences.

[0979] Server: A standard web server is used to collect, store, analyze, and notify data.

[0980] External communication tool: To notify the recommendation content, we use the API of a messaging application. In this example, we use a general-purpose messaging application.

[0981] Processing Description

[0982] Data collection and analysis

[0983] When a user accesses a virtual store, the server automatically collects user data (user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The collected data is sent to the generation AI for analysis, either periodically or when a specific trigger event occurs. The generation AI analyzes the user data and recognizes the user's preferences and purchasing behavior patterns.

[0984] Recommendation generation and notification

[0985] The AI ​​then selects the most suitable product for the user based on the analysis results and generates recommendations. These recommendations are provided in the form of text, images, and videos. The server then notifies the user of the recommendations created by the AI ​​via the API of an external communication tool.

[0986] Chat feature

[0987] If a user has a question about the recommended content, they can send it in chat format through a messaging application. This question is then sent to the AI ​​via the server, and the AI ​​generates an appropriate answer and sends it back to the user in real time via the server.

[0988] Specific examples

[0989] For example, if User A purchases running shoes in a virtual reality environment, the system operates as follows: The server collects User A's purchase information and stores it in a database. The collected data is then sent to the generation AI, which analyzes User A's preferences. The generation AI uses "running" as a keyword to select related products (e.g., running socks, running wear), and generates a recommendation message containing text and an image saying, "How about the perfect running socks to go with your new shoes?" The server notifies User A's device via the messaging application's API, and User A can receive the recommendation message on their smartphone or in the VR environment.

[0990] Example prompts for generative AI models

[0991] User's purchase history: {"item": "Running shoes", "date": "2023-01-15"}

[0992] User's browsing history: {"item": "Running wear", "date": "2023-01-14"}

[0993] User click history: {"item": "Running socks", "date": "2023-01-13"}

[0994] Recommend the best product for this user.

[0995] In this way, the system of the present invention can analyze user data and provide real-time personalized product recommendations in a virtual reality environment, allowing users to enjoy a more efficient and effective shopping experience.

[0996] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0997] Step 1:

[0998] When a user accesses a virtual store, the server automatically collects user data (e.g., user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The input data is various user behavioral data, and based on this, the server manages the storage volume as database entries. At the same time, a timestamp of user activity is also recorded.

[0999] Step 2:

[1000] The server sends the collected user data to the generation AI for analysis periodically or when a specific trigger event occurs. The input for this process is the user data saved in step 1, and the output is the analysis results such as user preferences, purchasing behavior patterns, and purchase predictions recognized by the generation AI. The generation AI uses prompt statements to perform data analysis and returns the analysis results in text format to the server.

[1001] Step 3:

[1002] The server uses the generation AI to select the most suitable product for the user based on the analysis results from the generation AI. At this time, the generation AI is instructed to "recommend the most suitable product based on the user's purchase history, browsing history, and click history" using specific prompts. The output provided to the server is a list of candidate products and text and image links related to the recommended content.

[1003] Step 4:

[1004] The server uses the recommendation means to notify the user's device of the recommendation content created by the generation AI via the API of the external communication tool. At this time, the recommendation content obtained from the generation AI is used as input, and the recommendation information is notified in real time to the user's smartphone or VR headset as output. Specifically, the server generates an API request and pushes the recommendation content to the user's device.

[1005] Step 5:

[1006] The user checks the recommendations sent to their device and, if they have any questions, sends them in chat format using a messaging application. The input is a text message from the user, which is sent to the server via the messaging application. The server receives this message and forwards the question to the generation AI.

[1007] Step 6:

[1008] The generation AI generates appropriate answers based on questions received from users. The input is the user's question, and the output is the generated answer text. The generation AI analyzes past user data and the content of the question to generate an appropriate answer.

[1009] Step 7:

[1010] The server notifies the user of the answer generated by the AI ​​by sending the reply to the user's device in real time using an external communication tool. The input is the answer text from the AI, and the output is a text message displayed on the user's device. Specifically, the server generates an API request and sends a text message to the messaging application.

[1011] Through these seven steps, user data collection, analysis, personalized product recommendations, and real-time chat support are achieved, allowing users to enjoy an efficient and effective shopping experience even in a virtual reality environment.

[1012] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1013] The present invention is a personalized recommendation system for improving a user's online shopping experience, and is characterized in that it incorporates an emotion engine that recognizes the user's emotions. Embodiments of the present invention are described below.

[1014] System Configuration

[1015] 1. Collection of User Data

[1016] When a user accesses an online shopping site, the server automatically collects data such as the user ID, browsing history, purchase history, and click history, and stores it in a database.

[1017] 2. Data Analysis

[1018] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[1019] Generative AI analyzes user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that that brand's products are likely to be preferred.

[1020] 3. Emotional Data Collection and Analysis

[1021] The server collects sentiment data from users' real-time text messages and reviews.

[1022] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[1023] 4. Generating Recommendations

[1024] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[1025] The generative AI takes into account the user's emotional state and generates recommendations with an appropriate tone and content. For example, if the user is expressing joy, the recommendations will include positive messages.

[1026] 5. Notification

[1027] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[1028] 6. Chat integration

[1029] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[1030] The server receives messages from users and sends the content to the generation AI and emotion engine.

[1031] The generative AI and emotion engine analyze the user's questions and emotions, generate appropriate answers and additional recommendations, and send them back to the user's device in real time via the server.

[1032] Example: System behavior when user B purchases running shoes

[1033] As an example, we will explain the system flow when User B purchases running shoes on an online shopping site.

[1034] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[1035] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[1036] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[1037] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[1038] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[1039] 6. The server notifies User B of this recommendation via the API of the external communication tool. User B receives this recommendation via a messaging application such as LINE.

[1040] 7. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[1041] 8. The server receives the question and sends it to the generative AI and emotion engine.

[1042] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[1043] In this way, the system according to the present invention analyzes user purchasing behavior data and emotional data and provides personalized product recommendations in real time, thereby significantly improving the online shopping experience.

[1044] The processing flow will be explained below.

[1045] Step 1:

[1046] The device accesses an online shopping site, where the user browses or purchases products.

[1047] Step 2:

[1048] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[1049] Step 3:

[1050] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[1051] Step 4:

[1052] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[1053] Step 5:

[1054] The server retrieves users' real-time text messages and reviews and sends them to the emotion engine.

[1055] Step 6:

[1056] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[1057] Step 7:

[1058] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[1059] Step 8:

[1060] The AI ​​generator generates recommendations with appropriate tone and content, taking into account the user's emotional state. For example, if the user is expressing joy, the recommendation will include positive messages.

[1061] Step 9:

[1062] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application).

[1063] Step 10:

[1064] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[1065] Step 11:

[1066] The server receives questions from users and sends them to the generative AI and emotion engine.

[1067] Step 12:

[1068] The generative AI and emotion engine analyzes the user's question and emotion, generating appropriate answers and emotionally sensitive explanations.

[1069] Step 13:

[1070] The server sends the generated answers back to the user's device in real time via the API of the external communication tool.

[1071] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[1072] Example 2

[1073] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1074] Conventional online shopping systems sometimes recommend products based on a user's preferences and purchasing patterns, but they fail to consider the user's emotional state. As a result, recommendations are sometimes made at inappropriate times or with inappropriate tones, leading to a loss of motivation or dissatisfaction. Furthermore, the lack of a means to quickly and appropriately respond to questions or additional suggestions leads to a poor user experience.

