System

Abstract

A system is provided.SOLUTION: A system includes a means for collecting purchase behavior data of a customer, a means for analyzing the collected purchase behavior data, a means for automatically generating an optimal user interface and user experience to the customer on the basis of an analysis result, and a means for providing the optimal user interface and user experience to the customer.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] In recent years, customer purchasing behavior and preferences have become increasingly diverse on e-commerce sites, making it difficult to provide a user interface (UI) and user experience (UX) that is suitable for all customers. This has led to the problem that customers are unable to access the information they are looking for quickly and accurately, resulting in a decline in purchase rates. [Means for solving the problem]

[0005] The present invention provides a system that collects and analyzes customer purchasing behavior data to automatically generate a UI and UX optimized for each customer. This system includes means for optimizing the display order of search results based on the customer's profile, customizing the information structure of product detail pages, and displaying related recommended products. Furthermore, by using a machine learning model to generate and continuously update customer profiles, it is possible to always provide the most suitable shopping experience for each customer.

[0006] "Customer purchasing behavior data" refers to data that records the behavior of customers on e-commerce sites, such as search keywords, browsing history, cart addition data, and browsing time.

[0007] "Analysis" refers to the process of analyzing collected purchasing behavior data to identify customer preferences and behavior patterns.

[0008] "User interface (UI)" is a term that refers to the overall design of the screens and controls that customers use to interact with an e-commerce site.

[0009] "User experience (UX)" is a concept that describes the overall experience and satisfaction that customers have when using an e-commerce site.

[0010] "Automatic generation" is a process in which the system uses machine learning technology and algorithms to generate and deliver the optimal UI and UX for each customer.

[0011] "Display order of search results" refers to the order in which the system displays product lists for keywords searched by customers.

[0012] A "product detail page" is a web page that displays detailed information about a particular product.

[0013] "Information organization" refers to the structure and layout for arranging, displaying, and highlighting information within a web page.

[0014] "Recommended Information" refers to related products, accessories, and other value-added information presented to customers.

[0015] A "machine learning model" is an algorithm that learns patterns and rules from large amounts of data and makes predictions and classifications based on that knowledge.

[0016] A "profile" is a collection of customer preferences and behavioral patterns presented as a single data set. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that collects and analyzes customer purchasing behavior data on e-commerce sites, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language, along with specific examples.

[0039] Data collection

[0040] When a user accesses an e-commerce site, the server automatically collects the following data: visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[0041] Data analysis

[0042] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models to analyze customer behavior patterns and preferences, identifying interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0043] Optimizing search results

[0044] When a user searches for a product on an e-commerce site, the server refers to a pre-created customer profile to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[0045] Customizing your product detail page

[0046] When a user visits a particular product detail page, the server customizes the information structure of that page. For example, if a user prefers high-resolution images, the image gallery might be displayed first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the review section might be brought to the forefront and detailed reviews might be displayed.

[0047] Viewing recommendations

[0048] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[0049] Continuous learning and optimization

[0050] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[0051] Specific examples

[0052] Example 1: Searching for and purchasing a smartphone

[0053] 1. A user searches for "smartphone."

[0054] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[0055] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0056] 4. User clicks on a specific phone to view details.

[0057] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0058] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0059] Example 2: Purchasing a fashion item

[0060] 1. A user searches for "summer dresses."

[0061] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[0062] 3. Casual and affordable dresses will appear at the top of the search results page.

[0063] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0064] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[0065] The above is an embodiment of the present invention. This system provides a UI and UX that are optimized for each customer, and is expected to improve purchase rates.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] A user accesses an e-commerce site and enters search keywords.

[0069] Step 2:

[0070] The server automatically collects and logs users' search keywords and access information (such as visit time, IP address, and referring URL).

[0071] Step 3:

[0072] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from the database.

[0073] Step 4:

[0074] The server analyzes the collected data in real time and identifies user preferences and behavioral patterns based on machine learning models.

