System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting past purchase behavior data of a customer; means for analyzing the collected purchase behavior data and extracting a purchase behavior pattern for each customer; means for determining an arrangement order of search results and an information configuration of a product detail page that are optimal for the customer based on the extracted purchase behavior pattern; and means for automatically generating a user interface and a user experience that are optimal for the customer using the determined arrangement order of search results and the determined information configuration of the product detail page.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] On e-commerce sites, diverse customers each require a different user interface and user experience (UIUX), but it is difficult to meet all of their needs. Therefore, providing a uniform, non-optimal UIUX can reduce customer motivation and lower purchase rates. The present invention aims to solve this problem and maximize purchase rates by automatically providing an optimized UIUX for each customer. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system including the following means.

[0006] A means of collecting data on customers' past purchasing behavior;

[0007] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[0008] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior pattern;

[0009] A method for automatically generating the optimal user interface and user experience for customers using the determined sort order of search results and information structure of product detail pages.

[0010] It also includes a means for collecting new customer purchasing behavior data and continuously updating customer profiles.

[0011] This makes it possible to continue providing an optimized UIUX every time a customer visits, continuously maximizing the purchase rate of the e-commerce site.

[0012] "Customer" refers to an individual or corporation that uses an e-commerce site to search for and purchase products.

[0013] "Purchasing behavior data" refers to data that includes a customer's product search history on an e-commerce site, browsing information on product detail pages, information on products added to the cart, and purchase history.

[0014] "Analysis" refers to the data analysis process of processing collected purchasing behavior data and extracting customer purchasing behavior patterns.

[0015] "Purchasing behavior patterns" are patterns that indicate how customers behave under specific conditions, and include, for example, tendencies such as preferring products in a specific price range, placing importance on reviews, and looking at a lot of images.

[0016] "Search result sorting" refers to the order in which products are displayed when a customer searches for a product on an e-commerce site, and is optimized based on the customer's purchasing behavior patterns.

[0017] "Information configuration of product detail page" refers to the layout of the page that displays detailed product information and the arrangement of which information is emphasized.

[0018] "User interface" is a general term for the screen design and operation method of the web page that customers directly come into contact with when using an e-commerce site.

[0019] "User experience" refers to the overall experience that customers have while using an e-commerce site, and includes the site's ease of use, comfort, and satisfaction.

[0020] "Automatic generation" is the process by which a system automatically creates the structure and information of a web page based on pre-set algorithms and rules. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0043] The system includes the following main functions:

[0044] 1. Data Collection

[0045] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[0046] 2. Data analysis

[0047] The server analyzes the collected purchasing behavior data and extracts purchasing behavior patterns for each user, including factors that are important when choosing a product (e.g., price, reviews, images, etc.).

[0048] 3. Personalization

[0049] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of the product detail page for the user, such as displaying products in descending order of review ratings or displaying many product photos.

[0050] 4. UIUX automatic generation

[0051] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page.

[0052] 5. Feedback and Improvement

[0053] The server collects new purchasing behavior data from users and continuously updates customer profiles, ensuring that UIUX is always optimized based on the latest data.

[0054] Specific examples

[0055] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[0056] 1. Data Collection

[0057] The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[0058] 2. Data analysis

[0059] The server analyzes Mr. B's purchasing data and reveals that he places importance on images and tends to check reviews.

[0060] 3. Personalization

[0061] Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits the e-commerce site.

[0062] 4. UIUX automatic generation

[0063] The device uses Person B's profile information to display search results and product detail pages optimized for Person B. For example, if Person B searches for "dress," pages with many images and dresses with the highest reviews are displayed.

[0064] 5. Feedback and Improvement

[0065] The server monitors B's new purchasing behavior and updates his profile, further optimizing the UIUX based on the latest information on his next visit.

[0066] Through the above process, users can experience the optimal UIUX tailored to their individual purchasing behavior, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[0070] Step 2:

[0071] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0072] Step 3:

[0073] The server normalizes the data it collects, eliminating duplicate and invalid data and converting it into a consistent, chronological data format.

[0074] Step 4:

[0075] The server analyzes the normalized data to extract purchasing patterns for each user, a process that involves using machine learning algorithms to identify specific behavioral trends (e.g., a penchant for reviews, a preference for certain brands, etc.).

[0076] Step 5:

[0077] The server generates a user profile based on the extracted purchasing behavior patterns. This profile includes factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[0078] Step 6:

[0079] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[0080] Step 7:

[0081] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[0082] Step 8:

[0083] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[0084] Step 9:

[0085] The server collects new purchasing behavior data on users in real time and adds it to the existing database, thus continually updating the user's profile.

[0086] Step 10:

[0087] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[0088] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior, improving the purchase rate on e-commerce sites.

[0089] Example 1

[0090] 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."

[0091] On conventional e-commerce sites, it is difficult to provide an optimal user interface and user experience (UIUX) based on individual customer purchasing behavior, resulting in a lack of improvement in purchase rates. Furthermore, there are also insufficient systems that can dynamically change the UIUX to reflect customer behavior in real time. For this reason, it is necessary to increase customer satisfaction and maximize the purchase rate on e-commerce sites.

[0092] 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.

[0093] In this invention, the server includes means for collecting data on customers' past purchasing behavior, means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer, means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern, means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, means for transmitting data to the terminal in real time, and means for the terminal to display the optimized user interface and user experience. This makes it possible to always provide customers with an optimal purchasing experience based on the latest behavior data.

[0094] "Customer past purchasing behavior data" refers to data that shows a series of actions that a customer has taken on an e-commerce site, such as purchase history, browsing history, product information added to cart, and search history.

[0095] "Means of collection" refers to programs or devices installed to collect data on customers' past purchasing behavior, such as using data tracking tools or analysis platforms.

[0096] "Means of analysis" refers to programs and technologies used to analyze collected customer purchasing behavior data and extract specific trends and patterns.

[0097] "Purchase behavior patterns" are information that indicates the factors and behavioral trends that customers consider important when selecting products. For example, they include patterns such as prioritizing price, checking reviews, and browsing images.

[0098] "Means for determining the optimal order of search results and the information structure of product detail pages" refers to programs or algorithms that determine the display order and information layout of search result pages and product detail pages based on customer purchasing behavior patterns.

[0099] "Means for automatically generating a user interface and user experience" refers to a program or system that uses determined search results and product information to generate the most user-friendly interface and operating experience for customers.

[0100] "Means for transmitting data to the terminal in real time" refers to the programs and protocols that allow the server to instantly transmit analysis results and personalized information to the terminal.

[0101] "Means by which the device displays an optimized user interface and user experience" refers to programs and applications that provide the customer with an optimal interface and experience based on the personalized information received by the device.

[0102] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users. Specifically, it functions as follows:

[0103] Data collection

[0104] The server collects data on customers' past purchasing behavior, specifically using data tracking tools such as Google Analytics and Adobe Analytics to acquire data such as search history, browsing information on product detail pages, products added to carts, and purchase history, and stores this data in a database.

[0105] Data analysis

[0106] The server analyzes the collected purchasing behavior data and extracts purchasing patterns for each customer. This analysis uses Python libraries such as Pandas and Scikit-learn, as well as data warehouses such as Google BigQuery and AWS Redshift. The analysis reveals the factors (such as price, reviews, and images) that each customer considers important when choosing a product.

[0107] Personalization

[0108] The server determines the optimal order of search results and the information structure of product detail pages based on the extracted purchasing behavior patterns. This decision is made using Apache Kafka and RabbitMQ for real-time data processing, and the optimized information is provided to users through front-end frameworks such as React and Vue.js.

[0109] UIUX automatic generation

[0110] The device displays an optimized UI / UX in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The UI / UX is displayed through native applications for iOS and Android, as well as browsers such as Chrome and Safari.

[0111] Feedback and Improvements

[0112] The server collects new purchasing behavior data from users and continuously updates customer profiles. Machine learning algorithms using TensorFlow and Keras are used for updating, enabling more advanced personalization. This ensures that users can continue to experience an optimized UI / UX based on the latest data.

[0113] Specific examples

[0114] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[0115] 1. The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[0116] 2. The server cleans the data using Pandas and extracts purchasing behavior patterns using Scikit-learn. It becomes clear that Person B places importance on images and tends to check reviews.

[0117] 3. Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits.

[0118] 4. The server sends the personalized results to the device via Apache Kafka, and the device generates an optimized UI / UX using React. For example, if user B searches for "dress," pages with many images and dresses with the highest review ratings are displayed.

[0119] 5. The server collects Mr. B's new purchasing behavior using Google Analytics, and then retrains the model using TensorFlow based on the new data.

[0120] Through this process, Mr. B can experience a UIUX that is optimized for his purchasing behavior, resulting in increased purchasing satisfaction on the site.

[0121] Prompt Sentence Examples

[0122] Please explain the specific process of a system that provides optimal UIUX based on purchasing behavior data for a customer named "Mr. B."

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1: Start collecting data

[0125] The server tracks customer activity on the e-commerce site. Specifically, it runs a tracking script and collects data such as customer search history, browsing information on product detail pages, products added to carts, and purchase history using Google Analytics or Adobe Analytics. In this way, the server obtains a variety of purchasing behavior data and stores it in a database. The input is data on customer behavior on the website, and the output is tracked purchasing behavior data.

[0126] Step 2: Initial Data Processing

[0127] The server cleans the collected purchasing behavior data and removes duplicates and missing data. Specifically, it uses the Python library Pandas to clean and shape the data. This results in a clean dataset suitable for analysis. The input is the tracked raw data, and the output is the cleaned data.

[0128] Step 3: Extract purchasing behavior patterns

[0129] The server analyzes the cleaned data using machine learning algorithms to extract purchasing behavior patterns for each customer. Specifically, it uses Scikit-learn and TensorFlow to identify factors (price, reviews, images, etc.) that customers consider important when choosing a product. At this stage, it processes large amounts of data using data warehouses such as Google BigQuery and AWS Redshift. The input is the cleaned data, and the output is the purchasing behavior patterns for each customer.

[0130] Step 4: Decide on personalization

[0131] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. For example, it sets it up so that products are displayed in descending order of review ratings. Apache Kafka and RabbitMQ are used for real-time data processing. The input is the customer's purchasing behavior patterns, and the output is a personalized order of search results and the structure of product detail pages.

[0132] Step 5: Sending personalization data

[0133] The server then sends the determined personalized data to the terminal. This transmission uses a real-time data transfer protocol such as Apache Kafka or RabbitMQ. The input is the personalized search results and product detail page configuration, and the output is the personalized data sent to the terminal.

[0134] Step 6: Automated UI / UX generation

[0135] The device generates and displays an optimized UI / UX based on the personalized data received from the server. Specifically, it uses front-end frameworks such as "React" and "Vue.js" to display optimal search results and product detail pages for customers in real time. The input is the personalized data sent to the device, and the output is the optimized UI / UX displayed to the customer.

[0136] Step 7: Collect new data

[0137] The server collects new customer purchasing behavior data and continuously updates the existing customer profile, for example, by recording newly purchased products or new browsing history. The input is the new purchasing behavior data, and the output is the updated customer profile.

[0138] Step 8: Retrain the model

[0139] The server retrains the machine learning model based on new data to achieve even more accurate personalization. Specifically, the retraining process is performed using TensorFlow and Keras. The input is the updated customer profile and new data, and the output is a machine learning model with improved accuracy.

[0140] Through these steps, customers can experience the optimal user interface and user experience tailored to their individual purchasing behavior, resulting in higher purchase rates and greater customer satisfaction on e-commerce sites.

[0141] (Application example 1)

[0142] 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."

[0143] Conventional e-commerce sites provide the same user interface and user experience to all customers, which means that the site is unable to display content optimally based on each individual customer's purchasing behavior patterns, making it difficult to improve purchase rates. Furthermore, there is a demand for systems that can reflect new purchasing behavior data in real time and keep customer profiles up to date.

[0144] 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.

[0145] In this invention, the server includes: means for collecting past purchasing behavior data of customers; means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer; means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern; means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and information configuration of the product detail page; means for collecting new purchasing behavior data of the customer and updating the customer profile based on the purchasing behavior data; means for inputting prompt sentences into the generation AI model based on the updated customer profile data to further optimize the analysis results of the purchasing behavior pattern; and means for providing the optimized user interface and user experience in real time. This enables optimal display tailored to each individual customer, thereby improving purchase rates and customer satisfaction.

[0146] "Purchasing behavior data" refers to information such as a customer's past product search history, browsing information on product detail pages, products added to cart, and purchase history.

[0147] "Purchasing behavior patterns" refer to certain trends and characteristics in customer purchasing behavior that are extracted by analyzing collected purchasing behavior data.

[0148] "Search result sort order" refers to the order in which products are displayed when a customer searches for a product.

[0149] "Information configuration on product detail page" refers to the layout and order in which detailed information about each product is displayed.

[0150] "User interface" refers to the interface through which a user interacts with a computer system, specifically the screen layout, button arrangement, etc.

[0151] "User experience" refers to the overall experience a user has when using a system.

[0152] "Profile updates" refers to the continuous updating of customer profile information based on new purchasing behavior data.

[0153] A "generative AI model" refers to a model that uses machine learning techniques to generate specific output based on data.

[0154] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0155] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on data on customers' past purchasing behavior, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0156] Hardware and software used

[0157] Smartphone (iOS or Android): Serves as the front end of the user interface.

[0158] Server: Acts as the backend for collecting and analyzing data.

[0159] Database (e.g., PostgreSQL): Used to manage purchasing behavior data.

[0160] Cloud services (AWS, Google Cloud, etc.): Used to operate servers and databases.

[0161] AI model (built with PyTorch, TensorFlow, etc.): Used to analyze and optimize purchasing behavior patterns.

[0162] Specific operation of the system

[0163] Data collection

[0164] The server collects customer purchasing behavior data via smartphones, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0165] Data analysis

[0166] The server analyzes the collected purchasing behavior data and uses an AI model to extract each customer's purchasing behavior patterns, including the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.).

[0167] Personalization

[0168] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of product detail pages for each customer, for example, by displaying products in descending order of review ratings or by displaying more product photos.

[0169] UIUX automatic generation

[0170] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server, making it easier for customers to find the products they are looking for.

[0171] For example, if a user searches for "smartphone," smartphones will be listed in order of highest review rating, and images and reviews will be highlighted on each product detail page.

[0172] Feedback and Improvements

[0173] The server continuously collects new purchasing behavior data from users and updates the customer profile. Based on the updated customer profile data, it inputs prompts into the generative AI model to further optimize the analysis results of purchasing behavior patterns.

[0174] An example of a prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to look at a lot of images and place importance on reviews."

[0175] This allows the system to continually provide an optimized UI / UX based on the latest customer data, which is expected to improve the purchase rate and customer satisfaction on e-commerce sites.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] The server collects customer purchasing behavior data via smartphones. This data includes search history, product detail page browsing information, products added to carts, and purchase history. Specifically, when a user searches for a product or browses a product detail page on their smartphone, that information is sent to the server. The input for data collection is user activity, and the output is purchasing behavior data stored on the server.

[0179] Step 2:

[0180] The server analyzes the collected purchasing behavior data. Using an AI model (using PyTorch and TensorFlow), it extracts purchasing behavior patterns for each customer. These patterns include factors that customers consider important when choosing a product (price, reviews, images, etc.). The input for the data analysis is the collected purchasing behavior data, and the output is the purchasing behavior pattern.

[0181] Step 3:

[0182] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. Specific operations include sorting products by highest review rating and displaying many product photos. The input for personalization is purchasing behavior patterns, and the output is an optimized order of search results and the information structure of product detail pages.

[0183] Step 4:

[0184] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest review ratings are displayed, and multiple images and reviews are highlighted on each product detail page. The input for UIUX auto-generation is the optimized sort order of search results and the information structure of the product detail page, and the output is a customized UIUX displayed on the smartphone.

[0185] Step 5:

[0186] The server continuously collects new purchasing behavior data from users and updates their customer profiles. Based on the updated customer profile data, prompts are input into the generative AI model to further optimize the analysis results of purchasing behavior patterns. An example of a specific prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to check many images and place importance on reviews." The input for feedback and improvement is new purchasing behavior data, and the output is an optimized UI / UX based on the latest analysis results.

[0187] 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.

[0188] This invention is a system that combines customer purchasing behavior data and an emotion engine to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0189] composition

[0190] The system includes the following main functions:

[0191] 1. Data Collection

[0192] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[0193] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes their facial expressions and voice to identify their emotional state. This data is sent to a server.

[0194] 2. Data analysis

[0195] The server analyzes the purchasing behavior data collected and extracts purchasing behavior patterns for each user. It also analyzes the emotional data obtained from the emotion engine to identify what content and products the user will respond positively to.