[1075] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1076] In this invention, the server includes means for collecting user online activity data, means for storing the collected user data in a database, and analysis means including a generative artificial intelligence (AI) for analyzing the stored user data, which enables means for collecting emotion data from the analyzed user data, means for analyzing the collected emotion data, means for recommending optimal products taking the user's emotions into consideration based on the analysis results, means for notifying the user of the recommended content via the API of an external communication tool, and chat means for answering questions from users in real time.

[1077] "User online activity data" refers to data such as user ID, browsing history, purchase history, and click history that is recorded when a user accesses an online shopping site.

[1078] A "database" is a data storage device that systematically stores collected user data, making it easy to analyze and search later.

[1079] "Generative artificial intelligence (AI)" is a system that uses advanced analytical algorithms to analyze user data and recognize and understand user preferences and purchasing patterns.

[1080] "Emotional Data" means data that indicates a user's emotional state (e.g., joy, sadness, surprise, etc.) extracted from a user's real-time text messages or reviews.

[1081] An "emotion engine" is a software or hardware system for analyzing collected emotion data and identifying a user's emotional state.

[1082] The "means for recommending optimal products" is a system that has the function of selecting and recommending the most suitable products for users based on analyzed user data and emotional data.

[1083] An "API for external communication tools" is an interface for communicating data between the system and the user's device using a messaging application or other external communication tool.

[1084] A "chat means" is a system with a communication function that responds in real time to questions and additional suggestions from users and provides appropriate answers and additional recommendations.

[1085] This invention provides a personalized recommendation system that utilizes generative AI models and emotion engines to improve users' online shopping experience. By collecting and analyzing users' online activity data and emotion data, the system can recommend the most suitable products to users, significantly improving the user experience.

[1086] System Configuration

[1087] The system includes the following main hardware and software:

[1088] 1. Server:

[1089] It has the ability to collect users' online activity data (e.g., user ID, browsing history, purchase history, click history, etc.) and store it in a database.

[1090] The collected data is sent to and analyzed by Generative Artificial Intelligence (AI), which identifies user preferences and purchasing patterns.

[1091] 2. Database:

[1092] Systematically store collected online activity data, which can then be accessed and analyzed by the generative AI and emotion engine.

[1093] 3. Generation AI:

[1094] By analyzing user data and learning about user preferences and purchasing behavior patterns, the Generative AI generates personalized product recommendations based on the user's purchase and browsing history.

[1095] 4. Emotion Engine:

[1096] It collects sentiment data from users' real-time text messages and reviews and analyzes that data.

[1097] The emotion engine identifies whether the user is expressing emotions such as happiness, sadness, or surprise, and provides this emotional information to the generative AI.

[1098] 5. API for external communication tools:

[1099] It acts as an interface to notify users of the recommended content. As a result, the recommendations generated by the generative AI and emotion engine are sent to the user's device via an external messaging application (e.g., LINE or WhatsApp).

[1100] 6. User Device:

[1101] The device through which users receive recommendations and send questions or additional suggestions. Devices include smartphones, tablets, and PCs.

[1102] Specific examples

[1103] Here is a specific example where User B purchases running shoes on an online shopping site.

[1104] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[1105] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[1106] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[1107] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[1108] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[1109] 6. The server notifies User B of the recommendation via the API of the external communication tool. User B receives the recommendation via a messaging application.

[1110] 7. The user is interested in the recommendation and sends a message asking, "What size are these socks?"

[1111] 8. The server receives the question and sends it to the generative AI and emotion engine.

[1112] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[1113] Prompt Sentence Examples

[1114] "After User B purchases running shoes, recommend the best running socks as the next product with a positive message."

[1115] Thus, the present invention is a system that significantly improves the online shopping experience by analyzing users' purchasing behavior and emotions and providing personalized product recommendations in real time.

[1116] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] Input: User ID, browsing history, purchase history, click history when the user accesses an online shopping site

[1119] Operation:

[1120] When a user accesses an online shopping site, the server collects data in real time, such as the user ID, browsing history, purchase history, click history, etc. For example, if a user views a page for "running shoes," that information will be recorded.

[1121] Output: Collected user data is stored in a database.

[1122] Step 2:

[1123] Input: User data stored in the database

[1124] Operation:

[1125] The server sends the stored user data to the generation AI periodically or in response to a specific trigger event (e.g., product purchase).

[1126] Output: User data is provided to the generative AI for analysis.

[1127] Step 3:

[1128] Input: User data provided to the generative AI

[1129] Operation:

[1130] The Generative AI analyzes the provided user data and recognizes the user's preferences and purchasing behavior patterns. Specifically, it learns the trends of frequently purchased brands and products. For example, if User B has purchased "running shoes" multiple times in the past, it can identify their preferences.

[1131] Output: Analysis of user preferences and purchasing patterns

[1132] Step 4:

[1133] Input: Real-time text messages and reviews

[1134] Operation:

[1135] The server collects real-time text messages and reviews posted by users. For example, if a user posts a review saying, "These running shoes are great!", the server records the text data.

[1136] Output: Collected text data

[1137] Step 5:

[1138] Input: Collected text data

[1139] Operation:

[1140] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.). For example, it identifies positive emotions from the keyword "great."

[1141] Output: Parsed user sentiment data

[1142] Step 6:

[1143] Input: Preference analysis results from generative AI and emotional data from the emotion engine

[1144] Operation:

[1145] The generative AI and emotion engine work together to select the best products for the user based on the analysis results and generate recommendations. For example, if a user purchases running shoes, related running socks and apparel will be recommended. If the user expresses positive emotions, the recommendation message will also be positive.

[1146] Output: Generated recommendations

[1147] Step 7:

[1148] Input: Generated recommendation

[1149] Operation:

[1150] The server then sends the generated recommendations to the user's device via the API of an external communication tool, for example, by sending a message about the recommended products using LINE or WhatsApp.

[1151] Output: Recommendations sent to the user's device

[1152] Step 8:

[1153] Input: User message with questions or additional suggestions

[1154] Operation:

[1155] If a user has questions or additional suggestions after receiving a recommendation, they can send a chat question through a messaging application, such as "What size are these socks?"

[1156] Output: A message from the user is sent to the server.

[1157] Step 9:

[1158] Input: Message sent by the user

[1159] Operation:

[1160] The server receives the user's question and sends it to the generative AI and emotion engine.

[1161] Output: Data is provided to the generative AI and emotion engine for analysis.

[1162] Step 10:

[1163] Input: User question and sentiment data

[1164] Operation:

[1165] The generative AI and emotion engine analyze the user's question and emotion to generate appropriate answers and additional recommendations, such as, "These socks fit you perfectly in size medium. We also recommend the same series of running wear."

[1166] Output: Generated answers and additional recommendations

[1167] Step 11:

[1168] Input: Generated answers and additional recommendations

[1169] Operation:

[1170] The server sends the generated answers to the user's device in real time.

[1171] Output: The appropriate answer and additional recommendations sent to the user's device

[1172] Through this series of processing steps, personalized product recommendations based on users' purchasing behavior and emotions can be provided in real time, greatly improving the online shopping experience.

[1173] (Application example 2)

[1174] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1175] In online shopping, it is difficult to recommend products that fully take into account the user's individual needs and emotional state. Current systems mainly make simple recommendations based on the user's purchase and browsing history, which does not improve user satisfaction. It is also difficult to provide immediate and appropriate responses to user questions and requests.