[0075] Step 5:

[0076] The server uses the customer profile generated from the analysis results to optimize the search results, specifically sorting products that are likely to interest the user to the top.

[0077] Step 6:

[0078] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[0079] Step 7:

[0080] When a user clicks to view a particular product detail page, the server customizes the information on that page, for example, changing the image gallery, review section, or product specifications.

[0081] Step 8:

[0082] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[0083] Step 9:

[0084] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[0085] Step 10:

[0086] When a user adds an item to their cart, the server records that information and updates the customer profile.

[0087] Step 11:

[0088] The server periodically retrains the machine learning model based on new purchasing behavior data to improve the accuracy of the profile.

[0089] These are the specific processing steps for a system that provides an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[0090] Example 1

[0091] 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."

[0092] Conventional e-commerce sites face the challenge of being unable to provide a personalized user interface (UI) or user experience (UX) based on each individual customer's purchasing behavior and preferences. Furthermore, because continuous optimization through real-time data processing and retraining of machine learning models is not performed, they are unable to quickly respond to changes in customer interests and purchasing trends. A system that can solve these problems and increase customer purchase rates is needed.

[0093] 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.

[0094] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, means for using a machine learning model to analyze customer behavior patterns and preferences, means for processing data in real time, and means for generating a profile for each customer and storing it in a database. This makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[0095] "Customer purchasing behavior data" refers to information about a customer's behavior on a website, such as the time of visit, IP address, referring URL, search keywords, ID of the viewed product, viewing time, and cart addition information.

[0096] "Analysis means" refers to the technical means for processing collected customer purchasing behavior data and identifying customer behavior patterns and preferences.

[0097] "User interface" refers to the interactive elements that customers directly touch and manipulate when searching, browsing, and purchasing products through a website.

[0098] "User experience" refers to the overall experience and feeling a customer has when using a website, including the site's structure, design, usability, and the quality of the information provided.

[0099] A "machine learning model" is an algorithm or technology that learns from collected data and enables future predictions and classifications.

[0100] A "profile" is a collection of data that includes each customer's preferences and behavioral patterns, created based on the results of analysis.

[0101] A "database" is a system that stores and manages data based on a certain structure, enabling efficient searching and updating.

[0102] "Optimization" refers to maximizing the efficiency of what is provided to customers based on collected data and analysis results, and providing the most appropriate information and context for each individual customer.

[0103] "Processing data in real time" refers to a series of processes in which collected data is analyzed immediately and the results are reflected immediately.

[0104] "Recommended information" is information that presents highly relevant products and services based on a customer's current browsing and purchasing behavior.

[0105] "Retraining" is the process of retraining an existing machine learning model using new data to improve the model's accuracy and effectiveness.

[0106] The present invention is a system that collects and analyzes customer purchasing behavior data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Specific embodiments of the system are described below.

[0107] Data collection

[0108] When a user visits an e-commerce site, the server automatically collects the following data: time of visit, IP address, referring URL, search keywords, viewed product ID, viewing time, add-to-cart information, etc. This information is collected using web server software such as Apache or Nginx.

[0109] Data analysis

[0110] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences and identify interests and purchasing trends. The analysis results are stored in a relational database (e.g., MySQL or PostgreSQL) as a profile for each customer.

[0111] Optimizing search results

[0112] When a user searches for a product on an e-commerce site, the server refers to the user profile created in advance to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[0113] Customizing your product detail page

[0114] When a user visits a particular product detail page, the server customizes the page's information structure based on the user's preferences. For example, if a user prefers high-resolution images, the server might display an image gallery first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the server might bring the review section to the forefront and display detailed reviews.

[0115] Viewing recommendations

[0116] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[0117] Continuous learning and optimization

[0118] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[0119] Specific examples

[0120] Example 1: Searching for and purchasing a smartphone

[0121] 1. A user searches for "smartphone."

[0122] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[0123] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0124] 4. User clicks on a specific phone to view details.

[0125] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0126] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0127] Example 2: Purchasing a fashion item

[0128] 1. A user searches for "summer dresses."