[0196] 3. Personalization

[0197] The server generates a user profile based on the purchasing behavior patterns and emotional data, which includes the factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state.

[0198] The server determines the order of search results and the information structure of product detail pages based on the user profile.

[0199] 4. UIUX automatic generation

[0200] The device displays a UI / UX optimized for the user in real time based on the data received from the server. For example, if a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the user's emotions.

[0201] 5. Feedback and Improvement

[0202] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[0203] The new data is analyzed again and the UIUX provided for subsequent visits is optimized, ensuring that the user experience is always improved based on the latest data.

[0204] Specific examples

[0205] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[0206] 1. Data Collection

[0207] The server collects data on C's purchasing behavior over the past six months. For example, it records that C has browsed many fashion items and checked images of multiple products before purchasing.

[0208] The device's emotion engine analyzes Mr. C's facial expressions to determine his current emotional state, and this data is sent to the server.

[0209] 2. Data analysis

[0210] The server analyzes C's purchasing data and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[0211] 3. Personalization

[0212] The server creates a profile for C, and the next time C visits the e-commerce site, it automatically generates a product detail page that displays many images and emphasizes review information.The server also dynamically changes the content displayed based on emotional data, displaying prompts and messages that reduce stress.

[0213] 4. UIUX automatic generation

[0214] The device displays search results and product detail pages optimized for C based on her profile information. For example, if C searches for "dress," pages with many images and dresses with the highest reviews are displayed. Furthermore, the content displayed is dynamically adjusted according to C's emotional state.

[0215] 5. Feedback and Improvement

[0216] The server monitors Mr. C's new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information on his next visit.

[0217] Through this process, users can experience the optimal UI / UX tailored to their individual purchasing behavior and emotional state, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[0221] Step 2:

[0222] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0223] Step 3:

[0224] The device's emotion engine analyzes the user's facial and voice data in real time to determine their emotional state. This information is collected, for example, using the user's webcam and microphone.

[0225] Step 4:

[0226] The server normalizes the purchasing behavior data and sentiment data collected, eliminating duplicates and incorrect data and converting it into a time-series data format.

[0227] Step 5:

[0228] The server analyzes the normalized data to extract purchasing patterns for each user, including using machine learning algorithms to identify specific behavioral trends (e.g., a tendency to value reviews or a preference for certain brands).

[0229] Step 6:

[0230] The server analyzes the emotional data to understand the emotional state the user is in when browsing or purchasing products, and can identify patterns such as a decrease in purchasing motivation when stress persists.

[0231] Step 7:

[0232] The server generates a user profile based on purchasing behavior patterns and emotional data, including factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[0233] Step 8:

[0234] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[0235] Step 9:

[0236] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[0237] Step 10:

[0238] The device dynamically changes the content displayed depending on the user's emotional state. For example, if the user is feeling stressed, it will display messages and images that have a relaxing effect, in order to increase the user's desire to purchase.

[0239] Step 11:

[0240] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[0241] Step 12:

[0242] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[0243] Step 13:

[0244] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[0245] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior and emotional state, improving the purchase rate on e-commerce sites.

[0246] Example 2

[0247] 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."

[0248] Conventional e-commerce site systems offered recommendation functions based on customer purchasing behavior data, but they did not optimize the user interface and user experience based on the customer's emotional state. As a result, they ignored the impact of customer emotions on purchasing intent, making it difficult to maximize purchase rates. In addition, customer profiles were static and not updated in real time, making it difficult to respond quickly to changes in customer interests.

[0249] 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.

[0250] In this invention, the server

[0251] A means of collecting data on customers' past purchasing behavior;

[0252] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[0253] A means for collecting customer emotional data in real time and analyzing their emotional state;

[0254] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior patterns and analyzed emotion data;

[0255] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[0256] This allows for the provision of an optimal user interface and user experience based on the customer's purchasing behavior and emotional state.

[0257] "Customer past purchasing behavior data" refers to data related to a customer's past purchases, searches, browsing, products added to carts, and other actions.

[0258] "Purchasing behavior patterns" are the results of analyzing customer purchasing behavior data and extracting specific behavioral characteristics and tendencies exhibited by customers.

[0259] "Emotion data" is data that represents the customer's current emotional state by analyzing the customer's facial expressions, voice, etc.

[0260] The "order of search results" refers to the order in which search results for products are displayed to customers.

[0261] The "information configuration of the product detail page" refers to the layout and content of the information displayed when a customer views the product detail page.

[0262] "User interface" is a general term for the operation screens and display elements that customers encounter when using an e-commerce site.

[0263] "User experience" refers to the overall experience and satisfaction that customers feel while using an e-commerce site.

[0264] A "profile" is a collection of information about an individual customer that is generated based on the customer's purchasing behavior patterns and emotional data.

[0265] This invention is a system that combines customer purchasing behavior data and emotional data to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0266] Components

[0267] server

[0268] The server uses the following hardware and software:

[0269] Data collection: The server can use cloud storage to collect purchasing behavior data, for example, by using the database service of Amazon Web Services (AWS).

[0270] Data analysis: The server can use a data analysis platform to analyze the collected data, for example, AWS Glue to clean, consolidate, and analyze the data.

[0271] Personalization: The server can use a recommendation engine to personalize the user interface, specifically AWS Personalize.

[0272] Feedback: The server can use data monitoring tools to collect new data and update customer profiles in real time.

[0273] Terminal

[0274] The terminal uses the following hardware and software:

[0275] Emotion engine: The device can use the camera and facial expression analysis software to perform emotion analysis, for example, using the Google Cloud Vision API.

[0276] User interface: The device can use a front-end framework to dynamically generate the user interface, for example using ReactJS.

[0277] Specific examples

[0278] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[0279] 1. Data Collection

[0280] The server retrieves data on C's purchasing behavior over the past six months from the AWS database. For example, C browsed many fashion items and checked images of multiple products before purchasing.

[0281] The device's emotion engine analyzes Mr. C's facial expressions using the Google Cloud Vision API to determine his current emotional state, and this data is sent to a server in real time.

[0282] 2. Data analysis

[0283] The server analyzes C's purchasing data using AWS Glue and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[0284] 3. Personalization

[0285] The server uses AWS Personalize to create a profile of C based on his purchasing behavior patterns and emotional data. The server then determines the order of search results and the information structure of the product detail page based on this profile.

[0286] 4. UIUX automatic generation

[0287] The device uses ReactJS to display optimized search results and product detail pages in real time based on C's profile. For example, if C searches for "dress," dresses with many images and the highest reviews are displayed. Furthermore, if C is feeling stressed, a message encouraging her to relax is displayed.

[0288] 5. Feedback and Improvement

[0289] The server collects new purchasing behavior and emotional data about Mr. C in real time and updates his profile, enabling even more accurate personalization on his next visit.

[0290] Example of input to a generative AI model

[0291] By inputting the following prompts into the generative AI model, the AI ​​can explain the specific method for generating optimal UIUX based on user purchasing behavior and emotional data.

[0292] Example prompt:

[0293] Describe a system that generates the optimal user interface and experience in real time based on a user's past purchasing behavior data and current emotional state when shopping online on a website. Specifically, please describe in detail each step of data collection, data analysis, personalization, automated UI / UX generation, and feedback and improvement.

[0294] Using this prompt, the generative AI model can generate sentences that explain the detailed operation of the system and its benefits.

[0295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0296] Step 1:

[0297] Data collection

[0298] The server collects data on users' past purchasing behavior.

[0299] Input: Data such as user search history, product detail page visits, items added to cart, and purchase history.

[0300] Data processing: Store the collected data in an AWS database and perform data cleaning as needed.

[0301] Output: Purchasing behavior data stored in a database.

[0302] The terminal uses an emotion engine to recognize the user's emotions.

[0303] Input: Image and video data captured by a camera of the user's face.

[0304] Data processing: Facial expressions are analyzed using Google Cloud Vision API to identify emotional states.

[0305] Output: Emotion data (e.g., happy, stressed, excited).

[0306] Step 2:

[0307] Data analysis

[0308] The server analyzes the collected purchasing behavior data and sentiment data.

[0309] Input: Collected purchasing behavior and sentiment data.

[0310] Data processing:

[0311] Use AWS Glue to integrate data and extract purchasing behavior patterns.

[0312] Analyze sentiment data to identify what content and products users respond to positively.

[0313] Output: Analysis results of purchasing behavior patterns and sentiment data for each user.

[0314] Step 3:

[0315] Personalization

[0316] The server personalizes the user interface.

[0317] Input: Analyzed buying behavior patterns and sentiment data.

[0318] Data processing:

[0319] Use AWS Personalize to generate user profiles.

[0320] The order of search results and the information structure of product detail pages are determined based on the user profile.

[0321] Output: Personalized user profile and UI configuration data.

[0322] Step 4:

[0323] UIUX automatic generation

[0324] The device displays an optimized UIUX in real time.

[0325] Input: Personalized user profile and UI configuration data.

[0326] Data processing:

[0327] Use ReactJS to generate a dynamic UI based on user profile.

[0328] The content displayed is based on the order of search results and the information structure of the product details page.

[0329] Output: Customer-optimized search results and product detail pages.

[0330] Step 5:

[0331] Feedback and Improvements

[0332] The server collects new purchasing behavior and sentiment data of the user and updates the profile.

[0333] Input: New user purchasing behavior and sentiment data.

[0334] Data processing:

[0335] New data is collected in real time and added to the database.

[0336] Update your existing profile and optimize the UI / UX you provide on subsequent visits.

[0337] Output: Updated user profile and optimized UIUX.

[0338] (Application example 2)

[0339] 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."

[0340] On conventional e-commerce sites, personalization was based solely on data on customers' past purchasing behavior, which meant that the purchasing experience was not optimized enough to take into account the emotional state of each individual customer. Furthermore, because it was not possible to dynamically adjust the displayed content according to the customer's emotional state, there was a lack of an effective approach to increasing purchasing motivation. This made it difficult to improve customer satisfaction and maximize purchase rates.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past purchasing behavior data, means for analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer, means for recognizing and acquiring customer emotion data, means for determining the optimal order of search results and the information configuration of the product detail page for the customer based on the extracted purchasing behavior pattern and emotion data, means for automatically generating the optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, and means for providing dynamic display content according to the customer's emotional state. This makes it possible to provide a personalized purchasing experience according to the customer's emotional state, maximizing purchasing motivation and improving customer satisfaction.

[0342] "Past purchasing behavior data" refers to a series of data related to a customer's purchasing activities, such as product searches, viewing of product detail pages, adding to carts, and purchase history.

[0343] "Purchasing behavior patterns" are data that are analyzed based on collected purchasing behavior data and show consistent trends and preferences when customers select and purchase products.

[0344] "Emotion data" is data that indicates the psychological state and emotional state of a customer, obtained by analyzing the customer's facial expressions and voice.

[0345] "Search result sorting" refers to the order in which the results list is displayed when a customer searches for a product, and is data determined based on specific criteria.

[0346] "Information configuration on product details page" refers to the layout, order, and content of the various information displayed on the product details page, and is a configuration optimized according to the customer's preferences and emotions.

[0347] "User interface" refers to the parts that customers directly touch when interacting with the system, such as the screen design and operation method.

[0348] "User experience" refers to the overall experience and satisfaction that customers feel when using a system, and is a concept related to the ease of use and comfort of the entire system.

[0349] "Dynamic content" refers to content and messages that change in real time depending on the customer's current emotional state.

[0350] The present invention is a system that automatically generates optimal user interfaces and user experiences by combining customer purchasing behavior data and emotional data. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between a server, terminals, and users.

[0351] Hardware and software used

[0352] Server: Database (MySQL), analytical AI (TensorFlow, Keras)

[0353] Device: Smartphone (iOS, Android)

[0354] Emotion recognition engine: OpenCV, Facial Emotion Recognition (FER)

[0355] Data collection

[0356] The server collects data on the customer's past purchasing behavior, including search history, browsing information on product detail pages, items added to carts, and purchase history. The device uses an emotion recognition engine to analyze the customer's facial expressions and voice to identify their emotional state. This data is sent to the server in real time.

[0357] Data analysis

[0358] The server analyzes the collected purchasing behavior data to extract each customer's purchasing behavior patterns. It also analyzes the emotional data obtained from the emotion engine to identify what content and products customers respond positively to.

[0359] Personalization

[0360] The server generates a customer profile based on purchasing behavior patterns and emotional data. This profile includes the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state. The server determines the order of search results and the information structure of product detail pages based on the user profile.

[0361] UIUX automatic generation

[0362] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the customer's emotions.

[0363] Feedback and Improvements

[0364] The server collects new customer purchasing behavior and sentiment data in real time and adds it to the existing database. This continuously updates the customer profile. The new data is analyzed again to optimize the UI / UX provided for subsequent visits. This ensures that the customer experience is always improved based on the latest data.

[0365] Specific examples

[0366] For example, let's say a customer is "Mr. A," who places importance on product reviews and tends to be sensitive to sale information. Furthermore, Mr. A's motivation to purchase tends to decrease when he is stressed. The system optimizes Mr. A's purchasing experience by following the steps below.

[0367] 1. Data collection: The server collects data on A's purchasing behavior over the past six months. For example, it records that A checks many reviews before deciding to purchase. The device's emotion recognition engine analyzes A's facial expressions and identifies his / her current emotional state. This data is sent to the server.

[0368] 2. Data analysis: The server analyzes A's purchasing data and determines that A is review-oriented and sensitive to sales information. It also determines from the emotional data that A's purchasing motivation decreases when he is stressed.

[0369] 3. Personalization: The server creates a profile for Mr. A and automatically generates a product detail page that highlights reviews and sales information the next time he visits the e-commerce site. It also dynamically changes the content displayed based on his emotional data, displaying prompts and messages that reduce stress.

[0370] 4. Automatic UI / UX generation: The device will display search results and product detail pages optimized for Person A based on their profile information. For example, if Person A searches for "smartphone," pages with many images and smartphones with the highest reviews will be displayed. Furthermore, the displayed content will be dynamically adjusted according to Person A's emotional state.

[0371] 5. Feedback and Improvement: The server monitors Mr. A’s new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information during his next visit.

[0372] Example prompt for a generative AI model:

[0373] "User A is review-focused, so if you detect a stressful situation, please display a message that will help them relax."

[0374] The above system provides each customer with an optimized purchasing experience, maximizing purchasing motivation and improving customer satisfaction.

[0375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0376] Step 1:

[0377] The server collects data on customers' past purchasing behavior. Specifically, it collects search history, product detail page browsing information, items added to carts, and purchase history. This data is stored in a database (MySQL) based on the customer's past purchasing behavior. The input is purchasing behavior data, and the output is a structured record.

[0378] Step 2:

[0379] The device uses an emotion recognition engine (OpenCV, Facial Emotion Recognition) to analyze the customer's facial expressions and voice to collect emotional data. It uses the smartphone's camera and microphone to identify the customer's current emotional state and transmits this data to the server in real time. The input is facial expression and voice data, and the output is structured emotional data.

[0380] Step 3:

[0381] The server analyzes the collected purchasing behavior data and emotion data. It processes the data using analytical AI (TensorFlow, Keras) and extracts purchasing behavior and emotion patterns for each customer. The input is purchasing behavior data and emotion data, and the output is purchasing behavior patterns and emotion patterns.

[0382] Step 4:

[0383] The server generates a customer profile based on purchasing behavior and emotional patterns, including factors that customers consider important when choosing a product (price, reviews, images, etc.) and their emotional state. The input is purchasing behavior and emotional patterns, and the output is the customer profile.

[0384] Step 5:

[0385] The server determines the order of search results and the information structure of product detail pages based on the customer profile. AI is used to rank search results and optimize information display according to the customer's emotional state. The input is the customer profile, and the output is the optimized order of search results and the information structure of product detail pages.

[0386] Step 6:

[0387] The device displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The display content also changes dynamically depending on the customer's emotions. The input is the optimized order and information structure of search results, and the output is the UI display content.

[0388] Step 7:

[0389] The server monitors new customer purchasing behavior and emotional data and adds it to the existing database. This continuously updates the customer profile. The AI ​​performs further analysis based on the new data and optimizes the UI / UX provided for subsequent visits. The input is new purchasing behavior and emotional data, and the output is an updated customer profile.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] [Second embodiment]

[0394] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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."

[0406] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0407] The system includes the following main functions:

[0408] 1. Data Collection

[0409] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[0410] 2. Data analysis

[0411] The server analyzes the collected purchasing behavior data and extracts purchasing behavior patterns for each user, including factors that are important when choosing a product (e.g., price, reviews, images, etc.).