[1176] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, means for collecting and analyzing user emotion data, recommendation means for recommending optimal products to the user based on the analysis results and the emotion data, means for notifying the user of the recommendation content via an external communication tool, and chat means for answering questions from the user in real time. This makes it possible to provide personalized recommendations based on the user's preferences and emotional state, and to provide immediate and appropriate responses.

[1177] "User data" refers to information related to online shopping, such as user ID, browsing history, purchase history, and click history.

[1178] "Generative artificial intelligence (AI)" refers to an artificial intelligence technology that analyzes user preferences and purchasing behavior patterns based on large amounts of data and makes optimal recommendations.

[1179] "Analysis Means" means a system or device for analyzing collected User Data.

[1180] "Emotional data" refers to information about a user's emotional state (such as joy, sadness, or surprise) obtained from their text messages, reviews, etc.

[1181] "Recommendation Means" means a system or function for selecting and recommending optimal products to a user based on analyzed user data and emotional data.

[1182] "External communication tools" refers to tools such as messaging applications and emails used to notify users of recommendations.

[1183] "Notification Means" means a system or function for sending recommendations to users via external communication tools.

[1184] "Chat means" means a system or function that provides real-time responses to user questions.

[1185] The present invention is a personalized recommendation system for improving a user's online shopping experience, and in particular, incorporates an emotion engine that recognizes a user's emotions. Specific embodiments of the present invention are described below.

[1186] First, the server collects user data, including user ID, browsing history, purchase history, click history, etc. This data is stored in Amazon RDS.

[1187] The server then periodically sends the data to the Generator AI, either periodically or upon specific trigger events (such as when a product is purchased). The Generator AI uses OpenAI GPT-4 to analyze the user data and recognize their preferences and purchasing patterns.

[1188] The server then collects sentiment data from user reviews and in-app messages, and uses IBM Watson Tone Analyzer as an emotion engine to analyze the collected text data and identify the user's emotional state (e.g., joy, sadness, surprise).

[1189] Based on the analyzed user preferences and emotional data, the generative AI and emotion engine work together to recommend the most suitable products to the user.The recommendations are generated with an appropriate tone and content and sent to the user's smartphone using an external communication tool (such as Twilio API for SMS or LINE Messaging API).

[1190] Users may receive a notification, become interested in the content, and submit a follow-up question. In this case, the server receives the question and sends it to the generation AI and emotion engine. The generation AI and emotion engine analyze the question, generate an appropriate answer, and send it back to the user's smartphone in real time.

[1191] As a concrete example, consider a situation where a user asks a question on LINE, such as "Tell me more about this product." An example of a prompt sentence for this situation would be as follows:

[1192] A user asked a question about a specific product. Product ID:

[12345] Question: "Tell me more about this product"

[1193] An example of the generated AI's response is as follows:

[1194] Hello! These are our latest running shoes, made with lightweight, breathable materials. They fit particularly well and are ideal for long-distance running. They are available in sizes from 22cm to 30cm and in a wide range of colors. If you're interested, you can purchase them here.

[1195] In this way, the system according to the present invention can analyze users' purchasing behavior data and emotional data and provide personalized recommendations in real time, thereby significantly improving the online shopping experience.

[1196] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1197] Step 1:

[1198] User Data Collection

[1199] The server collects user data (user ID, browsing history, purchase history, click history, etc.) every time a user logs in and performs an operation, and stores the data in Amazon RDS. The input is the user operation data, and the output is the stored data.

[1200] Step 2:

[1201] Regular analysis of user data

[1202] The server sends the collected data to OpenAI GPT-4 periodically or upon specific trigger events (e.g., when a product is purchased). The input is user data stored in Amazon RDS, and the output is the analyzed user preferences and purchasing behavior patterns.

[1203] Step 3:

[1204] Collecting Emotional Data

[1205] The server collects sentiment data from user reviews and in-app messages. The input is the reviews and messages posted by users, and the output is the text data.

[1206] Step 4:

[1207] Emotional Data Analysis

[1208] The server sends the collected text data to IBM Watson Tone Analyzer to identify the user's emotional state. The input is the text data of reviews and messages, and the output is the analyzed emotional data (e.g., joy, sadness, surprise, etc.).

[1209] Step 5:

[1210] Recommendation generation

[1211] The generative AI (OpenAI GPT-4) and the emotion engine (IBM Watson Tone Analyzer) work together to select the best products for users based on user data and emotion data. The input is analyzed user preferences and emotion data, and the output is personalized recommendations.

[1212] Step 6:

[1213] Notification of recommendation

[1214] The server uses the Twilio API or LINE Messaging API to notify the user of the generated recommendation content on their smartphone. The input is the generated recommendation content, and the output is a notification sent to the user's smartphone.

[1215] Step 7:

[1216] Receiving and sending user questions

[1217] When a user submits a question in response to a recommendation, the server receives it and sends the question to OpenAI GPT-4 and IBM Watson Tone Analyzer. The input is the question from the user, and the output is sent to the generative AI and emotion engine.

[1218] Step 8:

[1219] Generate answers to questions

[1220] The generative AI and emotion engine analyze the question, generate an appropriate answer, and send it to the server. The input is the user's question, past data, and emotional state, and the output is the generated answer.

[1221] Step 9:

[1222] Notification of response

[1223] The server notifies the user's smartphone of the answers generated by the generative AI and emotion engine via the Twilio API or LINE Messaging API. The input is the generated answer, and the output is the notification sent to the user's smartphone.

[1224] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1225] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1226] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1227] [Fourth embodiment]

[1228] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1229] 7, a 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.

[1230] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1231] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1232] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1233] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1234] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1235] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1236] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1237] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1238] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1239] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1240] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1241] The present invention is a personalized recommendation system for improving a user's online shopping experience, which is implemented as follows.

[1242] System Configuration

[1243] 1. Collection of User Data

[1244] When a user accesses an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history.

[1245] 2. Data Analysis

[1246] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[1247] Generative AI analyzes user data and recognizes user preferences and purchasing patterns. For example, it determines that a user who frequently purchases shoes from a particular brand will prefer that brand's products.

[1248] 3. Generating Recommendations

[1249] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[1250] The generative AI generates specific recommendations for the selected products, which are presented in the form of empathetic and logical text, images, videos, etc.

[1251] 4. Notification

[1252] The server sends the recommendations created by the AI ​​to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[1253] 5. Chat integration

[1254] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[1255] The server receives messages from users and sends the contents to the generation AI.

[1256] The generative AI analyzes the user's question, generates appropriate answers and additional recommendations, and sends them back to the user's device in real time via the server.

[1257] Example: System behavior when user A purchases running shoes

[1258] As an example, we will explain the system flow when user A purchases running shoes on an online shopping site.

[1259] 1. The server collects user A's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[1260] 2. The server also sends User A's past purchasing history and browsing history to the generation AI.

[1261] 3. The generation AI analyzes User A's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[1262] 4. The generative AI generates recommendations consisting of empathetic and logical text and images, such as, "How about the perfect running socks to go with your new shoes?"

[1263] 5. The server notifies User A's device of this recommendation via the API of the external communication tool. User A receives this recommendation via a messaging application such as LINE.

[1264] 6. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[1265] 7. The server receives the question and sends it to the generating AI.

[1266] 8. The generation AI generates appropriate size information in response to User A's question and returns it to User A's device in real time via the server.

[1267] In this way, the system according to the present invention analyzes user purchasing behavior data and provides personalized product recommendations in real time, thereby improving the online shopping experience.

[1268] The processing flow will be explained below.