[0129] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[0130] 3. Casual and affordable dresses will appear at the top of the search results page.

[0131] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0132] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[0133] This system can stimulate individual users' purchasing desire and increase the value of the EC site, which is expected to lead to increased sales and customer satisfaction.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1:

[0136] A user accesses an e-commerce site.

[0137] Input: The user enters the URL of the e-commerce site using a browser.

[0138] Action: The server receives an access request.

[0139] Output: The server prepares to record the user's visit information.

[0140] Step 2:

[0141] The server collects user visit information.

[0142] Input: Access request and associated metadata (e.g., time of visit, IP address, referring URL, etc.).

[0143] How it works: The server uses web server software such as Apache or Nginx to record visit times, IP addresses, referring URLs, search keywords, viewed product IDs, viewed times, add-to-cart information, etc.

[0144] Output: The collected visit information is stored in a database.

[0145] Step 3:

[0146] The data collected by the server is analyzed using machine learning models.

[0147] Input: User purchasing behavior data collected in a database.

[0148] How it works: The server sends data to a machine learning model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences.

[0149] Output: The analysis results are generated and stored in a database as a profile for each customer.

[0150] Step 4:

[0151] The user searches for a product.

[0152] Input: A user enters a product name or keyword into the search box of an e-commerce site.

[0153] Operation: A server receives a search query.

[0154] Output: The search query is prepared for analysis.

[0155] Step 5:

[0156] The server optimizes search results based on user profiles.

[0157] Input: Search query and user profile.

[0158] How it works: The server looks up your profile and sorts the search results to bring the most relevant products to the top.

[0159] Output: The optimized search results are displayed in the user's browser.

[0160] Step 6:

[0161] A user visits a specific product detail page.

[0162] Input: User clicks on a specific product from the search results.

[0163] What happens: The server retrieves the product details and renders the page.

[0164] Output: Detail page information is prepared.

[0165] Step 7:

[0166] The server customizes the product detail page based on the user's preferences.

[0167] Input: User profile and product details.

[0168] How it works: The server dynamically changes the layout and content of the page based on user preferences, highlighting high-resolution image galleries for image-focused users and highlighting reviews for review-focused users.

[0169] Output: A customized product detail page is displayed to the user.

[0170] Step 8:

[0171] The server displays related information about the product being viewed.

[0172] Input: Viewed product information and user profile.

[0173] How it works: The server collects information about related products and displays them on the page you are viewing. For example, on a smartphone detail page, it might recommend cases and screen protectors specifically for that model.

[0174] Output: Related product information is displayed to the user.

[0175] Step 9:

[0176] The server retrains the machine learning model with the new behavioral data.

[0177] Input: New purchasing behavior data.

[0178] How it works: The server retrains the machine learning model with newly collected data, improving the model's accuracy.

[0179] Output: Updated customer profile and optimization algorithm.

[0180] Through these steps, the present invention makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[0181] (Application example 1)

[0182] 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."

[0183] In online shopping, the challenge is to improve customer satisfaction by efficiently collecting customer behavior data and providing individually optimized user interfaces (UIs) and user experiences (UXs) based on that data. Furthermore, there is a need to increase purchasing motivation by analyzing customer interests and purchasing trends in real time and providing personalized recommendations.

[0184] 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.

[0185] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, and means for automatically generating an optimal user interface and user experience for the customer based on the analysis results. This makes it possible to analyze each customer's behavior data in real time using machine learning and provide a personalized experience in conjunction with an application installed on the smart device. In addition, by optimizing the display order of search results and displaying individually optimized product detail pages and related recommended information, it is possible to simultaneously improve customer satisfaction and purchasing motivation.

[0186] "Customer purchasing behavior data" refers to data that indicates the actions that customers take on an e-commerce site, such as browsing, searching, adding to cart, and purchasing.

[0187] "Means of collection" refers to the functions of systems and software that record and store customer behavior data when accessing an e-commerce site.

[0188] "Means of analysis" refers to machine learning models and algorithms used to analyze collected customer purchasing behavior data in real time and identify customer interests and preferences.