[0412] 3. Personalization

[0413] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of the product detail page for the user, such as displaying products in descending order of review ratings or displaying many product photos.

[0414] 4. UIUX automatic generation

[0415] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page.

[0416] 5. Feedback and Improvement

[0417] The server collects new purchasing behavior data from users and continuously updates customer profiles, ensuring that UIUX is always optimized based on the latest data.

[0418] Specific examples

[0419] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[0420] 1. Data Collection

[0421] The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[0422] 2. Data analysis

[0423] The server analyzes Mr. B's purchasing data and reveals that he places importance on images and tends to check reviews.

[0424] 3. Personalization

[0425] Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits the e-commerce site.

[0426] 4. UIUX automatic generation

[0427] The device uses Person B's profile information to display search results and product detail pages optimized for Person B. For example, if Person B searches for "dress," pages with many images and dresses with the highest reviews are displayed.

[0428] 5. Feedback and Improvement

[0429] The server monitors B's new purchasing behavior and updates his profile, further optimizing the UIUX based on the latest information on his next visit.

[0430] Through the above process, users can experience the optimal UIUX tailored to their individual purchasing behavior, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[0431] The processing flow will be explained below.

[0432] Step 1:

[0433] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[0434] Step 2:

[0435] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0436] Step 3:

[0437] The server normalizes the data it collects, eliminating duplicate and invalid data and converting it into a consistent, chronological data format.

[0438] Step 4:

[0439] The server analyzes the normalized data to extract purchasing patterns for each user, a process that involves using machine learning algorithms to identify specific behavioral trends (e.g., a penchant for reviews, a preference for certain brands, etc.).

[0440] Step 5:

[0441] The server generates a user profile based on the extracted purchasing behavior patterns. This profile includes factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[0442] Step 6:

[0443] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[0444] Step 7:

[0445] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[0446] Step 8:

[0447] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[0448] Step 9:

[0449] The server collects new purchasing behavior data on users in real time and adds it to the existing database, thus continually updating the user's profile.

[0450] Step 10:

[0451] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[0452] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior, improving the purchase rate on e-commerce sites.

[0453] Example 1

[0454] 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."

[0455] On conventional e-commerce sites, it is difficult to provide an optimal user interface and user experience (UIUX) based on individual customer purchasing behavior, resulting in a lack of improvement in purchase rates. Furthermore, there are also insufficient systems that can dynamically change the UIUX to reflect customer behavior in real time. For this reason, it is necessary to increase customer satisfaction and maximize the purchase rate on e-commerce sites.

[0456] 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.

[0457] In this invention, the server includes means for collecting data on customers' past purchasing behavior, means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer, means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern, means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, means for transmitting data to the terminal in real time, and means for the terminal to display the optimized user interface and user experience. This makes it possible to always provide customers with an optimal purchasing experience based on the latest behavior data.

[0458] "Customer past purchasing behavior data" refers to data that shows a series of actions that a customer has taken on an e-commerce site, such as purchase history, browsing history, product information added to cart, and search history.

[0459] "Means of collection" refers to programs or devices installed to collect data on customers' past purchasing behavior, such as using data tracking tools or analysis platforms.

[0460] "Means of analysis" refers to programs and technologies used to analyze collected customer purchasing behavior data and extract specific trends and patterns.

[0461] "Purchase behavior patterns" are information that indicates the factors and behavioral trends that customers consider important when selecting products. For example, they include patterns such as prioritizing price, checking reviews, and browsing images.

[0462] "Means for determining the optimal order of search results and the information structure of product detail pages" refers to programs or algorithms that determine the display order and information layout of search result pages and product detail pages based on customer purchasing behavior patterns.

[0463] "Means for automatically generating a user interface and user experience" refers to a program or system that uses determined search results and product information to generate the most user-friendly interface and operating experience for customers.

[0464] "Means for transmitting data to the terminal in real time" refers to the programs and protocols that allow the server to instantly transmit analysis results and personalized information to the terminal.

[0465] "Means by which the device displays an optimized user interface and user experience" refers to programs and applications that provide the customer with an optimal interface and experience based on the personalized information received by the device.

[0466] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users. Specifically, it functions as follows:

[0467] Data collection

[0468] The server collects data on customers' past purchasing behavior, specifically using data tracking tools such as Google Analytics and Adobe Analytics to acquire data such as search history, browsing information on product detail pages, products added to carts, and purchase history, and stores this data in a database.

[0469] Data analysis

[0470] The server analyzes the collected purchasing behavior data and extracts purchasing patterns for each customer. This analysis uses Python libraries such as Pandas and Scikit-learn, as well as data warehouses such as Google BigQuery and AWS Redshift. The analysis reveals the factors (such as price, reviews, and images) that each customer considers important when choosing a product.

[0471] Personalization

[0472] The server determines the optimal order of search results and the information structure of product detail pages based on the extracted purchasing behavior patterns. This decision is made using Apache Kafka and RabbitMQ for real-time data processing, and the optimized information is provided to users through front-end frameworks such as React and Vue.js.

[0473] UIUX automatic generation

[0474] The device displays an optimized UI / UX in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The UI / UX is displayed through native applications for iOS and Android, as well as browsers such as Chrome and Safari.

[0475] Feedback and Improvements

[0476] The server collects new purchasing behavior data from users and continuously updates customer profiles. Machine learning algorithms using TensorFlow and Keras are used for updating, enabling more advanced personalization. This ensures that users can continue to experience an optimized UI / UX based on the latest data.

[0477] Specific examples

[0478] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[0479] 1. The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[0480] 2. The server cleans the data using Pandas and extracts purchasing behavior patterns using Scikit-learn. It becomes clear that Person B places importance on images and tends to check reviews.

[0481] 3. Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits.

[0482] 4. The server sends the personalized results to the device via Apache Kafka, and the device generates an optimized UI / UX using React. For example, if user B searches for "dress," pages with many images and dresses with the highest review ratings are displayed.

[0483] 5. The server collects Mr. B's new purchasing behavior using Google Analytics, and then retrains the model using TensorFlow based on the new data.

[0484] Through this process, Mr. B can experience a UIUX that is optimized for his purchasing behavior, resulting in increased purchasing satisfaction on the site.

[0485] Prompt Sentence Examples

[0486] Please explain the specific process of a system that provides optimal UIUX based on purchasing behavior data for a customer named "Mr. B."

[0487] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0488] Step 1: Start collecting data

[0489] The server tracks customer activity on the e-commerce site. Specifically, it runs a tracking script and collects data such as customer search history, browsing information on product detail pages, products added to carts, and purchase history using Google Analytics or Adobe Analytics. In this way, the server obtains a variety of purchasing behavior data and stores it in a database. The input is data on customer behavior on the website, and the output is tracked purchasing behavior data.

[0490] Step 2: Initial Data Processing

[0491] The server cleans the collected purchasing behavior data and removes duplicates and missing data. Specifically, it uses the Python library Pandas to clean and shape the data. This results in a clean dataset suitable for analysis. The input is the tracked raw data, and the output is the cleaned data.

[0492] Step 3: Extract purchasing behavior patterns

[0493] The server analyzes the cleaned data using machine learning algorithms to extract purchasing behavior patterns for each customer. Specifically, it uses Scikit-learn and TensorFlow to identify factors (price, reviews, images, etc.) that customers consider important when choosing a product. At this stage, it processes large amounts of data using data warehouses such as Google BigQuery and AWS Redshift. The input is the cleaned data, and the output is the purchasing behavior patterns for each customer.

[0494] Step 4: Decide on personalization

[0495] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. For example, it sets it up so that products are displayed in descending order of review ratings. Apache Kafka and RabbitMQ are used for real-time data processing. The input is the customer's purchasing behavior patterns, and the output is a personalized order of search results and the structure of product detail pages.

[0496] Step 5: Sending personalization data

[0497] The server then sends the determined personalized data to the terminal. This transmission uses a real-time data transfer protocol such as Apache Kafka or RabbitMQ. The input is the personalized search results and product detail page configuration, and the output is the personalized data sent to the terminal.

[0498] Step 6: Automated UI / UX generation

[0499] The device generates and displays an optimized UI / UX based on the personalized data received from the server. Specifically, it uses front-end frameworks such as "React" and "Vue.js" to display optimal search results and product detail pages for customers in real time. The input is the personalized data sent to the device, and the output is the optimized UI / UX displayed to the customer.

[0500] Step 7: Collect new data

[0501] The server collects new customer purchasing behavior data and continuously updates the existing customer profile, for example, by recording newly purchased products or new browsing history. The input is the new purchasing behavior data, and the output is the updated customer profile.

[0502] Step 8: Retrain the model

[0503] The server retrains the machine learning model based on new data to achieve even more accurate personalization. Specifically, the retraining process is performed using TensorFlow and Keras. The input is the updated customer profile and new data, and the output is a machine learning model with improved accuracy.

[0504] Through these steps, customers can experience the optimal user interface and user experience tailored to their individual purchasing behavior, resulting in higher purchase rates and greater customer satisfaction on e-commerce sites.

[0505] (Application example 1)

[0506] 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."

[0507] Conventional e-commerce sites provide the same user interface and user experience to all customers, which means that the site is unable to display content optimally based on each individual customer's purchasing behavior patterns, making it difficult to improve purchase rates. Furthermore, there is a demand for systems that can reflect new purchasing behavior data in real time and keep customer profiles up to date.

[0508] 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.

[0509] In this invention, the server includes: means for collecting past purchasing behavior data of customers; means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer; means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern; means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and information configuration of the product detail page; means for collecting new purchasing behavior data of the customer and updating the customer profile based on the purchasing behavior data; means for inputting prompt sentences into the generation AI model based on the updated customer profile data to further optimize the analysis results of the purchasing behavior pattern; and means for providing the optimized user interface and user experience in real time. This enables optimal display tailored to each individual customer, thereby improving purchase rates and customer satisfaction.

[0510] "Purchasing behavior data" refers to information such as a customer's past product search history, browsing information on product detail pages, products added to cart, and purchase history.

[0511] "Purchasing behavior patterns" refer to certain trends and characteristics in customer purchasing behavior that are extracted by analyzing collected purchasing behavior data.

[0512] "Search result sort order" refers to the order in which products are displayed when a customer searches for a product.

[0513] "Information configuration on product detail page" refers to the layout and order in which detailed information about each product is displayed.

[0514] "User interface" refers to the interface through which a user interacts with a computer system, specifically the screen layout, button arrangement, etc.

[0515] "User experience" refers to the overall experience a user has when using a system.

[0516] "Profile updates" refers to the continuous updating of customer profile information based on new purchasing behavior data.

[0517] A "generative AI model" refers to a model that uses machine learning techniques to generate specific output based on data.

[0518] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0519] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on data on customers' past purchasing behavior, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0520] Hardware and software used

[0521] Smartphone (iOS or Android): Serves as the front end of the user interface.

[0522] Server: Acts as the backend for collecting and analyzing data.

[0523] Database (e.g., PostgreSQL): Used to manage purchasing behavior data.

[0524] Cloud services (AWS, Google Cloud, etc.): Used to operate servers and databases.

[0525] AI model (built with PyTorch, TensorFlow, etc.): Used to analyze and optimize purchasing behavior patterns.

[0526] Specific operation of the system

[0527] Data collection

[0528] The server collects customer purchasing behavior data via smartphones, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0529] Data analysis

[0530] The server analyzes the collected purchasing behavior data and uses an AI model to extract each customer's purchasing behavior patterns, including the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.).

[0531] Personalization

[0532] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of product detail pages for each customer, for example, by displaying products in descending order of review ratings or by displaying more product photos.

[0533] UIUX automatic generation

[0534] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server, making it easier for customers to find the products they are looking for.

[0535] For example, if a user searches for "smartphone," smartphones will be listed in order of highest review rating, and images and reviews will be highlighted on each product detail page.

[0536] Feedback and Improvements

[0537] The server continuously collects new purchasing behavior data from users and updates the customer profile. Based on the updated customer profile data, it inputs prompts into the generative AI model to further optimize the analysis results of purchasing behavior patterns.

[0538] An example of a prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to look at a lot of images and place importance on reviews."

[0539] This allows the system to continually provide an optimized UI / UX based on the latest customer data, which is expected to improve the purchase rate and customer satisfaction on e-commerce sites.

[0540] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0541] Step 1:

[0542] The server collects customer purchasing behavior data via smartphones. This data includes search history, product detail page browsing information, products added to carts, and purchase history. Specifically, when a user searches for a product or browses a product detail page on their smartphone, that information is sent to the server. The input for data collection is user activity, and the output is purchasing behavior data stored on the server.

[0543] Step 2:

[0544] The server analyzes the collected purchasing behavior data. Using an AI model (using PyTorch and TensorFlow), it extracts purchasing behavior patterns for each customer. These patterns include factors that customers consider important when choosing a product (price, reviews, images, etc.). The input for the data analysis is the collected purchasing behavior data, and the output is the purchasing behavior pattern.

[0545] Step 3:

[0546] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. Specific operations include sorting products by highest review rating and displaying many product photos. The input for personalization is purchasing behavior patterns, and the output is an optimized order of search results and the information structure of product detail pages.

[0547] Step 4:

[0548] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest review ratings are displayed, and multiple images and reviews are highlighted on each product detail page. The input for UIUX auto-generation is the optimized sort order of search results and the information structure of the product detail page, and the output is a customized UIUX displayed on the smartphone.

[0549] Step 5:

[0550] The server continuously collects new purchasing behavior data from users and updates their customer profiles. Based on the updated customer profile data, prompts are input into the generative AI model to further optimize the analysis results of purchasing behavior patterns. An example of a specific prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to check many images and place importance on reviews." The input for feedback and improvement is new purchasing behavior data, and the output is an optimized UI / UX based on the latest analysis results.

[0551] 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.

[0552] This invention is a system that combines customer purchasing behavior data and an emotion engine to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0553] composition

[0554] The system includes the following main functions:

[0555] 1. Data Collection

[0556] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[0557] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes their facial expressions and voice to identify their emotional state. This data is sent to a server.

[0558] 2. Data analysis

[0559] The server analyzes the purchasing behavior data collected and extracts purchasing behavior patterns for each user. It also analyzes the emotional data obtained from the emotion engine to identify what content and products the user will respond positively to.

[0560] 3. Personalization

[0561] The server generates a user profile based on the purchasing behavior patterns and emotional data, which includes the factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state.

[0562] The server determines the order of search results and the information structure of product detail pages based on the user profile.

[0563] 4. UIUX automatic generation

[0564] The device displays a UI / UX optimized for the user in real time based on the data received from the server. For example, if a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the user's emotions.

[0565] 5. Feedback and Improvement

[0566] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[0567] The new data is analyzed again and the UIUX provided for subsequent visits is optimized, ensuring that the user experience is always improved based on the latest data.

[0568] Specific examples

[0569] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[0570] 1. Data Collection

[0571] The server collects data on C's purchasing behavior over the past six months. For example, it records that C has browsed many fashion items and checked images of multiple products before purchasing.

[0572] The device's emotion engine analyzes Mr. C's facial expressions to determine his current emotional state, and this data is sent to the server.

[0573] 2. Data analysis

[0574] The server analyzes C's purchasing data and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[0575] 3. Personalization

[0576] The server creates a profile for C, and the next time C visits the e-commerce site, it automatically generates a product detail page that displays many images and emphasizes review information.The server also dynamically changes the content displayed based on emotional data, displaying prompts and messages that reduce stress.

[0577] 4. UIUX automatic generation

[0578] The device displays search results and product detail pages optimized for C based on her profile information. For example, if C searches for "dress," pages with many images and dresses with the highest reviews are displayed. Furthermore, the content displayed is dynamically adjusted according to C's emotional state.

[0579] 5. Feedback and Improvement

[0580] The server monitors Mr. C's new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information on his next visit.

[0581] Through this process, users can experience the optimal UI / UX tailored to their individual purchasing behavior and emotional state, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[0582] The processing flow will be explained below.

[0583] Step 1:

[0584] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[0585] Step 2:

[0586] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0587] Step 3:

[0588] The device's emotion engine analyzes the user's facial and voice data in real time to determine their emotional state. This information is collected, for example, using the user's webcam and microphone.

[0589] Step 4:

[0590] The server normalizes the purchasing behavior data and sentiment data collected, eliminating duplicates and incorrect data and converting it into a time-series data format.

[0591] Step 5:

[0592] The server analyzes the normalized data to extract purchasing patterns for each user, including using machine learning algorithms to identify specific behavioral trends (e.g., a tendency to value reviews or a preference for certain brands).

[0593] Step 6:

[0594] The server analyzes the emotional data to understand the emotional state the user is in when browsing or purchasing products, and can identify patterns such as a decrease in purchasing motivation when stress persists.