[1269] Step 1:

[1270] The device accesses an online shopping site, where the user browses or purchases products.

[1271] Step 2:

[1272] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[1273] Step 3:

[1274] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[1275] Step 4:

[1276] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[1277] Step 5:

[1278] Based on the analysis results, the generative AI selects the best products for the user. For example, if a user purchases new running shoes, it will select related products (e.g., running socks, running wear, etc.).

[1279] Step 6:

[1280] The generative AI generates specific recommendations (e.g., text, images, and videos that are both empathetic and logical) for the selected products. Specifically, it creates content such as, "How about the perfect running socks to go with your new shoes?"

[1281] Step 7:

[1282] The server sends the recommendations created by the generation AI to the user's device via the API of an external communication tool (e.g., a messaging application).

[1283] Step 8:

[1284] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[1285] Step 9:

[1286] The server receives questions from users and sends the content to the generation AI.

[1287] Step 10:

[1288] The generative AI analyzes the user's question and generates an appropriate answer (e.g., sock size information).

[1289] Step 11:

[1290] The server sends the answers generated by the generation AI back to the user's device in real time via the API of an external communication tool.

[1291] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[1292] Example 1

[1293] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1294] In conventional online shopping systems, product recommendations to users are made in a general and inefficient manner, making it difficult to make personalized recommendations based on individual users' preferences and purchasing behavior patterns. Furthermore, few systems have the ability to accurately respond to user questions in real time, which can lead to a poor user experience. To address these issues, a system is needed that can effectively collect and analyze user data, generate personalized recommendations, and notify users promptly and appropriately.

[1295] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1296] In this invention, the server includes means for collecting user data, means for periodically or upon the occurrence of a specific trigger event, transmitting the collected user data to the generative AI model for analysis, means for selecting the most suitable product for the user based on the analysis results of the generative AI model and creating recommendations, means for notifying the user of the created recommendations via the API of an external communication tool, and means for accepting questions from users, transmitting the answers generated by the generative AI model, and returning the answers generated by the generative AI model to the user in real time. This enables accurate collection and analysis of user data, and the creation and notification of personalized recommendations, improving the user experience.

[1297] "User data" refers to data such as a user's access, browsing, purchase, and click history on an online shopping site, as well as user ID, purchase date and time, and payment information.

[1298] A "generative AI model" is an artificial intelligence model that analyzes user data and recognizes user preferences and purchasing behavior patterns.

[1299] "Trigger Event" means a specific event or condition that causes data to be analyzed or transmitted, such as the moment a user purchases a product or after a certain period of time has passed.

[1300] "External communication tools" are tools, including messaging applications and social networking platforms, used to transmit information between servers and users.

[1301] "API" stands for Application Programming Interface, an interface that enables data exchange between different software systems.

[1302] "Real-time" means that information is processed and provided to users immediately, without delay.

[1303] "Recommendation content" refers to information about products and services that the generative AI model suggests to users based on the results of analyzing user data, and is provided in the form of text, images, videos, etc.

[1304] This invention is a personalized recommendation system for improving users' online shopping experiences. The system collects user data through multiple means, analyzes the data using a generative AI model, recommends optimal products, and provides the ability to interact with users in real time.

[1305] User Data Collection

[1306] When a user visits an online shopping site, the server automatically collects data such as user ID, browsing history, purchase history, and click history. This includes monitoring and collecting user behavior in real time using technologies such as JavaScript and tracking pixels. For example, when a user views or clicks on a particular product page, that data is immediately sent to the server.

[1307] Data analysis

[1308] The server stores the collected user data in a database. The stored data is automatically sent to the generative AI model periodically or when a specific trigger event occurs. The generative AI model is built using machine learning libraries such as TensorFlow and PyTorch. This allows for advanced analysis of user preferences and purchasing behavior patterns.

[1309] Recommendation generation

[1310] The generative AI model uses analyzed user data to select the most suitable products for each user and generate specific recommendations. These recommendations can include text, images, videos, and other formats, and are both empathetic and logical. For example, if a user purchases new running shoes, the model generates empathetic messages suggesting related products (e.g., running socks, running apparel, etc.).

[1311] Notification of recommendation

[1312] The server sends the generated recommendation to the user's device via the API of an external communication tool (e.g., LINE or Facebook Messenger). This allows the user to receive the recommendation in real time. For example, a LINE notification might display a message such as, "How about finding the perfect running socks to go with your new shoes?"

[1313] Chat function integration

[1314] After receiving the recommendations, users can ask additional questions or make suggestions. When a question is sent through a messaging application, the server sends it to the generative AI model. The generative AI model analyzes the user's question and generates an appropriate answer or additional recommendations. The generated answer is immediately sent back to the user's device via the server. For example, if a user asks, "What size are these socks?", a real-time answer such as, "These running socks are available in S, M, and L sizes" is provided.

[1315] Specific examples

[1316] An example of a specific prompt might be, "A user has purchased running shoes. Please generate text and images that recommend products related to this user."

[1317] Thus, the present invention aims to collect and analyze user purchasing behavior data, provide personalized product recommendations in real time, and improve user experience.

[1318] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1319] Step 1: Collect user data

[1320] When a user visits an online shopping site, the server automatically starts a session and collects the user ID, browsing history, and click history. Specifically, it records the product pages the user viewed and the links they clicked using JavaScript and tracking pixels.

[1321] Input: Behavioral data when users visit the site

[1322] Output: Collected user ID, browsing history, click history

[1323] Step 2: Collect your purchase history

[1324] When a user purchases a product, the server collects data such as the purchased product, purchase date and time, and payment information. This data is obtained through the confirmation page displayed when the purchase is completed and through APIs.

[1325] Input: Product information purchased by the user

[1326] Output: Collected purchased items, purchase date and time, payment information

[1327] Step 3: Save your data

[1328] The server stores the collected user behavior and purchase data in a main database, and organizes the data using a database management system (e.g., MySQL, PostgreSQL).

[1329] Input: Collected user behavior and purchase data

[1330] Output: Saved database records

[1331] Step 4: Prepare and send data

[1332] The server converts the stored data into a format suitable for the generative AI model and transmits the data periodically or when a specific trigger event occurs.

[1333] Input: User data stored in the database

[1334] Output: Formatted data sent to a generative AI model

[1335] Step 5: Data analysis

[1336] Generative AI models analyze the data they receive and learn user preferences and purchasing behavior patterns. They are built using machine learning libraries (e.g., TensorFlow, PyTorch) and trained on the data.

[1337] Input: Formatted user data

[1338] Output: Analysis results on user preferences and purchasing behavior

[1339] Step 6: Selecting recommended products

[1340] The generative AI model then selects the best products for the user based on the analysis results. For example, if a user purchases running shoes, it will select related products (e.g., running socks, running wear, etc.).

[1341] Input: Analysis results

[1342] Output: A list of products that are best suited for the user

[1343] Step 7: Generate recommendations

[1344] The generative AI model generates recommendations based on the selected products. Recommendations can take the form of text, images, videos, etc. For example, it might generate a message like, "How about the perfect running socks to go with your new shoes?"

[1345] Input: Selected product list

[1346] Output: Generated recommendation content (text, images, videos)

[1347] Step 8: Notification of recommendation

[1348] The server sends the generated recommendations to the user's device via the API of the external communication tool, securely communicating using an API key or token.

[1349] Input: Generated recommendation

[1350] Output: Recommendation notification sent to the user's device

[1351] Step 9: Accepting user questions

[1352] After receiving a recommendation, users can ask additional questions or make suggestions by sending a text message through the messaging app.