[0189] "User interface (UI)" refers to the screen layout and operation methods that customers see when using an e-commerce site or app.

[0190] "User experience (UX)" refers to the overall sense of use and satisfaction that customers feel in the process of using an e-commerce site or app.

[0191] "Optimization measures" refers to the function of adjusting search results and page display order based on data for each customer, and presenting the most appropriate content.

[0192] "Search result display order" refers to the order in which products are displayed when a customer searches for a product using keywords.

[0193] A "product detail page" refers to a web page or app screen that contains detailed information about a specific product.

[0194] "Information structure" refers to the layout and display format of information such as images, reviews, specifications, and recommended information on product detail pages.

[0195] "Applications installed on smart devices" refers to software programs installed on mobile devices such as smartphones and tablets.

[0196] "Analyzing behavioral data in real time using machine learning" refers to the process of collecting various operations performed by customers on a website or app in real time and instantly analyzing them using a machine learning model.

[0197] "Means of linking" refers to a mechanism by which applications on smart devices automatically generate and provide optimal UI and UX based on the analysis results.

[0198] "Recommended information" refers to information that suggests related products and services based on the products a customer is viewing and their past behavioral patterns.

[0199] "Continuous learning" refers to the process of retraining machine learning models based on newly collected data to improve analysis accuracy.

[0200] This invention is a system that collects and analyzes purchasing behavior data on e-commerce sites and provides customers with an optimized user interface and user experience through an application installed on a smart device. An embodiment of this system will be described in detail.

[0201] Hardware and software used

[0202] Hardware: Smartphone (iOS, Android), server

[0203] Software: Python, TensorFlow / Keras (machine learning libraries), Firebase (data collection and management)

[0204] Data collection

[0205] Customer purchasing behavior data for e-commerce sites is automatically collected in real time via Firebase, including visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[0206] Data analysis

[0207] The collected data is analyzed on the server. Machine learning models are run using Python and TensorFlow / Keras to analyze each customer's behavioral patterns and preferences. The analysis results identify the customer's interests and purchasing trends and are stored as a profile in Firebase. For example, a customer identified as being interested in "beachwear" will be prioritized in the display of products in that category.

[0208] Generate optimized search results and product detail pages

[0209] When a customer searches for a product, the server optimizes the order of search results based on the profile it creates. When the user visits a product detail page, the information on that page is also customized based on the profile, displaying information tailored to the customer's preferences, such as high-resolution images or expert reviews.

[0210] Viewing recommendations

[0211] In addition, the server recommends items related to the product being viewed. For example, if you are viewing a smartphone, cases and screen protectors for that model will be displayed, encouraging customers to make a purchase.

[0212] Continuous learning and optimization

[0213] The system continuously learns to deliver a more personalized experience. Every time a user interacts with a site or application, new behavioral data is collected and the machine learning model is retrained, ensuring customer profiles are always up-to-date and enabling further optimization.

[0214] Specific examples

[0215] Example 1: Searching for and purchasing a smartphone

[0216] When a user searches for "smartphone," the server determines from their browsing history that they are interested in the latest, high-performance smartphones. The search results page will display new products and highly rated smartphones at the top of the results. When a user visits the detail page for a specific smartphone, high-resolution images are prioritized and expert reviews are highlighted. Related accessories are also recommended.

[0217] Prompt Sentence Examples

[0218] When a user searches for "summer clothes":

[0219] "When a user searches for summer clothes, what data in particular do you collect and how do you analyze it?"

[0220] "Write a prompt recommending appropriate items for users interested in beachwear."

[0221] In this way, the system of the present invention provides users with an optimized UI and UX, increasing customer satisfaction.

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] When a user accesses an e-commerce site, the device collects purchasing behavior data such as visit time, IP address, referral URL, search keywords, viewed product ID, viewing time, and cart addition information. This data is sent to Firebase in real time. The input is user behavior data, and the output is the collected data stored in Firebase.