[0595] Step 7:

[0596] The server generates a user profile based on purchasing behavior patterns and emotional data, including factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[0597] Step 8:

[0598] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[0599] Step 9:

[0600] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[0601] Step 10:

[0602] The device dynamically changes the content displayed depending on the user's emotional state. For example, if the user is feeling stressed, it will display messages and images that have a relaxing effect, in order to increase the user's desire to purchase.

[0603] Step 11:

[0604] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[0605] Step 12:

[0606] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[0607] Step 13:

[0608] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[0609] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior and emotional state, improving the purchase rate on e-commerce sites.

[0610] Example 2

[0611] 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."

[0612] Conventional e-commerce site systems offered recommendation functions based on customer purchasing behavior data, but they did not optimize the user interface and user experience based on the customer's emotional state. As a result, they ignored the impact of customer emotions on purchasing intent, making it difficult to maximize purchase rates. In addition, customer profiles were static and not updated in real time, making it difficult to respond quickly to changes in customer interests.

[0613] 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.

[0614] In this invention, the server

[0615] A means of collecting data on customers' past purchasing behavior;

[0616] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[0617] A means for collecting customer emotional data in real time and analyzing their emotional state;

[0618] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior patterns and analyzed emotion data;

[0619] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[0620] This allows for the provision of an optimal user interface and user experience based on the customer's purchasing behavior and emotional state.

[0621] "Customer past purchasing behavior data" refers to data related to a customer's past purchases, searches, browsing, products added to carts, and other actions.

[0622] "Purchasing behavior patterns" are the results of analyzing customer purchasing behavior data and extracting specific behavioral characteristics and tendencies exhibited by customers.

[0623] "Emotion data" is data that represents the customer's current emotional state by analyzing the customer's facial expressions, voice, etc.

[0624] The "order of search results" refers to the order in which search results for products are displayed to customers.

[0625] The "information configuration of the product detail page" refers to the layout and content of the information displayed when a customer views the product detail page.

[0626] "User interface" is a general term for the operation screens and display elements that customers encounter when using an e-commerce site.

[0627] "User experience" refers to the overall experience and satisfaction that customers feel while using an e-commerce site.

[0628] A "profile" is a collection of information about an individual customer that is generated based on the customer's purchasing behavior patterns and emotional data.

[0629] This invention is a system that combines customer purchasing behavior data and emotional data to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0630] Components

[0631] server

[0632] The server uses the following hardware and software:

[0633] Data collection: The server can use cloud storage to collect purchasing behavior data, for example, by using the database service of Amazon Web Services (AWS).

[0634] Data analysis: The server can use a data analysis platform to analyze the collected data, for example, AWS Glue to clean, consolidate, and analyze the data.

[0635] Personalization: The server can use a recommendation engine to personalize the user interface, specifically AWS Personalize.

[0636] Feedback: The server can use data monitoring tools to collect new data and update customer profiles in real time.

[0637] Terminal

[0638] The terminal uses the following hardware and software:

[0639] Emotion engine: The device can use the camera and facial expression analysis software to perform emotion analysis, for example, using the Google Cloud Vision API.

[0640] User interface: The device can use a front-end framework to dynamically generate the user interface, for example using ReactJS.

[0641] Specific examples

[0642] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[0643] 1. Data Collection

[0644] The server retrieves data on C's purchasing behavior over the past six months from the AWS database. For example, C browsed many fashion items and checked images of multiple products before purchasing.

[0645] The device's emotion engine analyzes Mr. C's facial expressions using the Google Cloud Vision API to determine his current emotional state, and this data is sent to a server in real time.

[0646] 2. Data analysis

[0647] The server analyzes C's purchasing data using AWS Glue and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[0648] 3. Personalization

[0649] The server uses AWS Personalize to create a profile of C based on his purchasing behavior patterns and emotional data. The server then determines the order of search results and the information structure of the product detail page based on this profile.

[0650] 4. UIUX automatic generation

[0651] The device uses ReactJS to display optimized search results and product detail pages in real time based on C's profile. For example, if C searches for "dress," dresses with many images and the highest reviews are displayed. Furthermore, if C is feeling stressed, a message encouraging her to relax is displayed.

[0652] 5. Feedback and Improvement

[0653] The server collects new purchasing behavior and emotional data about Mr. C in real time and updates his profile, enabling even more accurate personalization on his next visit.

[0654] Example of input to a generative AI model

[0655] By inputting the following prompts into the generative AI model, the AI ​​can explain the specific method for generating optimal UIUX based on user purchasing behavior and emotional data.

[0656] Example prompt:

[0657] Describe a system that generates the optimal user interface and experience in real time based on a user's past purchasing behavior data and current emotional state when shopping online on a website. Specifically, please describe in detail each step of data collection, data analysis, personalization, automated UI / UX generation, and feedback and improvement.

[0658] Using this prompt, the generative AI model can generate sentences that explain the detailed operation of the system and its benefits.

[0659] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0660] Step 1:

[0661] Data collection

[0662] The server collects data on users' past purchasing behavior.

[0663] Input: Data such as user search history, product detail page visits, items added to cart, and purchase history.

[0664] Data processing: Store the collected data in an AWS database and perform data cleaning as needed.

[0665] Output: Purchasing behavior data stored in a database.

[0666] The terminal uses an emotion engine to recognize the user's emotions.

[0667] Input: Image and video data captured by a camera of the user's face.

[0668] Data processing: Facial expressions are analyzed using Google Cloud Vision API to identify emotional states.

[0669] Output: Emotion data (e.g., happy, stressed, excited).

[0670] Step 2:

[0671] Data analysis

[0672] The server analyzes the collected purchasing behavior data and sentiment data.

[0673] Input: Collected purchasing behavior and sentiment data.

[0674] Data processing:

[0675] Use AWS Glue to integrate data and extract purchasing behavior patterns.

[0676] Analyze sentiment data to identify what content and products users respond to positively.

[0677] Output: Analysis results of purchasing behavior patterns and sentiment data for each user.

[0678] Step 3:

[0679] Personalization

[0680] The server personalizes the user interface.

[0681] Input: Analyzed buying behavior patterns and sentiment data.

[0682] Data processing:

[0683] Use AWS Personalize to generate user profiles.

[0684] The order of search results and the information structure of product detail pages are determined based on the user profile.

[0685] Output: Personalized user profile and UI configuration data.

[0686] Step 4:

[0687] UIUX automatic generation

[0688] The device displays an optimized UIUX in real time.

[0689] Input: Personalized user profile and UI configuration data.

[0690] Data processing:

[0691] Use ReactJS to generate a dynamic UI based on user profile.

[0692] The content displayed is based on the order of search results and the information structure of the product details page.

[0693] Output: Customer-optimized search results and product detail pages.

[0694] Step 5:

[0695] Feedback and Improvements

[0696] The server collects new purchasing behavior and sentiment data of the user and updates the profile.

[0697] Input: New user purchasing behavior and sentiment data.

[0698] Data processing:

[0699] New data is collected in real time and added to the database.

[0700] Update your existing profile and optimize the UI / UX you provide on subsequent visits.

[0701] Output: Updated user profile and optimized UIUX.

[0702] (Application example 2)

[0703] 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."

[0704] On conventional e-commerce sites, personalization was based solely on data on customers' past purchasing behavior, which meant that the purchasing experience was not optimized enough to take into account the emotional state of each individual customer. Furthermore, because it was not possible to dynamically adjust the displayed content according to the customer's emotional state, there was a lack of an effective approach to increasing purchasing motivation. This made it difficult to improve customer satisfaction and maximize purchase rates.

[0705] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past purchasing behavior data, means for analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer, means for recognizing and acquiring customer emotion data, means for determining the optimal order of search results and the information configuration of the product detail page for the customer based on the extracted purchasing behavior pattern and emotion data, means for automatically generating the optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, and means for providing dynamic display content according to the customer's emotional state. This makes it possible to provide a personalized purchasing experience according to the customer's emotional state, maximizing purchasing motivation and improving customer satisfaction.

[0706] "Past purchasing behavior data" refers to a series of data related to a customer's purchasing activities, such as product searches, viewing of product detail pages, adding to carts, and purchase history.

[0707] "Purchasing behavior patterns" are data that are analyzed based on collected purchasing behavior data and show consistent trends and preferences when customers select and purchase products.

[0708] "Emotion data" is data that indicates the psychological state and emotional state of a customer, obtained by analyzing the customer's facial expressions and voice.

[0709] "Search result sorting" refers to the order in which the results list is displayed when a customer searches for a product, and is data determined based on specific criteria.

[0710] "Information configuration on product details page" refers to the layout, order, and content of the various information displayed on the product details page, and is a configuration optimized according to the customer's preferences and emotions.

[0711] "User interface" refers to the parts that customers directly touch when interacting with the system, such as the screen design and operation method.

[0712] "User experience" refers to the overall experience and satisfaction that customers feel when using a system, and is a concept related to the ease of use and comfort of the entire system.

[0713] "Dynamic content" refers to content and messages that change in real time depending on the customer's current emotional state.

[0714] The present invention is a system that automatically generates optimal user interfaces and user experiences by combining customer purchasing behavior data and emotional data. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between a server, terminals, and users.

[0715] Hardware and software used

[0716] Server: Database (MySQL), analytical AI (TensorFlow, Keras)

[0717] Device: Smartphone (iOS, Android)

[0718] Emotion recognition engine: OpenCV, Facial Emotion Recognition (FER)

[0719] Data collection

[0720] The server collects data on the customer's past purchasing behavior, including search history, browsing information on product detail pages, items added to carts, and purchase history. The device uses an emotion recognition engine to analyze the customer's facial expressions and voice to identify their emotional state. This data is sent to the server in real time.

[0721] Data analysis

[0722] The server analyzes the collected purchasing behavior data to extract each customer's purchasing behavior patterns. It also analyzes the emotional data obtained from the emotion engine to identify what content and products customers respond positively to.

[0723] Personalization

[0724] The server generates a customer profile based on purchasing behavior patterns and emotional data. This profile includes the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state. The server determines the order of search results and the information structure of product detail pages based on the user profile.

[0725] UIUX automatic generation

[0726] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the customer's emotions.

[0727] Feedback and Improvements

[0728] The server collects new customer purchasing behavior and sentiment data in real time and adds it to the existing database. This continuously updates the customer profile. The new data is analyzed again to optimize the UI / UX provided for subsequent visits. This ensures that the customer experience is always improved based on the latest data.

[0729] Specific examples

[0730] For example, let's say a customer is "Mr. A," who places importance on product reviews and tends to be sensitive to sale information. Furthermore, Mr. A's motivation to purchase tends to decrease when he is stressed. The system optimizes Mr. A's purchasing experience by following the steps below.

[0731] 1. Data collection: The server collects data on A's purchasing behavior over the past six months. For example, it records that A checks many reviews before deciding to purchase. The device's emotion recognition engine analyzes A's facial expressions and identifies his / her current emotional state. This data is sent to the server.

[0732] 2. Data analysis: The server analyzes A's purchasing data and determines that A is review-oriented and sensitive to sales information. It also determines from the emotional data that A's purchasing motivation decreases when he is stressed.

[0733] 3. Personalization: The server creates a profile for Mr. A and automatically generates a product detail page that highlights reviews and sales information the next time he visits the e-commerce site. It also dynamically changes the content displayed based on his emotional data, displaying prompts and messages that reduce stress.

[0734] 4. Automatic UI / UX generation: The device will display search results and product detail pages optimized for Person A based on their profile information. For example, if Person A searches for "smartphone," pages with many images and smartphones with the highest reviews will be displayed. Furthermore, the displayed content will be dynamically adjusted according to Person A's emotional state.

[0735] 5. Feedback and Improvement: The server monitors Mr. A’s new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information during his next visit.

[0736] Example prompt for a generative AI model:

[0737] "User A is review-focused, so if you detect a stressful situation, please display a message that will help them relax."

[0738] The above system provides each customer with an optimized purchasing experience, maximizing purchasing motivation and improving customer satisfaction.

[0739] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0740] Step 1:

[0741] The server collects data on customers' past purchasing behavior. Specifically, it collects search history, product detail page browsing information, items added to carts, and purchase history. This data is stored in a database (MySQL) based on the customer's past purchasing behavior. The input is purchasing behavior data, and the output is a structured record.

[0742] Step 2:

[0743] The device uses an emotion recognition engine (OpenCV, Facial Emotion Recognition) to analyze the customer's facial expressions and voice to collect emotional data. It uses the smartphone's camera and microphone to identify the customer's current emotional state and transmits this data to the server in real time. The input is facial expression and voice data, and the output is structured emotional data.

[0744] Step 3:

[0745] The server analyzes the collected purchasing behavior data and emotion data. It processes the data using analytical AI (TensorFlow, Keras) and extracts purchasing behavior and emotion patterns for each customer. The input is purchasing behavior data and emotion data, and the output is purchasing behavior patterns and emotion patterns.

[0746] Step 4:

[0747] The server generates a customer profile based on purchasing behavior and emotional patterns, including factors that customers consider important when choosing a product (price, reviews, images, etc.) and their emotional state. The input is purchasing behavior and emotional patterns, and the output is the customer profile.

[0748] Step 5:

[0749] The server determines the order of search results and the information structure of product detail pages based on the customer profile. AI is used to rank search results and optimize information display according to the customer's emotional state. The input is the customer profile, and the output is the optimized order of search results and the information structure of product detail pages.

[0750] Step 6:

[0751] The device displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The display content also changes dynamically depending on the customer's emotions. The input is the optimized order and information structure of search results, and the output is the UI display content.

[0752] Step 7:

[0753] The server monitors new customer purchasing behavior and emotional data and adds it to the existing database. This continuously updates the customer profile. The AI ​​performs further analysis based on the new data and optimizes the UI / UX provided for subsequent visits. The input is new purchasing behavior and emotional data, and the output is an updated customer profile.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] [Third embodiment]

[0758] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0759] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0760] 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).

[0761] 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.

[0762] 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.

[0763] 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).

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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."

[0770] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0771] The system includes the following main functions:

[0772] 1. Data Collection

[0773] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[0774] 2. Data analysis

[0775] The server analyzes the collected purchasing behavior data and extracts purchasing behavior patterns for each user, including factors that are important when choosing a product (e.g., price, reviews, images, etc.).

[0776] 3. Personalization

[0777] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of the product detail page for the user, such as displaying products in descending order of review ratings or displaying many product photos.

[0778] 4. UIUX automatic generation

[0779] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page.

[0780] 5. Feedback and Improvement

[0781] The server collects new purchasing behavior data from users and continuously updates customer profiles, ensuring that UIUX is always optimized based on the latest data.

[0782] Specific examples

[0783] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[0784] 1. Data Collection

[0785] The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[0786] 2. Data analysis

[0787] The server analyzes Mr. B's purchasing data and reveals that he places importance on images and tends to check reviews.

[0788] 3. Personalization

[0789] Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits the e-commerce site.

[0790] 4. UIUX automatic generation

[0791] The device uses Person B's profile information to display search results and product detail pages optimized for Person B. For example, if Person B searches for "dress," pages with many images and dresses with the highest reviews are displayed.

[0792] 5. Feedback and Improvement

[0793] The server monitors B's new purchasing behavior and updates his profile, further optimizing the UIUX based on the latest information on his next visit.

[0794] Through the above process, users can experience the optimal UIUX tailored to their individual purchasing behavior, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[0795] The processing flow will be explained below.

[0796] Step 1:

[0797] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[0798] Step 2:

[0799] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0800] Step 3:

[0801] The server normalizes the data it collects, eliminating duplicate and invalid data and converting it into a consistent, chronological data format.

[0802] Step 4:

[0803] The server analyzes the normalized data to extract purchasing patterns for each user, a process that involves using machine learning algorithms to identify specific behavioral trends (e.g., a penchant for reviews, a preference for certain brands, etc.).

[0804] Step 5:

[0805] The server generates a user profile based on the extracted purchasing behavior patterns. This profile includes factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[0806] Step 6:

[0807] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[0808] Step 7:

[0809] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[0810] Step 8:

[0811] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[0812] Step 9:

[0813] The server collects new purchasing behavior data on users in real time and adds it to the existing database, thus continually updating the user's profile.

[0814] Step 10:

[0815] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[0816] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior, improving the purchase rate on e-commerce sites.

[0817] Example 1

[0818] 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."

[0819] On conventional e-commerce sites, it is difficult to provide an optimal user interface and user experience (UIUX) based on individual customer purchasing behavior, resulting in a lack of improvement in purchase rates. Furthermore, there are also insufficient systems that can dynamically change the UIUX to reflect customer behavior in real time. For this reason, it is necessary to increase customer satisfaction and maximize the purchase rate on e-commerce sites.