[1353] Input: User question

[1354] Output: User's question received by the server

[1355] Step 10: Parsing the question and generating an answer

[1356] The server sends the user's question to the generative AI model, which analyzes the question and generates an appropriate answer or additional recommendations. For example, it generates an answer such as, "These running socks are available in sizes S, M, and L."

[1357] Input: User question

[1358] Output: Generated answers and additional recommendations

[1359] Step 11: Submit your response

[1360] The server sends the generated answer back to the user's device in real time, and the user receives the answer via a messaging application.

[1361] Input: The answer generated by the generative AI model

[1362] Output: The answer sent to the user's device

[1363] The above processing steps enable accurate collection and analysis of user purchasing behavior data, enabling personalized product recommendations and real-time dialogue.

[1364] (Application example 1)

[1365] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1366] Traditional online shopping systems are limited to a single form of product recommendation for users and are unable to adapt to the environment in which the user is shopping. Furthermore, when users shop in a virtual reality environment, traditional systems lack real-time personalized recommendations and direct chat functionality, limiting the user experience. This makes it difficult for users to enjoy shopping as efficiently and effectively as they would in a physical store.

[1367] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1368] In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, recommendation means for recommending optimal products to the user based on the analysis results, means for displaying products in a virtual reality environment, means for notifying the user of the recommended content via an external communication tool, and chat means for answering questions from the user in real time. This allows the user to receive personalized product recommendations in the virtual reality environment and further enables efficient shopping through real-time dialogue.

[1369] "User Data" means information related to a user's behavior on an online shopping site or virtual store, including, for example, purchase history, browsing history, and click history.

[1370] "Analytical means" means means, including artificial intelligence (AI), for analyzing collected user data, which is used to understand user preferences and purchasing patterns.

[1371] A "recommendation means" is a means for recommending optimal products to users based on analyzed data, and specifically provides recommended content to users in a format that includes text, images, videos, etc.

[1372] A "virtual reality environment" is an environment in which users shop in a virtual space using dedicated headsets or devices.

[1373] "External communication tools" are tools used to notify users of recommendations, and specifically include messaging applications.

[1374] The "chat tool" is a means for providing answers to user questions in real time, and works in conjunction with the generation AI to generate appropriate responses to user questions.

[1375] A system for implementing this invention enhances the online shopping experience by collecting user data, analyzing it, and providing personalized product recommendations in a virtual reality environment. The system includes the following components:

[1376] Hardware and Software Usage

[1377] Hardware:

[1378] VR headset: To realize the virtual reality environment, we use a general-purpose VR headset (e.g., Oculus Quest 2) as an example.

[1379] Smartphone: Use a standard smartphone (iPhone, Android) to receive notifications of recommendations.

[1380] software:

[1381] Generative AI (AI models): Use generative AI models, such as OpenAI GPT-4, to analyze user data and recommend products based on user preferences.

[1382] Server: A standard web server is used to collect, store, analyze, and notify data.

[1383] External communication tool: To notify the recommendation content, we use the API of a messaging application. In this example, we use a general-purpose messaging application.

[1384] Processing Description

[1385] Data collection and analysis

[1386] When a user accesses a virtual store, the server automatically collects user data (user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The collected data is sent to the generation AI for analysis, either periodically or when a specific trigger event occurs. The generation AI analyzes the user data and recognizes the user's preferences and purchasing behavior patterns.

[1387] Recommendation generation and notification

[1388] The AI ​​then selects the most suitable product for the user based on the analysis results and generates recommendations. These recommendations are provided in the form of text, images, and videos. The server then notifies the user of the recommendations created by the AI ​​via the API of an external communication tool.

[1389] Chat feature

[1390] If a user has a question about the recommended content, they can send it in chat format through a messaging application. This question is then sent to the AI ​​via the server, and the AI ​​generates an appropriate answer and sends it back to the user in real time via the server.

[1391] Specific examples

[1392] For example, if User A purchases running shoes in a virtual reality environment, the system operates as follows: The server collects User A's purchase information and stores it in a database. The collected data is then sent to the generation AI, which analyzes User A's preferences. The generation AI uses "running" as a keyword to select related products (e.g., running socks, running wear), and generates a recommendation message containing text and an image saying, "How about the perfect running socks to go with your new shoes?" The server notifies User A's device via the messaging application's API, and User A can receive the recommendation message on their smartphone or in the VR environment.

[1393] Example prompts for generative AI models

[1394] User's purchase history: {"item": "Running shoes", "date": "2023-01-15"}

[1395] User's browsing history: {"item": "Running wear", "date": "2023-01-14"}

[1396] User click history: {"item": "Running socks", "date": "2023-01-13"}

[1397] Recommend the best product for this user.

[1398] In this way, the system of the present invention can analyze user data and provide real-time personalized product recommendations in a virtual reality environment, allowing users to enjoy a more efficient and effective shopping experience.

[1399] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1400] Step 1:

[1401] When a user accesses a virtual store, the server automatically collects user data (e.g., user ID, purchase history, browsing history, click history, etc.) and stores it in a database. The input data is various user behavioral data, and based on this, the server manages the storage volume as database entries. At the same time, a timestamp of user activity is also recorded.

[1402] Step 2:

[1403] The server sends the collected user data to the generation AI for analysis periodically or when a specific trigger event occurs. The input for this process is the user data saved in step 1, and the output is the analysis results such as user preferences, purchasing behavior patterns, and purchase predictions recognized by the generation AI. The generation AI uses prompt statements to perform data analysis and returns the analysis results in text format to the server.

[1404] Step 3:

[1405] The server uses the generation AI to select the most suitable product for the user based on the analysis results from the generation AI. At this time, the generation AI is instructed to "recommend the most suitable product based on the user's purchase history, browsing history, and click history" using specific prompts. The output provided to the server is a list of candidate products and text and image links related to the recommended content.

[1406] Step 4:

[1407] The server uses the recommendation means to notify the user's device of the recommendation content created by the generation AI via the API of the external communication tool. At this time, the recommendation content obtained from the generation AI is used as input, and the recommendation information is notified in real time to the user's smartphone or VR headset as output. Specifically, the server generates an API request and pushes the recommendation content to the user's device.

[1408] Step 5:

[1409] The user checks the recommendations sent to their device and, if they have any questions, sends them in chat format using a messaging application. The input is a text message from the user, which is sent to the server via the messaging application. The server receives this message and forwards the question to the generation AI.

[1410] Step 6:

[1411] The generation AI generates appropriate answers based on questions received from users. The input is the user's question, and the output is the generated answer text. The generation AI analyzes past user data and the content of the question to generate an appropriate answer.

[1412] Step 7:

[1413] The server notifies the user of the answer generated by the AI ​​by sending the reply to the user's device in real time using an external communication tool. The input is the answer text from the AI, and the output is a text message displayed on the user's device. Specifically, the server generates an API request and sends a text message to the messaging application.

[1414] Through these seven steps, user data collection, analysis, personalized product recommendations, and real-time chat support are achieved, allowing users to enjoy an efficient and effective shopping experience even in a virtual reality environment.

[1415] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1416] The present invention is a personalized recommendation system for improving a user's online shopping experience, and is characterized in that it incorporates an emotion engine that recognizes the user's emotions. Embodiments of the present invention are described below.

[1417] System Configuration

[1418] 1. Collection of User Data

[1419] When a user accesses an online shopping site, the server automatically collects data such as the user ID, browsing history, purchase history, and click history, and stores it in a database.