[0225] Step 2:

[0226] The server analyzes the purchasing behavior data stored in Firebase. It applies machine learning models using Python and TensorFlow / Keras to analyze customer behavior patterns and preferences. The machine learning models process the data using neural networks and save it as a customer profile. The input is the collected user data, and the output is the analysis results generated as a customer profile.

[0227] Step 3:

[0228] When a user searches for a product on an e-commerce site, the server references the customer profile in Firebase to optimize the search results. The input is the user's search keywords and customer profile, and the output is optimized search results that are displayed to the user. The server calculates the ranking of related products and adjusts the display order.

[0229] Step 4:

[0230] When a user visits a particular product detail page, the server customizes the information structure of that page. First, the server prioritizes displaying information tailored to the customer's interests, such as high-resolution images and a review section. The input is the customer profile and product detail page data, and the output is a customized page displayed on the user's device.

[0231] Step 5:

[0232] The server displays recommendations related to the specific product the user is viewing, for example, accessories specific to that model while browsing a smartphone. The input is the currently viewed product information and a customer profile, and the output is generated and presented to the user with recommendations for related products and accessories.

[0233] Step 6:

[0234] Every time a user interacts with the e-commerce site, the server collects new behavioral data and retrains the machine learning model, ensuring that the customer profile is always up to date. The input is the user's new behavioral data, and the output is an updated machine learning model and customer profile. This step allows for further optimization.

[0235] 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.

[0236] This invention is a system that collects and analyzes customer purchasing behavior and emotion data on e-commerce sites to automatically generate and provide a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language and provide specific examples.

[0237] Data collection and emotion recognition

[0238] When a user accesses an e-commerce site and enters a search keyword, the server automatically collects the following data: visit time, IP address, referring URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. The emotion engine analyzes this data and identifies emotional states such as joy, excitement, and confusion.

[0239] Data analysis and profile generation

[0240] The collected purchasing behavior and emotional data is analyzed in real time. The server uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0241] Optimizing search results

[0242] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[0243] Customizing your product detail page

[0244] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[0245] Viewing Recommendations

[0246] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[0247] Continuous learning and optimization

[0248] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[0249] Specific examples

[0250] Example 1: Searching for and purchasing a smartphone

[0251] 1. A user searches for "smartphone."

[0252] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[0253] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0254] 4. User clicks on a specific phone to view details.

[0255] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0256] 6. The emotion engine recognizes that the user is curious and displays more detailed technical information and related videos.

[0257] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0258] Example 2: Purchasing a fashion item

[0259] 1. A user searches for "summer dresses."

[0260] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[0261] 3. Casual and affordable dresses will appear at the top of the search results page.

[0262] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0263] 5. If the sentiment engine detects that the user is confused, it will highlight detailed product descriptions and reviews.

[0264] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[0265] The above is an embodiment of the present invention. This system provides a UI and UX optimized for each customer, which is expected to improve purchase rates. By combining it with an emotion engine, a more personalized experience can be provided that responds to the customer's momentary emotional state.

[0266] The processing flow will be explained below.

[0267] Step 1:

[0268] A user accesses an e-commerce site and enters search keywords.

[0269] Step 2:

[0270] The server automatically collects and logs access information such as the user's search keywords, visit time, IP address, and referring URL.

[0271] Step 3:

[0272] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from a database, and the emotion engine collects emotional data such as the user's facial expressions, voice, and operation speed through the device's camera, microphone, and sensors.

[0273] Step 4:

[0274] The server analyzes purchasing behavior data and emotional data in real time and uses machine learning models to identify user preferences, behavioral patterns, and emotional states.

[0275] Step 5:

[0276] The server generates optimal search results for users based on the customer profile and emotion data generated from the analysis results, specifically sorting products of interest to the top.

[0277] Step 6:

[0278] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[0279] Step 7:

[0280] When a user clicks to view a particular product detail page, the server customizes the information structure on that page, for example displaying an image gallery first if the user prefers high-resolution images, or highlighting expert reviews.