[0820] 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.

[0821] In this invention, the server includes means for collecting data on customers' past purchasing behavior, means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer, means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern, means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, means for transmitting data to the terminal in real time, and means for the terminal to display the optimized user interface and user experience. This makes it possible to always provide customers with an optimal purchasing experience based on the latest behavior data.

[0822] "Customer past purchasing behavior data" refers to data that shows a series of actions that a customer has taken on an e-commerce site, such as purchase history, browsing history, product information added to cart, and search history.

[0823] "Means of collection" refers to programs or devices installed to collect data on customers' past purchasing behavior, such as using data tracking tools or analysis platforms.

[0824] "Means of analysis" refers to programs and technologies used to analyze collected customer purchasing behavior data and extract specific trends and patterns.

[0825] "Purchase behavior patterns" are information that indicates the factors and behavioral trends that customers consider important when selecting products. For example, they include patterns such as prioritizing price, checking reviews, and browsing images.

[0826] "Means for determining the optimal order of search results and the information structure of product detail pages" refers to programs or algorithms that determine the display order and information layout of search result pages and product detail pages based on customer purchasing behavior patterns.

[0827] "Means for automatically generating a user interface and user experience" refers to a program or system that uses determined search results and product information to generate the most user-friendly interface and operating experience for customers.

[0828] "Means for transmitting data to the terminal in real time" refers to the programs and protocols that allow the server to instantly transmit analysis results and personalized information to the terminal.

[0829] "Means by which the device displays an optimized user interface and user experience" refers to programs and applications that provide the customer with an optimal interface and experience based on the personalized information received by the device.

[0830] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users. Specifically, it functions as follows:

[0831] Data collection

[0832] The server collects data on customers' past purchasing behavior, specifically using data tracking tools such as Google Analytics and Adobe Analytics to acquire data such as search history, browsing information on product detail pages, products added to carts, and purchase history, and stores this data in a database.

[0833] Data analysis

[0834] The server analyzes the collected purchasing behavior data and extracts purchasing patterns for each customer. This analysis uses Python libraries such as Pandas and Scikit-learn, as well as data warehouses such as Google BigQuery and AWS Redshift. The analysis reveals the factors (such as price, reviews, and images) that each customer considers important when choosing a product.

[0835] Personalization

[0836] The server determines the optimal order of search results and the information structure of product detail pages based on the extracted purchasing behavior patterns. This decision is made using Apache Kafka and RabbitMQ for real-time data processing, and the optimized information is provided to users through front-end frameworks such as React and Vue.js.

[0837] UIUX automatic generation

[0838] The device displays an optimized UI / UX in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The UI / UX is displayed through native applications for iOS and Android, as well as browsers such as Chrome and Safari.

[0839] Feedback and Improvements

[0840] The server collects new purchasing behavior data from users and continuously updates customer profiles. Machine learning algorithms using TensorFlow and Keras are used for updating, enabling more advanced personalization. This ensures that users can continue to experience an optimized UI / UX based on the latest data.

[0841] Specific examples

[0842] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[0843] 1. The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[0844] 2. The server cleans the data using Pandas and extracts purchasing behavior patterns using Scikit-learn. It becomes clear that Person B places importance on images and tends to check reviews.

[0845] 3. Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits.

[0846] 4. The server sends the personalized results to the device via Apache Kafka, and the device generates an optimized UI / UX using React. For example, if user B searches for "dress," pages with many images and dresses with the highest review ratings are displayed.

[0847] 5. The server collects Mr. B's new purchasing behavior using Google Analytics, and then retrains the model using TensorFlow based on the new data.

[0848] Through this process, Mr. B can experience a UIUX that is optimized for his purchasing behavior, resulting in increased purchasing satisfaction on the site.

[0849] Prompt Sentence Examples

[0850] Please explain the specific process of a system that provides optimal UIUX based on purchasing behavior data for a customer named "Mr. B."

[0851] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0852] Step 1: Start collecting data

[0853] The server tracks customer activity on the e-commerce site. Specifically, it runs a tracking script and collects data such as customer search history, browsing information on product detail pages, products added to carts, and purchase history using Google Analytics or Adobe Analytics. In this way, the server obtains a variety of purchasing behavior data and stores it in a database. The input is data on customer behavior on the website, and the output is tracked purchasing behavior data.

[0854] Step 2: Initial Data Processing

[0855] The server cleans the collected purchasing behavior data and removes duplicates and missing data. Specifically, it uses the Python library Pandas to clean and shape the data. This results in a clean dataset suitable for analysis. The input is the tracked raw data, and the output is the cleaned data.

[0856] Step 3: Extract purchasing behavior patterns

[0857] The server analyzes the cleaned data using machine learning algorithms to extract purchasing behavior patterns for each customer. Specifically, it uses Scikit-learn and TensorFlow to identify factors (price, reviews, images, etc.) that customers consider important when choosing a product. At this stage, it processes large amounts of data using data warehouses such as Google BigQuery and AWS Redshift. The input is the cleaned data, and the output is the purchasing behavior patterns for each customer.

[0858] Step 4: Decide on personalization

[0859] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. For example, it sets it up so that products are displayed in descending order of review ratings. Apache Kafka and RabbitMQ are used for real-time data processing. The input is the customer's purchasing behavior patterns, and the output is a personalized order of search results and the structure of product detail pages.

[0860] Step 5: Sending personalization data

[0861] The server then sends the determined personalized data to the terminal. This transmission uses a real-time data transfer protocol such as Apache Kafka or RabbitMQ. The input is the personalized search results and product detail page configuration, and the output is the personalized data sent to the terminal.

[0862] Step 6: Automated UI / UX generation

[0863] The device generates and displays an optimized UI / UX based on the personalized data received from the server. Specifically, it uses front-end frameworks such as "React" and "Vue.js" to display optimal search results and product detail pages for customers in real time. The input is the personalized data sent to the device, and the output is the optimized UI / UX displayed to the customer.

[0864] Step 7: Collect new data

[0865] The server collects new customer purchasing behavior data and continuously updates the existing customer profile, for example, by recording newly purchased products or new browsing history. The input is the new purchasing behavior data, and the output is the updated customer profile.

[0866] Step 8: Retrain the model

[0867] The server retrains the machine learning model based on new data to achieve even more accurate personalization. Specifically, the retraining process is performed using TensorFlow and Keras. The input is the updated customer profile and new data, and the output is a machine learning model with improved accuracy.

[0868] Through these steps, customers can experience the optimal user interface and user experience tailored to their individual purchasing behavior, resulting in higher purchase rates and greater customer satisfaction on e-commerce sites.

[0869] (Application example 1)

[0870] 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."

[0871] Conventional e-commerce sites provide the same user interface and user experience to all customers, which means that the site is unable to display content optimally based on each individual customer's purchasing behavior patterns, making it difficult to improve purchase rates. Furthermore, there is a demand for systems that can reflect new purchasing behavior data in real time and keep customer profiles up to date.

[0872] 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.

[0873] In this invention, the server includes: means for collecting past purchasing behavior data of customers; means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer; means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern; means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and information configuration of the product detail page; means for collecting new purchasing behavior data of the customer and updating the customer profile based on the purchasing behavior data; means for inputting prompt sentences into the generation AI model based on the updated customer profile data to further optimize the analysis results of the purchasing behavior pattern; and means for providing the optimized user interface and user experience in real time. This enables optimal display tailored to each individual customer, thereby improving purchase rates and customer satisfaction.

[0874] "Purchasing behavior data" refers to information such as a customer's past product search history, browsing information on product detail pages, products added to cart, and purchase history.

[0875] "Purchasing behavior patterns" refer to certain trends and characteristics in customer purchasing behavior that are extracted by analyzing collected purchasing behavior data.

[0876] "Search result sort order" refers to the order in which products are displayed when a customer searches for a product.

[0877] "Information configuration on product detail page" refers to the layout and order in which detailed information about each product is displayed.

[0878] "User interface" refers to the interface through which a user interacts with a computer system, specifically the screen layout, button arrangement, etc.

[0879] "User experience" refers to the overall experience a user has when using a system.

[0880] "Profile updates" refers to the continuous updating of customer profile information based on new purchasing behavior data.

[0881] A "generative AI model" refers to a model that uses machine learning techniques to generate specific output based on data.

[0882] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0883] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on data on customers' past purchasing behavior, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0884] Hardware and software used

[0885] Smartphone (iOS or Android): Serves as the front end of the user interface.

[0886] Server: Acts as the backend for collecting and analyzing data.

[0887] Database (e.g., PostgreSQL): Used to manage purchasing behavior data.

[0888] Cloud services (AWS, Google Cloud, etc.): Used to operate servers and databases.

[0889] AI model (built with PyTorch, TensorFlow, etc.): Used to analyze and optimize purchasing behavior patterns.

[0890] Specific operation of the system

[0891] Data collection

[0892] The server collects customer purchasing behavior data via smartphones, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0893] Data analysis

[0894] The server analyzes the collected purchasing behavior data and uses an AI model to extract each customer's purchasing behavior patterns, including the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.).

[0895] Personalization

[0896] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of product detail pages for each customer, for example, by displaying products in descending order of review ratings or by displaying more product photos.

[0897] UIUX automatic generation

[0898] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server, making it easier for customers to find the products they are looking for.

[0899] For example, if a user searches for "smartphone," smartphones will be listed in order of highest review rating, and images and reviews will be highlighted on each product detail page.

[0900] Feedback and Improvements

[0901] The server continuously collects new purchasing behavior data from users and updates the customer profile. Based on the updated customer profile data, it inputs prompts into the generative AI model to further optimize the analysis results of purchasing behavior patterns.

[0902] An example of a prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to look at a lot of images and place importance on reviews."

[0903] This allows the system to continually provide an optimized UI / UX based on the latest customer data, which is expected to improve the purchase rate and customer satisfaction on e-commerce sites.

[0904] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0905] Step 1:

[0906] The server collects customer purchasing behavior data via smartphones. This data includes search history, product detail page browsing information, products added to carts, and purchase history. Specifically, when a user searches for a product or browses a product detail page on their smartphone, that information is sent to the server. The input for data collection is user activity, and the output is purchasing behavior data stored on the server.

[0907] Step 2:

[0908] The server analyzes the collected purchasing behavior data. Using an AI model (using PyTorch and TensorFlow), it extracts purchasing behavior patterns for each customer. These patterns include factors that customers consider important when choosing a product (price, reviews, images, etc.). The input for the data analysis is the collected purchasing behavior data, and the output is the purchasing behavior pattern.

[0909] Step 3:

[0910] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. Specific operations include sorting products by highest review rating and displaying many product photos. The input for personalization is purchasing behavior patterns, and the output is an optimized order of search results and the information structure of product detail pages.

[0911] Step 4:

[0912] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest review ratings are displayed, and multiple images and reviews are highlighted on each product detail page. The input for UIUX auto-generation is the optimized sort order of search results and the information structure of the product detail page, and the output is a customized UIUX displayed on the smartphone.

[0913] Step 5:

[0914] The server continuously collects new purchasing behavior data from users and updates their customer profiles. Based on the updated customer profile data, prompts are input into the generative AI model to further optimize the analysis results of purchasing behavior patterns. An example of a specific prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to check many images and place importance on reviews." The input for feedback and improvement is new purchasing behavior data, and the output is an optimized UI / UX based on the latest analysis results.

[0915] 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.

[0916] This invention is a system that combines customer purchasing behavior data and an emotion engine to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0917] composition

[0918] The system includes the following main functions:

[0919] 1. Data Collection

[0920] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[0921] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes their facial expressions and voice to identify their emotional state. This data is sent to a server.

[0922] 2. Data analysis

[0923] The server analyzes the purchasing behavior data collected and extracts purchasing behavior patterns for each user. It also analyzes the emotional data obtained from the emotion engine to identify what content and products the user will respond positively to.

[0924] 3. Personalization

[0925] The server generates a user profile based on the purchasing behavior patterns and emotional data, which includes the factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state.

[0926] The server determines the order of search results and the information structure of product detail pages based on the user profile.

[0927] 4. UIUX automatic generation

[0928] The device displays a UI / UX optimized for the user in real time based on the data received from the server. For example, if a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the user's emotions.

[0929] 5. Feedback and Improvement

[0930] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[0931] The new data is analyzed again and the UIUX provided for subsequent visits is optimized, ensuring that the user experience is always improved based on the latest data.

[0932] Specific examples

[0933] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[0934] 1. Data Collection

[0935] The server collects data on C's purchasing behavior over the past six months. For example, it records that C has browsed many fashion items and checked images of multiple products before purchasing.

[0936] The device's emotion engine analyzes Mr. C's facial expressions to determine his current emotional state, and this data is sent to the server.

[0937] 2. Data analysis

[0938] The server analyzes C's purchasing data and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[0939] 3. Personalization

[0940] The server creates a profile for C, and the next time C visits the e-commerce site, it automatically generates a product detail page that displays many images and emphasizes review information.The server also dynamically changes the content displayed based on emotional data, displaying prompts and messages that reduce stress.

[0941] 4. UIUX automatic generation

[0942] The device displays search results and product detail pages optimized for C based on her profile information. For example, if C searches for "dress," pages with many images and dresses with the highest reviews are displayed. Furthermore, the content displayed is dynamically adjusted according to C's emotional state.

[0943] 5. Feedback and Improvement

[0944] The server monitors Mr. C's new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information on his next visit.

[0945] Through this process, users can experience the optimal UI / UX tailored to their individual purchasing behavior and emotional state, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[0946] The processing flow will be explained below.

[0947] Step 1:

[0948] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[0949] Step 2:

[0950] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[0951] Step 3:

[0952] The device's emotion engine analyzes the user's facial and voice data in real time to determine their emotional state. This information is collected, for example, using the user's webcam and microphone.

[0953] Step 4:

[0954] The server normalizes the purchasing behavior data and sentiment data collected, eliminating duplicates and incorrect data and converting it into a time-series data format.

[0955] Step 5:

[0956] The server analyzes the normalized data to extract purchasing patterns for each user, including using machine learning algorithms to identify specific behavioral trends (e.g., a tendency to value reviews or a preference for certain brands).

[0957] Step 6:

[0958] The server analyzes the emotional data to understand the emotional state the user is in when browsing or purchasing products, and can identify patterns such as a decrease in purchasing motivation when stress persists.

[0959] Step 7:

[0960] The server generates a user profile based on purchasing behavior patterns and emotional data, including factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[0961] Step 8:

[0962] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[0963] Step 9:

[0964] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[0965] Step 10:

[0966] The device dynamically changes the content displayed depending on the user's emotional state. For example, if the user is feeling stressed, it will display messages and images that have a relaxing effect, in order to increase the user's desire to purchase.

[0967] Step 11:

[0968] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[0969] Step 12:

[0970] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[0971] Step 13:

[0972] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[0973] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior and emotional state, improving the purchase rate on e-commerce sites.

[0974] Example 2

[0975] 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."

[0976] Conventional e-commerce site systems offered recommendation functions based on customer purchasing behavior data, but they did not optimize the user interface and user experience based on the customer's emotional state. As a result, they ignored the impact of customer emotions on purchasing intent, making it difficult to maximize purchase rates. In addition, customer profiles were static and not updated in real time, making it difficult to respond quickly to changes in customer interests.

[0977] 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.

[0978] In this invention, the server

[0979] A means of collecting data on customers' past purchasing behavior;

[0980] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[0981] A means for collecting customer emotional data in real time and analyzing their emotional state;

[0982] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior patterns and analyzed emotion data;

[0983] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[0984] This allows for the provision of an optimal user interface and user experience based on the customer's purchasing behavior and emotional state.

[0985] "Customer past purchasing behavior data" refers to data related to a customer's past purchases, searches, browsing, products added to carts, and other actions.

[0986] "Purchasing behavior patterns" are the results of analyzing customer purchasing behavior data and extracting specific behavioral characteristics and tendencies exhibited by customers.

[0987] "Emotion data" is data that represents the customer's current emotional state by analyzing the customer's facial expressions, voice, etc.

[0988] The "order of search results" refers to the order in which search results for products are displayed to customers.

[0989] The "information configuration of the product detail page" refers to the layout and content of the information displayed when a customer views the product detail page.

[0990] "User interface" is a general term for the operation screens and display elements that customers encounter when using an e-commerce site.

[0991] "User experience" refers to the overall experience and satisfaction that customers feel while using an e-commerce site.

[0992] A "profile" is a collection of information about an individual customer that is generated based on the customer's purchasing behavior patterns and emotional data.

[0993] This invention is a system that combines customer purchasing behavior data and emotional data to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[0994] Components

[0995] server

[0996] The server uses the following hardware and software:

[0997] Data collection: The server can use cloud storage to collect purchasing behavior data, for example, by using the database service of Amazon Web Services (AWS).