[1420] 2. Data Analysis

[1421] The server stores the collected user data in a database and periodically, or when certain trigger events occur, sends the data to the Generative AI for analysis.

[1422] Generative AI analyzes user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that that brand's products are likely to be preferred.

[1423] 3. Emotional Data Collection and Analysis

[1424] The server collects sentiment data from users' real-time text messages and reviews.

[1425] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[1426] 4. Generating Recommendations

[1427] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[1428] The generative AI takes into account the user's emotional state and generates recommendations with an appropriate tone and content. For example, if the user is expressing joy, the recommendations will include positive messages.

[1429] 5. Notification

[1430] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application), allowing the user to receive recommended products and related information in real time.

[1431] 6. Chat integration

[1432] If a user receives a recommendation and has questions or additional suggestions, they can send their questions in chat format via a messaging application.

[1433] The server receives messages from users and sends the content to the generation AI and emotion engine.

[1434] The generative AI and emotion engine analyze the user's questions and emotions, generate appropriate answers and additional recommendations, and send them back to the user's device in real time via the server.

[1435] Example: System behavior when user B purchases running shoes

[1436] As an example, we will explain the system flow when User B purchases running shoes on an online shopping site.

[1437] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[1438] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[1439] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[1440] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[1441] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[1442] 6. The server notifies User B of this recommendation via the API of the external communication tool. User B receives this recommendation via a messaging application such as LINE.

[1443] 7. The user becomes interested in the recommendation and sends a question via LINE asking, "What size are these socks?"

[1444] 8. The server receives the question and sends it to the generative AI and emotion engine.

[1445] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[1446] In this way, the system according to the present invention analyzes user purchasing behavior data and emotional data and provides personalized product recommendations in real time, thereby significantly improving the online shopping experience.

[1447] The processing flow will be explained below.

[1448] Step 1:

[1449] The device accesses an online shopping site, where the user browses or purchases products.

[1450] Step 2:

[1451] The server automatically collects user data such as user ID, browsing history, purchase history, and click history and stores it in a database.

[1452] Step 3:

[1453] The server retrieves user data from the database periodically or when a specific trigger event occurs and sends it to the generation AI.

[1454] Step 4:

[1455] The Generative AI analyzes the user data and recognizes their preferences and purchasing patterns. For example, if a user frequently purchases shoes from a particular brand, it will determine that they tend to like that brand's products.

[1456] Step 5:

[1457] The server retrieves users' real-time text messages and reviews and sends them to the emotion engine.

[1458] Step 6:

[1459] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.).

[1460] Step 7:

[1461] The generative AI and emotion engine work together to select the best products for the user based on the analysis results. For example, if a user purchases new running shoes, related products (e.g., running socks, running apparel, etc.) will be selected.

[1462] Step 8:

[1463] The AI ​​generator generates recommendations with appropriate tone and content, taking into account the user's emotional state. For example, if the user is expressing joy, the recommendation will include positive messages.

[1464] Step 9:

[1465] The server sends the recommendations created by the generative AI and emotion engine to the user's device via the API of an external communication tool (e.g., a messaging application).

[1466] Step 10:

[1467] If a user receives a recommendation and is interested, they can send a question via a messaging application, such as "What size are these socks?"

[1468] Step 11:

[1469] The server receives questions from users and sends them to the generative AI and emotion engine.

[1470] Step 12:

[1471] The generative AI and emotion engine analyzes the user's question and emotion, generating appropriate answers and emotionally sensitive explanations.

[1472] Step 13:

[1473] The server sends the generated answers back to the user's device in real time via the API of the external communication tool.

[1474] This process improves the online shopping experience by allowing users to receive personalized product recommendations in real time and get quick responses to any follow-up questions.

[1475] Example 2

[1476] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1477] Conventional online shopping systems sometimes recommend products based on a user's preferences and purchasing patterns, but they fail to consider the user's emotional state. As a result, recommendations are sometimes made at inappropriate times or with inappropriate tones, leading to a loss of motivation or dissatisfaction. Furthermore, the lack of a means to quickly and appropriately respond to questions or additional suggestions leads to a poor user experience.

[1478] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1479] In this invention, the server includes means for collecting user online activity data, means for storing the collected user data in a database, and analysis means including a generative artificial intelligence (AI) for analyzing the stored user data, which enables means for collecting emotion data from the analyzed user data, means for analyzing the collected emotion data, means for recommending optimal products taking the user's emotions into consideration based on the analysis results, means for notifying the user of the recommended content via the API of an external communication tool, and chat means for answering questions from users in real time.

[1480] "User online activity data" refers to data such as user ID, browsing history, purchase history, and click history that is recorded when a user accesses an online shopping site.

[1481] A "database" is a data storage device that systematically stores collected user data, making it easy to analyze and search later.

[1482] "Generative artificial intelligence (AI)" is a system that uses advanced analytical algorithms to analyze user data and recognize and understand user preferences and purchasing patterns.

[1483] "Emotional Data" means data that indicates a user's emotional state (e.g., joy, sadness, surprise, etc.) extracted from a user's real-time text messages or reviews.

[1484] An "emotion engine" is a software or hardware system for analyzing collected emotion data and identifying a user's emotional state.

[1485] The "means for recommending optimal products" is a system that has the function of selecting and recommending the most suitable products for users based on analyzed user data and emotional data.

[1486] An "API for external communication tools" is an interface for communicating data between the system and the user's device using a messaging application or other external communication tool.

[1487] A "chat means" is a system with a communication function that responds in real time to questions and additional suggestions from users and provides appropriate answers and additional recommendations.

[1488] This invention provides a personalized recommendation system that utilizes generative AI models and emotion engines to improve users' online shopping experience. By collecting and analyzing users' online activity data and emotion data, the system can recommend the most suitable products to users, significantly improving the user experience.

[1489] System Configuration

[1490] The system includes the following main hardware and software:

[1491] 1. Server:

[1492] It has the ability to collect users' online activity data (e.g., user ID, browsing history, purchase history, click history, etc.) and store it in a database.

[1493] The collected data is sent to and analyzed by Generative Artificial Intelligence (AI), which identifies user preferences and purchasing patterns.

[1494] 2. Database:

[1495] Systematically store collected online activity data, which can then be accessed and analyzed by the generative AI and emotion engine.

[1496] 3. Generation AI:

[1497] By analyzing user data and learning about user preferences and purchasing behavior patterns, the Generative AI generates personalized product recommendations based on the user's purchase and browsing history.

[1498] 4. Emotion Engine:

[1499] It collects sentiment data from users' real-time text messages and reviews and analyzes that data.

[1500] The emotion engine identifies whether the user is expressing emotions such as happiness, sadness, or surprise, and provides this emotional information to the generative AI.

[1501] 5. API for external communication tools:

[1502] It acts as an interface to notify users of the recommended content. As a result, the recommendations generated by the generative AI and emotion engine are sent to the user's device via an external messaging application (e.g., LINE or WhatsApp).

[1503] 6. User Device:

[1504] The device through which users receive recommendations and send questions or additional suggestions. Devices include smartphones, tablets, and PCs.

[1505] Specific examples

[1506] Here is a specific example where User B purchases running shoes on an online shopping site.

[1507] 1. The server collects User B's purchase information (user ID, purchased item, purchase date and time) and stores it in the database.

[1508] 2. The server also sends User B's past purchasing history and browsing history to the generation AI.

[1509] 3. The generation AI analyzes User B's data and selects related products (e.g., running socks, running wear) using the keyword "running."