[0281] Step 8:

[0282] Based on the user's emotional state (e.g., confused) recognized by the emotion engine, the server highlights detailed product descriptions and usage instructions.

[0283] Step 9:

[0284] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[0285] Step 10:

[0286] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[0287] Step 11:

[0288] The emotion engine adjusts the type and timing of recommendations based on the user's emotional state. For example, if the user is excited, it will display related products at an earlier stage, with higher prices.

[0289] Step 12:

[0290] When a user adds an item to their cart, the server records that information and updates the customer profile.

[0291] Step 13:

[0292] The server periodically retrains the machine learning model with new purchasing behavior and sentiment data to improve the accuracy of the profiles.

[0293] These are the specific processing steps of a system that combines an emotion engine to provide an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[0294] Example 2

[0295] 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."

[0296] Conventional e-commerce sites typically attempt to optimize the user experience by using only customer purchasing behavior data. However, this makes it difficult to achieve detailed personalization based on the customer's emotional state, and further improvements in purchase rates cannot be expected. The purpose of this invention is to solve this problem and achieve even more accurate personalization by utilizing each customer's emotional data.

[0297] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting customer purchasing behavior data, means for collecting customer emotion data, means for analyzing the collected purchasing behavior data and emotion data, means for generating and updating a customer profile based on the analysis results, means for automatically generating an optimal user interface and user experience for the customer, and means for providing an optimal user interface and user experience for the customer. This enables personalization that takes into account the emotional state of the customer, making it possible to improve the purchase rate.

[0298] "Customer" refers to a user who uses an e-commerce site to search for, browse, and purchase products and services.

[0299] "Purchasing behavior data" refers to the behavioral history of customers on e-commerce sites, such as search keywords, viewed product IDs, viewing times, and cart addition information.

[0300] "Emotion data" is data that expresses the emotional state of the customer, obtained from facial expressions, voice, operation speed, etc.

[0301] "Analysis" is the process of identifying customer preferences, behavioral patterns, and emotional states based on collected data.

[0302] A "profile" is data that compiles information such as each customer's preferences, behavioral patterns, and emotional state.

[0303] A "user interface" refers to the screen layout and operational elements that customers interact with visually and operationally when using an e-commerce site.

[0304] "User experience" is a concept that refers to the overall satisfaction and usability that customers feel when using an e-commerce site.

[0305] "Optimization" is the process of adjusting search results, product detail pages, and even recommendations based on each customer's individual profile.

[0306] "Automatic generation" refers to the operation in which the system performs settings and output based on specific conditions and data without human intervention.

[0307] "Recommendations" are additional suggestions or information displayed related to the product or service a customer is viewing.

[0308] A "machine learning model" is a collection of algorithms used to predict or classify specific outcomes based on data.

[0309] MODE FOR CARRYING OUT THE INVENTION

[0310] This invention is a system that collects and analyzes customer purchasing behavior data and emotion data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. A specific embodiment of this system is described below.

[0311] Data collection and emotion recognition

[0312] A user accesses an e-commerce site and enters a search keyword. At this point, the server automatically collects purchasing behavior data, such as the visit time, IP address, referrer URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the server uses the device's built-in camera, microphone, and sensors to collect real-time emotional data, such as the user's facial expression, voice, and operation speed. This data is analyzed by an emotion engine to identify the user's emotional state, such as joy, excitement, or confusion.

[0313] Data analysis and profile generation

[0314] The collected purchasing behavior and emotional data is analyzed in real time by a server. The server uses machine learning models, such as generative AI models, to perform detailed analysis of customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0315] Optimizing search results

[0316] When a user searches for a product on an e-commerce site, the server compares pre-generated customer profiles with real-time emotional data to optimize search results. For example, if a user searches for "smartphone," the server will display the latest models and feature-rich smartphones at the top of the results based on past data and the user's current emotional state.

[0317] Customizing your product detail page

[0318] When a user visits a particular product detail page, the server customizes the information on that page. For example, if a user prefers high-resolution images, the product detail page might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, detailed product descriptions and usage instructions might be highlighted.