[0998] Data analysis: The server can use a data analysis platform to analyze the collected data, for example, AWS Glue to clean, consolidate, and analyze the data.

[0999] Personalization: The server can use a recommendation engine to personalize the user interface, specifically AWS Personalize.

[1000] Feedback: The server can use data monitoring tools to collect new data and update customer profiles in real time.

[1001] Terminal

[1002] The terminal uses the following hardware and software:

[1003] Emotion engine: The device can use the camera and facial expression analysis software to perform emotion analysis, for example, using the Google Cloud Vision API.

[1004] User interface: The device can use a front-end framework to dynamically generate the user interface, for example using ReactJS.

[1005] Specific examples

[1006] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[1007] 1. Data Collection

[1008] The server retrieves data on C's purchasing behavior over the past six months from the AWS database. For example, C browsed many fashion items and checked images of multiple products before purchasing.

[1009] The device's emotion engine analyzes Mr. C's facial expressions using the Google Cloud Vision API to determine his current emotional state, and this data is sent to a server in real time.

[1010] 2. Data analysis

[1011] The server analyzes C's purchasing data using AWS Glue and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[1012] 3. Personalization

[1013] The server uses AWS Personalize to create a profile of C based on his purchasing behavior patterns and emotional data. The server then determines the order of search results and the information structure of the product detail page based on this profile.

[1014] 4. UIUX automatic generation

[1015] The device uses ReactJS to display optimized search results and product detail pages in real time based on C's profile. For example, if C searches for "dress," dresses with many images and the highest reviews are displayed. Furthermore, if C is feeling stressed, a message encouraging her to relax is displayed.

[1016] 5. Feedback and Improvement

[1017] The server collects new purchasing behavior and emotional data about Mr. C in real time and updates his profile, enabling even more accurate personalization on his next visit.

[1018] Example of input to a generative AI model

[1019] By inputting the following prompts into the generative AI model, the AI ​​can explain the specific method for generating optimal UIUX based on user purchasing behavior and emotional data.

[1020] Example prompt:

[1021] Describe a system that generates the optimal user interface and experience in real time based on a user's past purchasing behavior data and current emotional state when shopping online on a website. Specifically, please describe in detail each step of data collection, data analysis, personalization, automated UI / UX generation, and feedback and improvement.

[1022] Using this prompt, the generative AI model can generate sentences that explain the detailed operation of the system and its benefits.

[1023] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] Data collection

[1026] The server collects data on users' past purchasing behavior.

[1027] Input: Data such as user search history, product detail page visits, items added to cart, and purchase history.

[1028] Data processing: Store the collected data in an AWS database and perform data cleaning as needed.

[1029] Output: Purchasing behavior data stored in a database.

[1030] The terminal uses an emotion engine to recognize the user's emotions.

[1031] Input: Image and video data captured by a camera of the user's face.

[1032] Data processing: Facial expressions are analyzed using Google Cloud Vision API to identify emotional states.

[1033] Output: Emotion data (e.g., happy, stressed, excited).

[1034] Step 2:

[1035] Data analysis

[1036] The server analyzes the collected purchasing behavior data and sentiment data.

[1037] Input: Collected purchasing behavior and sentiment data.

[1038] Data processing:

[1039] Use AWS Glue to integrate data and extract purchasing behavior patterns.

[1040] Analyze sentiment data to identify what content and products users respond to positively.

[1041] Output: Analysis results of purchasing behavior patterns and sentiment data for each user.

[1042] Step 3:

[1043] Personalization

[1044] The server personalizes the user interface.

[1045] Input: Analyzed buying behavior patterns and sentiment data.

[1046] Data processing:

[1047] Use AWS Personalize to generate user profiles.

[1048] The order of search results and the information structure of product detail pages are determined based on the user profile.

[1049] Output: Personalized user profile and UI configuration data.

[1050] Step 4:

[1051] UIUX automatic generation

[1052] The device displays an optimized UIUX in real time.

[1053] Input: Personalized user profile and UI configuration data.

[1054] Data processing:

[1055] Use ReactJS to generate a dynamic UI based on user profile.

[1056] The content displayed is based on the order of search results and the information structure of the product details page.

[1057] Output: Customer-optimized search results and product detail pages.

[1058] Step 5:

[1059] Feedback and Improvements

[1060] The server collects new purchasing behavior and sentiment data of the user and updates the profile.

[1061] Input: New user purchasing behavior and sentiment data.

[1062] Data processing:

[1063] New data is collected in real time and added to the database.

[1064] Update your existing profile and optimize the UI / UX you provide on subsequent visits.

[1065] Output: Updated user profile and optimized UIUX.

[1066] (Application example 2)

[1067] 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."

[1068] On conventional e-commerce sites, personalization was based solely on data on customers' past purchasing behavior, which meant that the purchasing experience was not optimized enough to take into account the emotional state of each individual customer. Furthermore, because it was not possible to dynamically adjust the displayed content according to the customer's emotional state, there was a lack of an effective approach to increasing purchasing motivation. This made it difficult to improve customer satisfaction and maximize purchase rates.

[1069] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past purchasing behavior data, means for analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer, means for recognizing and acquiring customer emotion data, means for determining the optimal order of search results and the information configuration of the product detail page for the customer based on the extracted purchasing behavior pattern and emotion data, means for automatically generating the optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, and means for providing dynamic display content according to the customer's emotional state. This makes it possible to provide a personalized purchasing experience according to the customer's emotional state, maximizing purchasing motivation and improving customer satisfaction.

[1070] "Past purchasing behavior data" refers to a series of data related to a customer's purchasing activities, such as product searches, viewing of product detail pages, adding to carts, and purchase history.

[1071] "Purchasing behavior patterns" are data that are analyzed based on collected purchasing behavior data and show consistent trends and preferences when customers select and purchase products.

[1072] "Emotion data" is data that indicates the psychological state and emotional state of a customer, obtained by analyzing the customer's facial expressions and voice.

[1073] "Search result sorting" refers to the order in which the results list is displayed when a customer searches for a product, and is data determined based on specific criteria.

[1074] "Information configuration on product details page" refers to the layout, order, and content of the various information displayed on the product details page, and is a configuration optimized according to the customer's preferences and emotions.

[1075] "User interface" refers to the parts that customers directly touch when interacting with the system, such as the screen design and operation method.

[1076] "User experience" refers to the overall experience and satisfaction that customers feel when using a system, and is a concept related to the ease of use and comfort of the entire system.

[1077] "Dynamic content" refers to content and messages that change in real time depending on the customer's current emotional state.

[1078] The present invention is a system that automatically generates optimal user interfaces and user experiences by combining customer purchasing behavior data and emotional data. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between a server, terminals, and users.

[1079] Hardware and software used

[1080] Server: Database (MySQL), analytical AI (TensorFlow, Keras)

[1081] Device: Smartphone (iOS, Android)

[1082] Emotion recognition engine: OpenCV, Facial Emotion Recognition (FER)

[1083] Data collection

[1084] The server collects data on the customer's past purchasing behavior, including search history, browsing information on product detail pages, items added to carts, and purchase history. The device uses an emotion recognition engine to analyze the customer's facial expressions and voice to identify their emotional state. This data is sent to the server in real time.

[1085] Data analysis

[1086] The server analyzes the collected purchasing behavior data to extract each customer's purchasing behavior patterns. It also analyzes the emotional data obtained from the emotion engine to identify what content and products customers respond positively to.

[1087] Personalization

[1088] The server generates a customer profile based on purchasing behavior patterns and emotional data. This profile includes the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state. The server determines the order of search results and the information structure of product detail pages based on the user profile.

[1089] UIUX automatic generation

[1090] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the customer's emotions.

[1091] Feedback and Improvements

[1092] The server collects new customer purchasing behavior and sentiment data in real time and adds it to the existing database. This continuously updates the customer profile. The new data is analyzed again to optimize the UI / UX provided for subsequent visits. This ensures that the customer experience is always improved based on the latest data.

[1093] Specific examples

[1094] For example, let's say a customer is "Mr. A," who places importance on product reviews and tends to be sensitive to sale information. Furthermore, Mr. A's motivation to purchase tends to decrease when he is stressed. The system optimizes Mr. A's purchasing experience by following the steps below.

[1095] 1. Data collection: The server collects data on A's purchasing behavior over the past six months. For example, it records that A checks many reviews before deciding to purchase. The device's emotion recognition engine analyzes A's facial expressions and identifies his / her current emotional state. This data is sent to the server.

[1096] 2. Data analysis: The server analyzes A's purchasing data and determines that A is review-oriented and sensitive to sales information. It also determines from the emotional data that A's purchasing motivation decreases when he is stressed.

[1097] 3. Personalization: The server creates a profile for Mr. A and automatically generates a product detail page that highlights reviews and sales information the next time he visits the e-commerce site. It also dynamically changes the content displayed based on his emotional data, displaying prompts and messages that reduce stress.

[1098] 4. Automatic UI / UX generation: The device will display search results and product detail pages optimized for Person A based on their profile information. For example, if Person A searches for "smartphone," pages with many images and smartphones with the highest reviews will be displayed. Furthermore, the displayed content will be dynamically adjusted according to Person A's emotional state.

[1099] 5. Feedback and Improvement: The server monitors Mr. A’s new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information during his next visit.

[1100] Example prompt for a generative AI model:

[1101] "User A is review-focused, so if you detect a stressful situation, please display a message that will help them relax."

[1102] The above system provides each customer with an optimized purchasing experience, maximizing purchasing motivation and improving customer satisfaction.

[1103] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1104] Step 1:

[1105] The server collects data on customers' past purchasing behavior. Specifically, it collects search history, product detail page browsing information, items added to carts, and purchase history. This data is stored in a database (MySQL) based on the customer's past purchasing behavior. The input is purchasing behavior data, and the output is a structured record.

[1106] Step 2:

[1107] The device uses an emotion recognition engine (OpenCV, Facial Emotion Recognition) to analyze the customer's facial expressions and voice to collect emotional data. It uses the smartphone's camera and microphone to identify the customer's current emotional state and transmits this data to the server in real time. The input is facial expression and voice data, and the output is structured emotional data.

[1108] Step 3:

[1109] The server analyzes the collected purchasing behavior data and emotion data. It processes the data using analytical AI (TensorFlow, Keras) and extracts purchasing behavior and emotion patterns for each customer. The input is purchasing behavior data and emotion data, and the output is purchasing behavior patterns and emotion patterns.

[1110] Step 4:

[1111] The server generates a customer profile based on purchasing behavior and emotional patterns, including factors that customers consider important when choosing a product (price, reviews, images, etc.) and their emotional state. The input is purchasing behavior and emotional patterns, and the output is the customer profile.

[1112] Step 5:

[1113] The server determines the order of search results and the information structure of product detail pages based on the customer profile. AI is used to rank search results and optimize information display according to the customer's emotional state. The input is the customer profile, and the output is the optimized order of search results and the information structure of product detail pages.

[1114] Step 6:

[1115] The device displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The display content also changes dynamically depending on the customer's emotions. The input is the optimized order and information structure of search results, and the output is the UI display content.

[1116] Step 7:

[1117] The server monitors new customer purchasing behavior and emotional data and adds it to the existing database. This continuously updates the customer profile. The AI ​​performs further analysis based on the new data and optimizes the UI / UX provided for subsequent visits. The input is new purchasing behavior and emotional data, and the output is an updated customer profile.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] [Fourth embodiment]

[1122] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1123] 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.

[1124] 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).

[1125] 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.

[1126] 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.

[1127] 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).

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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."

[1135] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[1136] The system includes the following main functions:

[1137] 1. Data Collection

[1138] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[1139] 2. Data analysis

[1140] The server analyzes the collected purchasing behavior data and extracts purchasing behavior patterns for each user, including factors that are important when choosing a product (e.g., price, reviews, images, etc.).

[1141] 3. Personalization

[1142] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of the product detail page for the user, such as displaying products in descending order of review ratings or displaying many product photos.

[1143] 4. UIUX automatic generation

[1144] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page.

[1145] 5. Feedback and Improvement

[1146] The server collects new purchasing behavior data from users and continuously updates customer profiles, ensuring that UIUX is always optimized based on the latest data.

[1147] Specific examples

[1148] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[1149] 1. Data Collection

[1150] The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[1151] 2. Data analysis

[1152] The server analyzes Mr. B's purchasing data and reveals that he places importance on images and tends to check reviews.

[1153] 3. Personalization

[1154] Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits the e-commerce site.

[1155] 4. UIUX automatic generation

[1156] The device uses Person B's profile information to display search results and product detail pages optimized for Person B. For example, if Person B searches for "dress," pages with many images and dresses with the highest reviews are displayed.

[1157] 5. Feedback and Improvement

[1158] The server monitors B's new purchasing behavior and updates his profile, further optimizing the UIUX based on the latest information on his next visit.

[1159] Through the above process, users can experience the optimal UIUX tailored to their individual purchasing behavior, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[1163] Step 2:

[1164] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[1165] Step 3:

[1166] The server normalizes the data it collects, eliminating duplicate and invalid data and converting it into a consistent, chronological data format.

[1167] Step 4:

[1168] The server analyzes the normalized data to extract purchasing patterns for each user, a process that involves using machine learning algorithms to identify specific behavioral trends (e.g., a penchant for reviews, a preference for certain brands, etc.).

[1169] Step 5:

[1170] The server generates a user profile based on the extracted purchasing behavior patterns. This profile includes factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[1171] Step 6:

[1172] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[1173] Step 7:

[1174] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[1175] Step 8:

[1176] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[1177] Step 9:

[1178] The server collects new purchasing behavior data on users in real time and adds it to the existing database, thus continually updating the user's profile.

[1179] Step 10:

[1180] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[1181] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior, improving the purchase rate on e-commerce sites.

[1182] Example 1

[1183] 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."

[1184] On conventional e-commerce sites, it is difficult to provide an optimal user interface and user experience (UIUX) based on individual customer purchasing behavior, resulting in a lack of improvement in purchase rates. Furthermore, there are also insufficient systems that can dynamically change the UIUX to reflect customer behavior in real time. For this reason, it is necessary to increase customer satisfaction and maximize the purchase rate on e-commerce sites.

[1185] 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.

[1186] In this invention, the server includes means for collecting data on customers' past purchasing behavior, means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer, means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern, means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, means for transmitting data to the terminal in real time, and means for the terminal to display the optimized user interface and user experience. This makes it possible to always provide customers with an optimal purchasing experience based on the latest behavior data.

[1187] "Customer past purchasing behavior data" refers to data that shows a series of actions that a customer has taken on an e-commerce site, such as purchase history, browsing history, product information added to cart, and search history.

[1188] "Means of collection" refers to programs or devices installed to collect data on customers' past purchasing behavior, such as using data tracking tools or analysis platforms.

[1189] "Means of analysis" refers to programs and technologies used to analyze collected customer purchasing behavior data and extract specific trends and patterns.

[1190] "Purchase behavior patterns" are information that indicates the factors and behavioral trends that customers consider important when selecting products. For example, they include patterns such as prioritizing price, checking reviews, and browsing images.

[1191] "Means for determining the optimal order of search results and the information structure of product detail pages" refers to programs or algorithms that determine the display order and information layout of search result pages and product detail pages based on customer purchasing behavior patterns.

[1192] "Means for automatically generating a user interface and user experience" refers to a program or system that uses determined search results and product information to generate the most user-friendly interface and operating experience for customers.

[1193] "Means for transmitting data to the terminal in real time" refers to the programs and protocols that allow the server to instantly transmit analysis results and personalized information to the terminal.

[1194] "Means by which the device displays an optimized user interface and user experience" refers to programs and applications that provide the customer with an optimal interface and experience based on the personalized information received by the device.

[1195] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on customer purchasing behavior data, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users. Specifically, it functions as follows:

[1196] Data collection

[1197] The server collects data on customers' past purchasing behavior, specifically using data tracking tools such as Google Analytics and Adobe Analytics to acquire data such as search history, browsing information on product detail pages, products added to carts, and purchase history, and stores this data in a database.

[1198] Data analysis

[1199] The server analyzes the collected purchasing behavior data and extracts purchasing patterns for each customer. This analysis uses Python libraries such as Pandas and Scikit-learn, as well as data warehouses such as Google BigQuery and AWS Redshift. The analysis reveals the factors (such as price, reviews, and images) that each customer considers important when choosing a product.

[1200] Personalization

[1201] The server determines the optimal order of search results and the information structure of product detail pages based on the extracted purchasing behavior patterns. This decision is made using Apache Kafka and RabbitMQ for real-time data processing, and the optimized information is provided to users through front-end frameworks such as React and Vue.js.