[1510] 4. The server collects emotion data from User B's text messages and reviews, and the emotion engine analyzes the content to identify the user's emotional state. For example, if User B posts a positive review, the emotion engine identifies the emotion of joy.

[1511] 5. Generative AI and an emotion engine generate recommendations with positive messages, such as, "How about the perfect running socks to go with your new shoes?"

[1512] 6. The server notifies User B of the recommendation via the API of the external communication tool. User B receives the recommendation via a messaging application.

[1513] 7. The user is interested in the recommendation and sends a message asking, "What size are these socks?"

[1514] 8. The server receives the question and sends it to the generative AI and emotion engine.

[1515] 9. The generative AI and emotion engine generate appropriate size information and an explanation that takes emotions into consideration in response to User B's question, and send the response to User B's device in real time via the server.

[1516] Prompt Sentence Examples

[1517] "After User B purchases running shoes, recommend the best running socks as the next product with a positive message."

[1518] Thus, the present invention is a system that significantly improves the online shopping experience by analyzing users' purchasing behavior and emotions and providing personalized product recommendations in real time.

[1519] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1520] Step 1:

[1521] Input: User ID, browsing history, purchase history, click history when the user accesses an online shopping site

[1522] Operation:

[1523] When a user accesses an online shopping site, the server collects data in real time, such as the user ID, browsing history, purchase history, click history, etc. For example, if a user views a page for "running shoes," that information will be recorded.

[1524] Output: Collected user data is stored in a database.

[1525] Step 2:

[1526] Input: User data stored in the database

[1527] Operation:

[1528] The server sends the stored user data to the generation AI periodically or in response to a specific trigger event (e.g., product purchase).

[1529] Output: User data is provided to the generative AI for analysis.

[1530] Step 3:

[1531] Input: User data provided to the generative AI

[1532] Operation:

[1533] The Generative AI analyzes the provided user data and recognizes the user's preferences and purchasing behavior patterns. Specifically, it learns the trends of frequently purchased brands and products. For example, if User B has purchased "running shoes" multiple times in the past, it can identify their preferences.

[1534] Output: Analysis of user preferences and purchasing patterns

[1535] Step 4:

[1536] Input: Real-time text messages and reviews

[1537] Operation:

[1538] The server collects real-time text messages and reviews posted by users. For example, if a user posts a review saying, "These running shoes are great!", the server records the text data.

[1539] Output: Collected text data

[1540] Step 5:

[1541] Input: Collected text data

[1542] Operation:

[1543] The emotion engine analyzes the collected text data and identifies the user's emotional state (e.g., joy, sadness, surprise, etc.). For example, it identifies positive emotions from the keyword "great."

[1544] Output: Parsed user sentiment data

[1545] Step 6:

[1546] Input: Preference analysis results from generative AI and emotional data from the emotion engine

[1547] Operation:

[1548] The generative AI and emotion engine work together to select the best products for the user based on the analysis results and generate recommendations. For example, if a user purchases running shoes, related running socks and apparel will be recommended. If the user expresses positive emotions, the recommendation message will also be positive.

[1549] Output: Generated recommendations

[1550] Step 7:

[1551] Input: Generated recommendation

[1552] Operation:

[1553] The server then sends the generated recommendations to the user's device via the API of an external communication tool, for example, by sending a message about the recommended products using LINE or WhatsApp.

[1554] Output: Recommendations sent to the user's device

[1555] Step 8:

[1556] Input: User message with questions or additional suggestions

[1557] Operation:

[1558] If a user has questions or additional suggestions after receiving a recommendation, they can send a chat question through a messaging application, such as "What size are these socks?"

[1559] Output: A message from the user is sent to the server.

[1560] Step 9:

[1561] Input: Message sent by the user

[1562] Operation:

[1563] The server receives the user's question and sends it to the generative AI and emotion engine.

[1564] Output: Data is provided to the generative AI and emotion engine for analysis.

[1565] Step 10:

[1566] Input: User question and sentiment data

[1567] Operation:

[1568] The generative AI and emotion engine analyze the user's question and emotion to generate appropriate answers and additional recommendations, such as, "These socks fit you perfectly in size medium. We also recommend the same series of running wear."

[1569] Output: Generated answers and additional recommendations

[1570] Step 11:

[1571] Input: Generated answers and additional recommendations

[1572] Operation:

[1573] The server sends the generated answers to the user's device in real time.

[1574] Output: The appropriate answer and additional recommendations sent to the user's device

[1575] Through this series of processing steps, personalized product recommendations based on users' purchasing behavior and emotions can be provided in real time, greatly improving the online shopping experience.

[1576] (Application example 2)

[1577] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1578] In online shopping, it is difficult to recommend products that fully take into account the user's individual needs and emotional state. Current systems mainly make simple recommendations based on the user's purchase and browsing history, which does not improve user satisfaction. It is also difficult to provide immediate and appropriate responses to user questions and requests.

[1579] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user data, analysis means including a generative artificial intelligence (AI) that analyzes the collected user data, means for collecting and analyzing user emotion data, recommendation means for recommending optimal products to the user based on the analysis results and the emotion data, means for notifying the user of the recommendation content via an external communication tool, and chat means for answering questions from the user in real time. This makes it possible to provide personalized recommendations based on the user's preferences and emotional state, and to provide immediate and appropriate responses.

[1580] "User data" refers to information related to online shopping, such as user ID, browsing history, purchase history, and click history.

[1581] "Generative artificial intelligence (AI)" refers to an artificial intelligence technology that analyzes user preferences and purchasing behavior patterns based on large amounts of data and makes optimal recommendations.

[1582] "Analysis Means" means a system or device for analyzing collected User Data.

[1583] "Emotional data" refers to information about a user's emotional state (such as joy, sadness, or surprise) obtained from their text messages, reviews, etc.

[1584] "Recommendation Means" means a system or function for selecting and recommending optimal products to a user based on analyzed user data and emotional data.

[1585] "External communication tools" refers to tools such as messaging applications and emails used to notify users of recommendations.

[1586] "Notification Means" means a system or function for sending recommendations to users via external communication tools.

[1587] "Chat means" means a system or function that provides real-time responses to user questions.

[1588] The present invention is a personalized recommendation system for improving a user's online shopping experience, and in particular, incorporates an emotion engine that recognizes a user's emotions. Specific embodiments of the present invention are described below.

[1589] First, the server collects user data, including user ID, browsing history, purchase history, click history, etc. This data is stored in Amazon RDS.

[1590] The server then periodically sends the data to the Generator AI, either periodically or upon specific trigger events (such as when a product is purchased). The Generator AI uses OpenAI GPT-4 to analyze the user data and recognize their preferences and purchasing patterns.

[1591] The server then collects sentiment data from user reviews and in-app messages, and uses IBM Watson Tone Analyzer as an emotion engine to analyze the collected text data and identify the user's emotional state (e.g., joy, sadness, surprise).

[1592] Based on the analyzed user preferences and emotional data, the generative AI and emotion engine work together to recommend the most suitable products to the user.The recommendations are generated with an appropriate tone and content and sent to the user's smartphone using an external communication tool (such as Twilio API for SMS or LINE Messaging API).

[1593] Users may receive a notification, become interested in the content, and submit a follow-up question. In this case, the server receives the question and sends it to the generation AI and emotion engine. The generation AI and emotion engine analyze the question, generate an appropriate answer, and send it back to the user's smartphone in real time.