[0319] Viewing recommendations

[0320] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state.

[0321] Continuous learning and optimization

[0322] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model. This process continually updates customer profiles, providing an even more accurate and personalized experience.

[0323] Adding specific examples

[0324] Example 1: Searching for and purchasing a smartphone

[0325] 1. A user searches for "smartphone."

[0326] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[0327] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0328] 4. User clicks on a specific phone to view details.

[0329] 5. Product detail pages highlight high-resolution images first, followed by expert reviews.

[0330] 6. The emotion engine recognizes that the user is curious and displays detailed technical information and related videos.

[0331] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0332] Example 2: Purchasing a fashion item

[0333] 1. A user searches for "summer dresses."

[0334] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[0335] 3. Casual and affordable dresses will appear at the top of the search results page.

[0336] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0337] 5. If the emotion engine detects that the user is confused, detailed product descriptions and reviews will be highlighted.

[0338] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[0339] The system of the present invention provides a user interface and user experience that is optimized for each individual customer, which is expected to increase purchase rates. By combining it with an emotion engine, a more personalized experience that responds to the customer's momentary emotional state becomes possible.

[0340] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0341] Step 1: Collecting user access and sentiment data

[0342] A user accesses an e-commerce site and enters search keywords. The device records purchasing behavior data such as visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information, and sends this data to the server. At the same time, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. This data is collected to identify the user's emotional state. The input is the user's behavior and the data sensed by the device, and the output is a set of these data.

[0343] Step 2: Temporary storage and initial analysis of data

[0344] The server temporarily stores the collected access data and emotion data in a database. It then performs initial analysis, checks data consistency, and fills in missing values. Specifically, it performs anomaly detection, statistical analysis, and necessary preprocessing on the collected data. The input is the collected raw data, and the output is preprocessed data.

[0345] Step 3: Analyze purchasing behavior and sentiment using machine learning models

[0346] The server analyzes the collected purchasing behavior and emotional data using a pre-built generative AI model. The model analyzes users' preferences, behavioral patterns, and emotional states to identify their interests and purchasing tendencies. Specific operations include data preprocessing, feature extraction, model input, and obtaining prediction results. The input is the preprocessed data, and the output is the analysis results.

[0347] Step 4: Generate and update customer profiles

[0348] Based on the analysis results, the server generates a profile for each individual user and stores or updates it in a database. The profile includes the user's preferences, behavioral patterns, emotional state, etc. Specifically, this involves organizing and storing the analysis results, merging them with existing data, and updating the profile as needed. The input is the analysis results, and the output is an updated customer profile.

[0349] Step 5: Optimize search results

[0350] When a user searches for a product, the server matches the pre-generated customer profile with real-time emotional data to optimize the search results. For example, if a user searches for "smartphone," the most suitable products will be displayed at the top based on past data and current emotional state. Specifically, this includes calculating the degree of match between the profile data and the search query, setting priorities, and adjusting the display order of the search results. The input is the search query and customer profile, and the output is an optimized list of search results.

[0351] Step 6: Customize your product detail page

[0352] When a user visits a specific product detail page, the server customizes the information on that page. For example, if the user prefers high-resolution images, an image gallery might be displayed first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, a detailed description of the product and its usage might be highlighted. The input is a customer profile and real-time emotion data; the output is a customized product detail page.

[0353] Step 7: View recommendations

[0354] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state. The input is information about the product being viewed, a customer profile, and emotional data, and the output is dynamically generated recommended information.

[0355] Step 8: Continuous learning and optimization

[0356] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected, and the server retrains the machine learning model based on this data. This continuously updates the customer profile, providing an even more accurate and personalized experience. Specifically, this involves preparing new data, retraining the model, and regenerating the profile. The input is the latest purchasing behavior and sentiment data, and the output is an updated machine learning model and customer profile.

[0357] (Application example 2)

[0358] 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."