[1202] UIUX automatic generation

[1203] The device displays an optimized UI / UX in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The UI / UX is displayed through native applications for iOS and Android, as well as browsers such as Chrome and Safari.

[1204] Feedback and Improvements

[1205] The server collects new purchasing behavior data from users and continuously updates customer profiles. Machine learning algorithms using TensorFlow and Keras are used for updating, enabling more advanced personalization. This ensures that users can continue to experience an optimized UI / UX based on the latest data.

[1206] Specific examples

[1207] Let's say the user is a customer named "Mr. B." When purchasing fashion items, Mr. B tends to check many images and refer to reviews. Below we will show how this system optimizes Mr. B's purchasing experience.

[1208] 1. The server collects data on B's purchasing behavior over the past six months. For example, it records that B has browsed many fashion items and checked images of multiple products before purchasing.

[1209] 2. The server cleans the data using Pandas and extracts purchasing behavior patterns using Scikit-learn. It becomes clear that Person B places importance on images and tends to check reviews.

[1210] 3. Based on Mr. B's profile, the server automatically generates a product detail page that displays many images and highlights review information the next time Mr. B visits.

[1211] 4. The server sends the personalized results to the device via Apache Kafka, and the device generates an optimized UI / UX using React. For example, if user B searches for "dress," pages with many images and dresses with the highest review ratings are displayed.

[1212] 5. The server collects Mr. B's new purchasing behavior using Google Analytics, and then retrains the model using TensorFlow based on the new data.

[1213] Through this process, Mr. B can experience a UIUX that is optimized for his purchasing behavior, resulting in increased purchasing satisfaction on the site.

[1214] Prompt Sentence Examples

[1215] Please explain the specific process of a system that provides optimal UIUX based on purchasing behavior data for a customer named "Mr. B."

[1216] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1217] Step 1: Start collecting data

[1218] The server tracks customer activity on the e-commerce site. Specifically, it runs a tracking script and collects data such as customer search history, browsing information on product detail pages, products added to carts, and purchase history using Google Analytics or Adobe Analytics. In this way, the server obtains a variety of purchasing behavior data and stores it in a database. The input is data on customer behavior on the website, and the output is tracked purchasing behavior data.

[1219] Step 2: Initial Data Processing

[1220] The server cleans the collected purchasing behavior data and removes duplicates and missing data. Specifically, it uses the Python library Pandas to clean and shape the data. This results in a clean dataset suitable for analysis. The input is the tracked raw data, and the output is the cleaned data.

[1221] Step 3: Extract purchasing behavior patterns

[1222] The server analyzes the cleaned data using machine learning algorithms to extract purchasing behavior patterns for each customer. Specifically, it uses Scikit-learn and TensorFlow to identify factors (price, reviews, images, etc.) that customers consider important when choosing a product. At this stage, it processes large amounts of data using data warehouses such as Google BigQuery and AWS Redshift. The input is the cleaned data, and the output is the purchasing behavior patterns for each customer.

[1223] Step 4: Decide on personalization

[1224] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. For example, it sets it up so that products are displayed in descending order of review ratings. Apache Kafka and RabbitMQ are used for real-time data processing. The input is the customer's purchasing behavior patterns, and the output is a personalized order of search results and the structure of product detail pages.

[1225] Step 5: Sending personalization data

[1226] The server then sends the determined personalized data to the terminal. This transmission uses a real-time data transfer protocol such as Apache Kafka or RabbitMQ. The input is the personalized search results and product detail page configuration, and the output is the personalized data sent to the terminal.

[1227] Step 6: Automated UI / UX generation

[1228] The device generates and displays an optimized UI / UX based on the personalized data received from the server. Specifically, it uses front-end frameworks such as "React" and "Vue.js" to display optimal search results and product detail pages for customers in real time. The input is the personalized data sent to the device, and the output is the optimized UI / UX displayed to the customer.

[1229] Step 7: Collect new data

[1230] The server collects new customer purchasing behavior data and continuously updates the existing customer profile, for example, by recording newly purchased products or new browsing history. The input is the new purchasing behavior data, and the output is the updated customer profile.

[1231] Step 8: Retrain the model

[1232] The server retrains the machine learning model based on new data to achieve even more accurate personalization. Specifically, the retraining process is performed using TensorFlow and Keras. The input is the updated customer profile and new data, and the output is a machine learning model with improved accuracy.

[1233] Through these steps, customers can experience the optimal user interface and user experience tailored to their individual purchasing behavior, resulting in higher purchase rates and greater customer satisfaction on e-commerce sites.

[1234] (Application example 1)

[1235] 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."

[1236] Conventional e-commerce sites provide the same user interface and user experience to all customers, which means that the site is unable to display content optimally based on each individual customer's purchasing behavior patterns, making it difficult to improve purchase rates. Furthermore, there is a demand for systems that can reflect new purchasing behavior data in real time and keep customer profiles up to date.

[1237] 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.

[1238] In this invention, the server includes: means for collecting past purchasing behavior data of customers; means for analyzing the collected purchasing behavior data to extract purchasing behavior patterns for each customer; means for determining an optimal order of search results and an information configuration of a product detail page for the customer based on the extracted purchasing behavior pattern; means for automatically generating an optimal user interface and user experience for the customer using the determined order of search results and information configuration of the product detail page; means for collecting new purchasing behavior data of the customer and updating the customer profile based on the purchasing behavior data; means for inputting prompt sentences into the generation AI model based on the updated customer profile data to further optimize the analysis results of the purchasing behavior pattern; and means for providing the optimized user interface and user experience in real time. This enables optimal display tailored to each individual customer, thereby improving purchase rates and customer satisfaction.

[1239] "Purchasing behavior data" refers to information such as a customer's past product search history, browsing information on product detail pages, products added to cart, and purchase history.

[1240] "Purchasing behavior patterns" refer to certain trends and characteristics in customer purchasing behavior that are extracted by analyzing collected purchasing behavior data.

[1241] "Search result sort order" refers to the order in which products are displayed when a customer searches for a product.

[1242] "Information configuration on product detail page" refers to the layout and order in which detailed information about each product is displayed.

[1243] "User interface" refers to the interface through which a user interacts with a computer system, specifically the screen layout, button arrangement, etc.

[1244] "User experience" refers to the overall experience a user has when using a system.

[1245] "Profile updates" refers to the continuous updating of customer profile information based on new purchasing behavior data.

[1246] A "generative AI model" refers to a model that uses machine learning techniques to generate specific output based on data.

[1247] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[1248] This invention is a system that automatically generates an optimal user interface and user experience (UIUX) based on data on customers' past purchasing behavior, maximizing the purchase rate of e-commerce sites. The system of this invention is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[1249] Hardware and software used

[1250] Smartphone (iOS or Android): Serves as the front end of the user interface.

[1251] Server: Acts as the backend for collecting and analyzing data.

[1252] Database (e.g., PostgreSQL): Used to manage purchasing behavior data.

[1253] Cloud services (AWS, Google Cloud, etc.): Used to operate servers and databases.

[1254] AI model (built with PyTorch, TensorFlow, etc.): Used to analyze and optimize purchasing behavior patterns.

[1255] Specific operation of the system

[1256] Data collection

[1257] The server collects customer purchasing behavior data via smartphones, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[1258] Data analysis

[1259] The server analyzes the collected purchasing behavior data and uses an AI model to extract each customer's purchasing behavior patterns, including the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.).

[1260] Personalization

[1261] Based on the extracted purchasing behavior patterns, the server determines the optimal order of search results and the information structure of product detail pages for each customer, for example, by displaying products in descending order of review ratings or by displaying more product photos.

[1262] UIUX automatic generation

[1263] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server, making it easier for customers to find the products they are looking for.

[1264] For example, if a user searches for "smartphone," smartphones will be listed in order of highest review rating, and images and reviews will be highlighted on each product detail page.

[1265] Feedback and Improvements

[1266] The server continuously collects new purchasing behavior data from users and updates the customer profile. Based on the updated customer profile data, it inputs prompts into the generative AI model to further optimize the analysis results of purchasing behavior patterns.

[1267] An example of a prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to look at a lot of images and place importance on reviews."

[1268] This allows the system to continually provide an optimized UI / UX based on the latest customer data, which is expected to improve the purchase rate and customer satisfaction on e-commerce sites.

[1269] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1270] Step 1:

[1271] The server collects customer purchasing behavior data via smartphones. This data includes search history, product detail page browsing information, products added to carts, and purchase history. Specifically, when a user searches for a product or browses a product detail page on their smartphone, that information is sent to the server. The input for data collection is user activity, and the output is purchasing behavior data stored on the server.

[1272] Step 2:

[1273] The server analyzes the collected purchasing behavior data. Using an AI model (using PyTorch and TensorFlow), it extracts purchasing behavior patterns for each customer. These patterns include factors that customers consider important when choosing a product (price, reviews, images, etc.). The input for the data analysis is the collected purchasing behavior data, and the output is the purchasing behavior pattern.

[1274] Step 3:

[1275] The server determines the optimal order of search results and the information structure of product detail pages for each customer based on the extracted purchasing behavior patterns. Specific operations include sorting products by highest review rating and displaying many product photos. The input for personalization is purchasing behavior patterns, and the output is an optimized order of search results and the information structure of product detail pages.

[1276] Step 4:

[1277] The device (smartphone) displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a user searches for "smartphone," smartphones with the highest review ratings are displayed, and multiple images and reviews are highlighted on each product detail page. The input for UIUX auto-generation is the optimized sort order of search results and the information structure of the product detail page, and the output is a customized UIUX displayed on the smartphone.

[1278] Step 5:

[1279] The server continuously collects new purchasing behavior data from users and updates their customer profiles. Based on the updated customer profile data, prompts are input into the generative AI model to further optimize the analysis results of purchasing behavior patterns. An example of a specific prompt might be, "Generate the optimal product search result sort order and product detail page information structure based on User B's purchasing behavior data from the past six months. User B tends to check many images and place importance on reviews." The input for feedback and improvement is new purchasing behavior data, and the output is an optimized UI / UX based on the latest analysis results.

[1280] 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.

[1281] This invention is a system that combines customer purchasing behavior data and an emotion engine to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[1282] composition

[1283] The system includes the following main functions:

[1284] 1. Data Collection

[1285] The server collects data on users' past purchasing behavior, such as search history, browsing information on product detail pages, products added to carts, and purchase history.

[1286] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes their facial expressions and voice to identify their emotional state. This data is sent to a server.

[1287] 2. Data analysis

[1288] The server analyzes the purchasing behavior data collected and extracts purchasing behavior patterns for each user. It also analyzes the emotional data obtained from the emotion engine to identify what content and products the user will respond positively to.

[1289] 3. Personalization

[1290] The server generates a user profile based on the purchasing behavior patterns and emotional data, which includes the factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state.

[1291] The server determines the order of search results and the information structure of product detail pages based on the user profile.

[1292] 4. UIUX automatic generation

[1293] The device displays a UI / UX optimized for the user in real time based on the data received from the server. For example, if a user searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the user's emotions.

[1294] 5. Feedback and Improvement

[1295] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[1296] The new data is analyzed again and the UIUX provided for subsequent visits is optimized, ensuring that the user experience is always improved based on the latest data.

[1297] Specific examples

[1298] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[1299] 1. Data Collection

[1300] The server collects data on C's purchasing behavior over the past six months. For example, it records that C has browsed many fashion items and checked images of multiple products before purchasing.

[1301] The device's emotion engine analyzes Mr. C's facial expressions to determine his current emotional state, and this data is sent to the server.

[1302] 2. Data analysis

[1303] The server analyzes C's purchasing data and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[1304] 3. Personalization

[1305] The server creates a profile for C, and the next time C visits the e-commerce site, it automatically generates a product detail page that displays many images and emphasizes review information.The server also dynamically changes the content displayed based on emotional data, displaying prompts and messages that reduce stress.

[1306] 4. UIUX automatic generation

[1307] The device displays search results and product detail pages optimized for C based on her profile information. For example, if C searches for "dress," pages with many images and dresses with the highest reviews are displayed. Furthermore, the content displayed is dynamically adjusted according to C's emotional state.

[1308] 5. Feedback and Improvement

[1309] The server monitors Mr. C's new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information on his next visit.

[1310] Through this process, users can experience the optimal UI / UX tailored to their individual purchasing behavior and emotional state, which results in higher purchase rates on e-commerce sites and increased customer satisfaction.

[1311] The processing flow will be explained below.

[1312] Step 1:

[1313] A user accesses an EC site and logs in. This sends the user's ID to the server and identifies them.

[1314] Step 2:

[1315] The server collects data on users' past purchasing behavior from a database, including search history, browsing information on product detail pages, products added to carts, and purchase history.

[1316] Step 3:

[1317] The device's emotion engine analyzes the user's facial and voice data in real time to determine their emotional state. This information is collected, for example, using the user's webcam and microphone.

[1318] Step 4:

[1319] The server normalizes the purchasing behavior data and sentiment data collected, eliminating duplicates and incorrect data and converting it into a time-series data format.

[1320] Step 5:

[1321] The server analyzes the normalized data to extract purchasing patterns for each user, including using machine learning algorithms to identify specific behavioral trends (e.g., a tendency to value reviews or a preference for certain brands).

[1322] Step 6:

[1323] The server analyzes the emotional data to understand the emotional state the user is in when browsing or purchasing products, and can identify patterns such as a decrease in purchasing motivation when stress persists.

[1324] Step 7:

[1325] The server generates a user profile based on purchasing behavior patterns and emotional data, including factors that the user considers important when choosing a product (e.g., price, reviews, images, etc.).

[1326] Step 8:

[1327] The server determines the order of search results and the information structure of product detail pages based on the user profile. For example, it places products with high reviews at the top and sets up product detail pages to emphasize images and reviews.

[1328] Step 9:

[1329] The device displays optimized search results and product detail pages to the user based on the data received from the server. When a user searches for a product, a product list is displayed in the determined sort order, and important information is highlighted on the detail page.

[1330] Step 10:

[1331] The device dynamically changes the content displayed depending on the user's emotional state. For example, if the user is feeling stressed, it will display messages and images that have a relaxing effect, in order to increase the user's desire to purchase.

[1332] Step 11:

[1333] The user selects a product from the displayed product list, checks detailed information, decides to purchase, adds it to the cart, or completes the purchase.

[1334] Step 12:

[1335] The server collects new user purchasing behavior and sentiment data in real time and adds it to the existing database, thereby continuously updating the user's profile.

[1336] Step 13:

[1337] The server analyzes the data again and optimizes the UI / UX provided for subsequent visits, ensuring that the user experience is always improved based on the latest data.

[1338] By repeating the above steps, users can always experience the optimal UIUX tailored to their individual purchasing behavior and emotional state, improving the purchase rate on e-commerce sites.

[1339] Example 2

[1340] 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."

[1341] Conventional e-commerce site systems offered recommendation functions based on customer purchasing behavior data, but they did not optimize the user interface and user experience based on the customer's emotional state. As a result, they ignored the impact of customer emotions on purchasing intent, making it difficult to maximize purchase rates. In addition, customer profiles were static and not updated in real time, making it difficult to respond quickly to changes in customer interests.

[1342] 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.

[1343] In this invention, the server

[1344] A means of collecting data on customers' past purchasing behavior;

[1345] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[1346] A means for collecting customer emotional data in real time and analyzing their emotional state;

[1347] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior patterns and analyzed emotion data;

[1348] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[1349] This allows for the provision of an optimal user interface and user experience based on the customer's purchasing behavior and emotional state.

[1350] "Customer past purchasing behavior data" refers to data related to a customer's past purchases, searches, browsing, products added to carts, and other actions.

[1351] "Purchasing behavior patterns" are the results of analyzing customer purchasing behavior data and extracting specific behavioral characteristics and tendencies exhibited by customers.

[1352] "Emotion data" is data that represents the customer's current emotional state by analyzing the customer's facial expressions, voice, etc.

[1353] The "order of search results" refers to the order in which search results for products are displayed to customers.

[1354] The "information configuration of the product detail page" refers to the layout and content of the information displayed when a customer views the product detail page.

[1355] "User interface" is a general term for the operation screens and display elements that customers encounter when using an e-commerce site.

[1356] "User experience" refers to the overall experience and satisfaction that customers feel while using an e-commerce site.

[1357] A "profile" is a collection of information about an individual customer that is generated based on the customer's purchasing behavior patterns and emotional data.

[1358] This invention is a system that combines customer purchasing behavior data and emotional data to automatically generate the optimal user interface and user experience (UIUX). This makes it possible to maximize the purchase rate of e-commerce sites. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between servers, terminals, and users.