[1594] As a concrete example, consider a situation where a user asks a question on LINE, such as "Tell me more about this product." An example of a prompt sentence for this situation would be as follows:

[1595] A user asked a question about a specific product. Product ID:

[12345] Question: "Tell me more about this product"

[1596] An example of the generated AI's response is as follows:

[1597] Hello! These are our latest running shoes, made with lightweight, breathable materials. They fit particularly well and are ideal for long-distance running. They are available in sizes from 22cm to 30cm and in a wide range of colors. If you're interested, you can purchase them here.

[1598] In this way, the system according to the present invention can analyze users' purchasing behavior data and emotional data and provide personalized recommendations in real time, thereby significantly improving the online shopping experience.

[1599] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1600] Step 1:

[1601] User Data Collection

[1602] The server collects user data (user ID, browsing history, purchase history, click history, etc.) every time a user logs in and performs an operation, and stores the data in Amazon RDS. The input is the user operation data, and the output is the stored data.

[1603] Step 2:

[1604] Regular analysis of user data

[1605] The server sends the collected data to OpenAI GPT-4 periodically or upon specific trigger events (e.g., when a product is purchased). The input is user data stored in Amazon RDS, and the output is the analyzed user preferences and purchasing behavior patterns.

[1606] Step 3:

[1607] Collecting Emotional Data

[1608] The server collects sentiment data from user reviews and in-app messages. The input is the reviews and messages posted by users, and the output is the text data.

[1609] Step 4:

[1610] Emotional Data Analysis

[1611] The server sends the collected text data to IBM Watson Tone Analyzer to identify the user's emotional state. The input is the text data of reviews and messages, and the output is the analyzed emotional data (e.g., joy, sadness, surprise, etc.).

[1612] Step 5:

[1613] Recommendation generation

[1614] The generative AI (OpenAI GPT-4) and the emotion engine (IBM Watson Tone Analyzer) work together to select the best products for users based on user data and emotion data. The input is analyzed user preferences and emotion data, and the output is personalized recommendations.

[1615] Step 6:

[1616] Notification of recommendation

[1617] The server uses the Twilio API or LINE Messaging API to notify the user of the generated recommendation content on their smartphone. The input is the generated recommendation content, and the output is a notification sent to the user's smartphone.

[1618] Step 7:

[1619] Receiving and sending user questions

[1620] When a user submits a question in response to a recommendation, the server receives it and sends the question to OpenAI GPT-4 and IBM Watson Tone Analyzer. The input is the question from the user, and the output is sent to the generative AI and emotion engine.

[1621] Step 8:

[1622] Generate answers to questions

[1623] The generative AI and emotion engine analyze the question, generate an appropriate answer, and send it to the server. The input is the user's question, past data, and emotional state, and the output is the generated answer.

[1624] Step 9:

[1625] Notification of response

[1626] The server notifies the user's smartphone of the answers generated by the generative AI and emotion engine via the Twilio API or LINE Messaging API. The input is the generated answer, and the output is the notification sent to the user's smartphone.

[1627] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1628] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1629] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1630] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1631] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1632] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1633] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1634] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1635] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1636] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1637] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1638] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1639] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1640] 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.

[1641] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1642] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1643] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1644] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1645] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1646] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1647] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1648] The following is further disclosed regarding the above embodiment.

[1649] (Claim 1)

[1650] the means by which user data is collected;

[1651] an analytical means including a generative artificial intelligence (AI) that analyzes the collected user data;

[1652] A recommendation means for recommending optimal products to users based on the analysis results;

[1653] A means of notifying users of the recommendations via external communication tools;

[1654] A chat method to answer questions from users in real time,

[1655] A system including:

[1656] (Claim 2)

[1657] 10. The system of claim 1, wherein the system uses a messaging application as an external communication tool.

[1658] (Claim 3)

[1659] 2. The system according to claim 1, wherein the recommendation content provided by the recommendation means is in a format including text, images, and videos.

[1660] "Example 1"

[1661] (Claim 1)

[1662] the means by which user data is collected;

[1663] A means for transmitting collected user data to the generative AI model for analysis periodically or upon the occurrence of specific trigger events;

[1664] A means to select the most suitable product for the user based on the analysis results of the generative AI model and create recommendations;

[1665] A means to notify users of the created recommendations via the API of an external communication tool, and

[1666] A means for accepting questions from users, sending them to a generative AI model, and returning the answers generated by the generative AI model to the user in real time;

[1667] A system including:

[1668] (Claim 2)

[1669] 10. The system of claim 1, wherein the system uses a messaging application as an external communication tool.

[1670] (Claim 3)

[1671] 2. The system according to claim 1, wherein the recommendation content provided by the recommendation means is in a format including text, images, and videos.

[1672] "Application Example 1"

[1673] (Claim 1)

[1674] the means by which user data is collected;

[1675] an analytical means including a generative artificial intelligence (AI) that analyzes the collected user data;

[1676] A recommendation means for recommending optimal products to users based on the analysis results;

[1677] a means for displaying the product in a virtual reality environment;

[1678] A means of notifying users of the recommendations via external communication tools;

[1679] A chat method to answer questions from users in real time,

[1680] A system including:

[1681] (Claim 2)

[1682] 10. The system of claim 1, further comprising means for a user to explore the product in the virtual reality environment.

[1683] (Claim 3)

[1684] 2. The system according to claim 1, wherein the recommendation content provided by the recommendation means is in a format including text, images, and videos.

[1685] "Example 2: Combining Emotion Engines"

[1686] (Claim 1)

[1687] means of collecting your online activity data;

[1688] a means for storing the collected user data in a database;

[1689] an analysis means including a generative artificial intelligence (AI) for analyzing the stored user data;

[1690] a means for collecting emotion data from the analyzed user data;

[1691] means for analyzing the collected emotion data;

[1692] A method for recommending optimal products based on the analysis results and taking into account the user's emotions.

[1693] A means to notify users of the recommendations via the API of external communication tools, and

[1694] A chat method to answer questions from users in real time,

[1695] A system including:

[1696] (Claim 2)

[1697] 10. The system of claim 1, wherein the system uses a messaging application as an external communication tool.

[1698] (Claim 3)

[1699] 2. The system according to claim 1, wherein the recommendation content provided by the recommendation means is in a format including text, images, and videos.

[1700] "Application example 2 when combining emotion engines"

[1701] (Claim 1)

[1702] the means by which user data is collected;

[1703] an analytical means including a generative artificial intelligence (AI) that analyzes the collected user data;

[1704] a means for collecting and analyzing user emotional data;

[1705] a recommendation means for recommending optimal products to users based on the analysis results and emotion data;

[1706] A means of notifying users of the recommendations via external communication tools;

[1707] A chat method to answer questions from users in real time,

[1708] A system including:

[1709] (Claim 2)

[1710] 10. The system of claim 1, wherein the system uses a messaging application as an external communication tool.

[1711] (Claim 3)

[1712] 2. The system according to claim 1, wherein the recommendation content provided by the recommendation means is in a format including text, images, and videos. [Explanation of symbols]

[1713] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. the means by which user data is collected; an analysis means including a generative artificial intelligence for analyzing the collected user data; A recommendation means for recommending optimal products to users based on the analysis results; A means of notifying users of the recommendations via external communication tools; A chat method to answer questions from users in real time, A system including:

2. The system of claim 1 , wherein the external communication tool is a messaging application.

3. 2. The system according to claim 1, wherein the recommendation content provided by the recommendation means is in a format including text, images, and videos.

Images