[1359] Components

[1360] server

[1361] The server uses the following hardware and software:

[1362] Data collection: The server can use cloud storage to collect purchasing behavior data, for example, by using the database service of Amazon Web Services (AWS).

[1363] Data analysis: The server can use a data analysis platform to analyze the collected data, for example, AWS Glue to clean, consolidate, and analyze the data.

[1364] Personalization: The server can use a recommendation engine to personalize the user interface, specifically AWS Personalize.

[1365] Feedback: The server can use data monitoring tools to collect new data and update customer profiles in real time.

[1366] Terminal

[1367] The terminal uses the following hardware and software:

[1368] Emotion engine: The device can use the camera and facial expression analysis software to perform emotion analysis, for example, using the Google Cloud Vision API.

[1369] User interface: The device can use a front-end framework to dynamically generate the user interface, for example using ReactJS.

[1370] Specific examples

[1371] Let's say the user is a customer named "Mr. C." When purchasing fashion items, Mr. C tends to check many reviews and frequently look at product images. Furthermore, Mr. C's motivation to purchase decreases when he feels stressed. Below we will show how this system optimizes Mr. C's purchasing experience.

[1372] 1. Data Collection

[1373] The server retrieves data on C's purchasing behavior over the past six months from the AWS database. For example, C browsed many fashion items and checked images of multiple products before purchasing.

[1374] The device's emotion engine analyzes Mr. C's facial expressions using the Google Cloud Vision API to determine his current emotional state, and this data is sent to a server in real time.

[1375] 2. Data analysis

[1376] The server analyzes C's purchasing data using AWS Glue and determines that C places importance on images and tends to check reviews. It also determines from the emotional data that C's purchasing motivation decreases when he is stressed.

[1377] 3. Personalization

[1378] The server uses AWS Personalize to create a profile of C based on his purchasing behavior patterns and emotional data. The server then determines the order of search results and the information structure of the product detail page based on this profile.

[1379] 4. UIUX automatic generation

[1380] The device uses ReactJS to display optimized search results and product detail pages in real time based on C's profile. For example, if C searches for "dress," dresses with many images and the highest reviews are displayed. Furthermore, if C is feeling stressed, a message encouraging her to relax is displayed.

[1381] 5. Feedback and Improvement

[1382] The server collects new purchasing behavior and emotional data about Mr. C in real time and updates his profile, enabling even more accurate personalization on his next visit.

[1383] Example of input to a generative AI model

[1384] By inputting the following prompts into the generative AI model, the AI ​​can explain the specific method for generating optimal UIUX based on user purchasing behavior and emotional data.

[1385] Example prompt:

[1386] Describe a system that generates the optimal user interface and experience in real time based on a user's past purchasing behavior data and current emotional state when shopping online on a website. Specifically, please describe in detail each step of data collection, data analysis, personalization, automated UI / UX generation, and feedback and improvement.

[1387] Using this prompt, the generative AI model can generate sentences that explain the detailed operation of the system and its benefits.

[1388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1389] Step 1:

[1390] Data collection

[1391] The server collects data on users' past purchasing behavior.

[1392] Input: Data such as user search history, product detail page visits, items added to cart, and purchase history.

[1393] Data processing: Store the collected data in an AWS database and perform data cleaning as needed.

[1394] Output: Purchasing behavior data stored in a database.

[1395] The terminal uses an emotion engine to recognize the user's emotions.

[1396] Input: Image and video data captured by a camera of the user's face.

[1397] Data processing: Facial expressions are analyzed using Google Cloud Vision API to identify emotional states.

[1398] Output: Emotion data (e.g., happy, stressed, excited).

[1399] Step 2:

[1400] Data analysis

[1401] The server analyzes the collected purchasing behavior data and sentiment data.

[1402] Input: Collected purchasing behavior and sentiment data.

[1403] Data processing:

[1404] Use AWS Glue to integrate data and extract purchasing behavior patterns.

[1405] Analyze sentiment data to identify what content and products users respond to positively.

[1406] Output: Analysis results of purchasing behavior patterns and sentiment data for each user.

[1407] Step 3:

[1408] Personalization

[1409] The server personalizes the user interface.

[1410] Input: Analyzed buying behavior patterns and sentiment data.

[1411] Data processing:

[1412] Use AWS Personalize to generate user profiles.

[1413] The order of search results and the information structure of product detail pages are determined based on the user profile.

[1414] Output: Personalized user profile and UI configuration data.

[1415] Step 4:

[1416] UIUX automatic generation

[1417] The device displays an optimized UIUX in real time.

[1418] Input: Personalized user profile and UI configuration data.

[1419] Data processing:

[1420] Use ReactJS to generate a dynamic UI based on user profile.

[1421] The content displayed is based on the order of search results and the information structure of the product details page.

[1422] Output: Customer-optimized search results and product detail pages.

[1423] Step 5:

[1424] Feedback and Improvements

[1425] The server collects new purchasing behavior and sentiment data of the user and updates the profile.

[1426] Input: New user purchasing behavior and sentiment data.

[1427] Data processing:

[1428] New data is collected in real time and added to the database.

[1429] Update your existing profile and optimize the UI / UX you provide on subsequent visits.

[1430] Output: Updated user profile and optimized UIUX.

[1431] (Application example 2)

[1432] 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."

[1433] On conventional e-commerce sites, personalization was based solely on data on customers' past purchasing behavior, which meant that the purchasing experience was not optimized enough to take into account the emotional state of each individual customer. Furthermore, because it was not possible to dynamically adjust the displayed content according to the customer's emotional state, there was a lack of an effective approach to increasing purchasing motivation. This made it difficult to improve customer satisfaction and maximize purchase rates.

[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past purchasing behavior data, means for analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer, means for recognizing and acquiring customer emotion data, means for determining the optimal order of search results and the information configuration of the product detail page for the customer based on the extracted purchasing behavior pattern and emotion data, means for automatically generating the optimal user interface and user experience for the customer using the determined order of search results and the information configuration of the product detail page, and means for providing dynamic display content according to the customer's emotional state. This makes it possible to provide a personalized purchasing experience according to the customer's emotional state, maximizing purchasing motivation and improving customer satisfaction.

[1435] "Past purchasing behavior data" refers to a series of data related to a customer's purchasing activities, such as product searches, viewing of product detail pages, adding to carts, and purchase history.

[1436] "Purchasing behavior patterns" are data that are analyzed based on collected purchasing behavior data and show consistent trends and preferences when customers select and purchase products.

[1437] "Emotion data" is data that indicates the psychological state and emotional state of a customer, obtained by analyzing the customer's facial expressions and voice.

[1438] "Search result sorting" refers to the order in which the results list is displayed when a customer searches for a product, and is data determined based on specific criteria.

[1439] "Information configuration on product details page" refers to the layout, order, and content of the various information displayed on the product details page, and is a configuration optimized according to the customer's preferences and emotions.

[1440] "User interface" refers to the parts that customers directly touch when interacting with the system, such as the screen design and operation method.

[1441] "User experience" refers to the overall experience and satisfaction that customers feel when using a system, and is a concept related to the ease of use and comfort of the entire system.

[1442] "Dynamic content" refers to content and messages that change in real time depending on the customer's current emotional state.

[1443] The present invention is a system that automatically generates optimal user interfaces and user experiences by combining customer purchasing behavior data and emotional data. This system is realized by collecting, analyzing, personalizing, displaying, and providing feedback on data between a server, terminals, and users.

[1444] Hardware and software used

[1445] Server: Database (MySQL), analytical AI (TensorFlow, Keras)

[1446] Device: Smartphone (iOS, Android)

[1447] Emotion recognition engine: OpenCV, Facial Emotion Recognition (FER)

[1448] Data collection

[1449] The server collects data on the customer's past purchasing behavior, including search history, browsing information on product detail pages, items added to carts, and purchase history. The device uses an emotion recognition engine to analyze the customer's facial expressions and voice to identify their emotional state. This data is sent to the server in real time.

[1450] Data analysis

[1451] The server analyzes the collected purchasing behavior data to extract each customer's purchasing behavior patterns. It also analyzes the emotional data obtained from the emotion engine to identify what content and products customers respond positively to.

[1452] Personalization

[1453] The server generates a customer profile based on purchasing behavior patterns and emotional data. This profile includes the factors that customers consider important when choosing a product (e.g., price, reviews, images, etc.) and their emotional state. The server determines the order of search results and the information structure of product detail pages based on the user profile.

[1454] UIUX automatic generation

[1455] The device displays a UI / UX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and multiple images and reviews are highlighted on each product detail page. The display content also changes dynamically depending on the customer's emotions.

[1456] Feedback and Improvements

[1457] The server collects new customer purchasing behavior and sentiment data in real time and adds it to the existing database. This continuously updates the customer profile. The new data is analyzed again to optimize the UI / UX provided for subsequent visits. This ensures that the customer experience is always improved based on the latest data.

[1458] Specific examples

[1459] For example, let's say a customer is "Mr. A," who places importance on product reviews and tends to be sensitive to sale information. Furthermore, Mr. A's motivation to purchase tends to decrease when he is stressed. The system optimizes Mr. A's purchasing experience by following the steps below.

[1460] 1. Data collection: The server collects data on A's purchasing behavior over the past six months. For example, it records that A checks many reviews before deciding to purchase. The device's emotion recognition engine analyzes A's facial expressions and identifies his / her current emotional state. This data is sent to the server.

[1461] 2. Data analysis: The server analyzes A's purchasing data and determines that A is review-oriented and sensitive to sales information. It also determines from the emotional data that A's purchasing motivation decreases when he is stressed.

[1462] 3. Personalization: The server creates a profile for Mr. A and automatically generates a product detail page that highlights reviews and sales information the next time he visits the e-commerce site. It also dynamically changes the content displayed based on his emotional data, displaying prompts and messages that reduce stress.

[1463] 4. Automatic UI / UX generation: The device will display search results and product detail pages optimized for Person A based on their profile information. For example, if Person A searches for "smartphone," pages with many images and smartphones with the highest reviews will be displayed. Furthermore, the displayed content will be dynamically adjusted according to Person A's emotional state.

[1464] 5. Feedback and Improvement: The server monitors Mr. A’s new purchasing behavior and emotional data and updates his profile, further optimizing the UI / UX based on the latest information during his next visit.

[1465] Example prompt for a generative AI model:

[1466] "User A is review-focused, so if you detect a stressful situation, please display a message that will help them relax."

[1467] The above system provides each customer with an optimized purchasing experience, maximizing purchasing motivation and improving customer satisfaction.

[1468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1469] Step 1:

[1470] The server collects data on customers' past purchasing behavior. Specifically, it collects search history, product detail page browsing information, items added to carts, and purchase history. This data is stored in a database (MySQL) based on the customer's past purchasing behavior. The input is purchasing behavior data, and the output is a structured record.

[1471] Step 2:

[1472] The device uses an emotion recognition engine (OpenCV, Facial Emotion Recognition) to analyze the customer's facial expressions and voice to collect emotional data. It uses the smartphone's camera and microphone to identify the customer's current emotional state and transmits this data to the server in real time. The input is facial expression and voice data, and the output is structured emotional data.

[1473] Step 3:

[1474] The server analyzes the collected purchasing behavior data and emotion data. It processes the data using analytical AI (TensorFlow, Keras) and extracts purchasing behavior and emotion patterns for each customer. The input is purchasing behavior data and emotion data, and the output is purchasing behavior patterns and emotion patterns.

[1475] Step 4:

[1476] The server generates a customer profile based on purchasing behavior and emotional patterns, including factors that customers consider important when choosing a product (price, reviews, images, etc.) and their emotional state. The input is purchasing behavior and emotional patterns, and the output is the customer profile.

[1477] Step 5:

[1478] The server determines the order of search results and the information structure of product detail pages based on the customer profile. AI is used to rank search results and optimize information display according to the customer's emotional state. The input is the customer profile, and the output is the optimized order of search results and the information structure of product detail pages.

[1479] Step 6:

[1480] The device displays a UIUX optimized for the customer in real time based on the data received from the server. For example, when a customer searches for "smartphone," smartphones with the highest reviews are displayed, and each product detail page highlights multiple images and reviews. The display content also changes dynamically depending on the customer's emotions. The input is the optimized order and information structure of search results, and the output is the UI display content.

[1481] Step 7:

[1482] The server monitors new customer purchasing behavior and emotional data and adds it to the existing database. This continuously updates the customer profile. The AI ​​performs further analysis based on the new data and optimizes the UI / UX provided for subsequent visits. The input is new purchasing behavior and emotional data, and the output is an updated customer profile.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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.

[1488] 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.

[1489] 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).

[1490] 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.

[1491] 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."

[1492] 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.

[1493] 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).

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] The following is further disclosed regarding the above embodiment.

[1505] (Claim 1)

[1506] A means of collecting data on customers' past purchasing behavior;

[1507] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[1508] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior pattern;

[1509] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[1510] A system including:

[1511] (Claim 2)

[1512] further including means for collecting new customer purchasing behavior data and continuously updating the customer profile;

[1513] 10. The system of claim 1.

[1514] (Claim 3)

[1515] The system further includes a means for dynamically adjusting the display order of each product based on the purchasing behavior pattern of each customer.

[1516] 10. The system of claim 1.

[1517] "Example 1"

[1518] (Claim 1)

[1519] A means of collecting data on customers' past purchasing behavior;

[1520] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[1521] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior pattern;

[1522] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[1523] means for transmitting data to the terminal in real time;

[1524] means for the terminal to display an optimized user interface and user experience;

[1525] A system including:

[1526] (Claim 2)

[1527] 10. The system of claim 1, further comprising means for collecting new customer purchasing behavior data and continually updating the customer profile.

[1528] (Claim 3)

[1529] 10. The system according to claim 1, further comprising means for dynamically adjusting the display ranking of each product based on the purchasing behavior pattern of each customer.

[1530] "Application Example 1"

[1531] Rewritten claims

[1532] (Claim 1)

[1533] A means of collecting data on customers' past purchasing behavior;

[1534] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[1535] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior pattern;

[1536] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[1537] a means for collecting new purchasing behavior data of the customer and updating the customer profile based on the purchasing behavior data;

[1538] Based on the updated customer profile data, prompt sentences are input into the generative AI model to further optimize the analysis results of purchasing behavior patterns.

[1539] a means for providing an optimized user interface and user experience in real time;

[1540] A system including:

[1541] (Claim 2)

[1542] further including means for collecting new customer purchasing behavior data and continuously updating the customer profile;

[1543] 10. The system of claim 1.

[1544] (Claim 3)

[1545] The system further includes a means for dynamically adjusting the display order of each product based on the purchasing behavior pattern of each customer.

[1546] 10. The system of claim 1.

[1547] "Example 2: Combining Emotion Engines"

[1548] (Claim 1)

[1549] A means of collecting data on customers' past purchasing behavior;

[1550] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[1551] A means for collecting customer emotional data in real time and analyzing their emotional state;

[1552] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior patterns and analyzed emotion data;

[1553] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[1554] A system including:

[1555] (Claim 2)

[1556] further comprising means for collecting new customer purchasing behavior data and sentiment data and continuously updating the customer profile;

[1557] 10. The system of claim 1.

[1558] (Claim 3)

[1559] The system further includes a means for dynamically adjusting the display ranking of each product based on the purchasing behavior pattern and emotion data of each customer.

[1560] 10. The system of claim 1.

[1561] "Application example 2 when combining emotion engines"

[1562] (Claim 1)

[1563] A means of collecting data on customers' past purchasing behavior;

[1564] A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer;

[1565] a means for recognizing and capturing customer sentiment data;

[1566] A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior patterns and emotion data;

[1567] A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page;

[1568] means for providing dynamic display content according to the emotional state of the customer;

[1569] A system including:

[1570] (Claim 2)

[1571] further comprising means for collecting new customer purchasing behavior data and sentiment data and continuously updating the customer profile;

[1572] 10. The system of claim 1.

[1573] (Claim 3)

[1574] The system further includes a means for dynamically adjusting the display ranking of each product based on the purchasing behavior pattern and emotion data of each customer.

[1575] 10. The system of claim 1. [Explanation of symbols]

[1576] 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. A means of collecting data on customers' past purchasing behavior; A means of analyzing the collected purchasing behavior data and extracting purchasing behavior patterns for each customer; A means for determining the optimal order of search results and information configuration of product detail pages for a customer based on the extracted purchasing behavior pattern; A means for automatically generating an optimal user interface and user experience for a customer using the determined sort order of search results and information configuration of a product detail page; A system including:

2. further including means for collecting new customer purchasing behavior data and continuously updating the customer profile; The system of claim 1 .

3. The system further includes a means for dynamically adjusting the display order of each product based on the purchasing behavior pattern of each customer. The system of claim 1 .

Images