[0359] Modern e-commerce sites and content distribution services are required to provide a user interface (UI) and user experience (UX) that is optimized for each individual customer. However, current systems have difficulty effectively utilizing customer emotional data to generate the optimal UI and UX in real time according to the situation. As a result, there is an issue that customer satisfaction, purchase rates, and viewer ratings are not being improved as effectively as expected.

[0360] 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 customer purchasing behavior data, means for analyzing the collected purchasing behavior data and emotional data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, and means for collecting user viewing behavior data and emotional data and recommending optimal content for the content distribution service based on the data. This solves the problems faced by conventional systems and makes it possible to provide each customer with an optimal UI and UX in real time, taking emotional data into consideration.

[0361] "Customer purchasing behavior data" refers to information about customer behavior history and transaction history on e-commerce sites.

[0362] "Emotion data" is data that identifies the emotional state of a customer extracted from their facial expressions, voice, operation speed, etc.

[0363] "User interface" refers to the entire interface that customers come into visual and operational contact with when using an e-commerce site or content distribution service.

[0364] "User experience" refers to the overall experience and evaluation that customers have when using an e-commerce site or content distribution service.

[0365] "Means for collection" refers to systems and devices for acquiring customer purchasing behavior data and emotional data.

[0366] "Means of analysis" refers to systems or devices that analyze collected data using machine learning models, etc., to reveal customer preferences and behavioral patterns.

[0367] "Automatic generation means" refers to a system or device that automatically designs and configures a user interface and user experience based on the analysis results.

[0368] "Providing means" refers to a system or device that displays or provides the generated user interface and user experience to a customer.

[0369] "Viewing behavior data" refers to information relating to the history, duration, and frequency of viewing of content viewed by a user in a content distribution service.

[0370] "Recommendation means" refers to a system or device that automatically selects optimal content based on analyzed data and suggests it to users.

[0371] This invention is a system for collecting and analyzing customer purchasing behavior data and emotion data on e-commerce sites and content distribution services, and automatically generating and providing a UI (user interface) and UX (user experience) optimized for each individual customer. Specific embodiments for implementing this invention are described below.

[0372] Data collection and emotion recognition

[0373] The device uses the camera, microphone, and sensors on the user's smartphone or computer to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. Purchasing behavior data, such as visit time, IP address, referring URL, search keywords, viewed product ID, viewing time, and cart addition information, is also collected at the same time. An emotion engine is used to analyze this data and identify emotional states such as joy, excitement, and confusion.

[0374] Data analysis and profile generation

[0375] The server analyzes the collected purchasing behavior and emotional data in real time. It uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0376] Optimizing search results

[0377] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[0378] Customizing your product detail page

[0379] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[0380] Viewing Recommendations

[0381] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[0382] Continuous learning and optimization

[0383] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[0384] Specific example of content distribution service

[0385] When a user opens a content distribution app, the server identifies videos or movies the user might want to watch based on their past viewing history and current emotional state (e.g., relaxed). The app's home screen displays movies and TV shows that match the user's mood and preferences at the time, and when the user clicks on a specific movie or TV show, the details page displays interesting trailers and cast information. The emotion engine monitors the user's reactions and adjusts the content it suggests.

[0386] Hardware and software used

[0387] Camera: Captures the user's facial expressions using the device's built-in camera.

[0388] Microphone: Collecting user feedback.

[0389] OpenCV: Image processing library for facial expression detection and preprocessing.

[0390] Keras: A framework for sentiment analysis models.

[0391] TensorFlow: Used to retrain machine learning models.

[0392] Emotion engine: Identify the user's emotional state.

[0393] Examples of prompts with concrete examples

[0394] An example of a prompt is:

[0395] Develop a system that suggests the best movies for users who are relaxing, based on their viewing history and facial expression data. Design an algorithm that recommends content tailored to each individual user, based on their viewing history and real-time emotional data.

[0396] The above is an embodiment of the present invention. This system makes it possible to provide each customer with an optimal UI and UX in real time, taking into account their emotional data.

[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0398] Step 1:

[0399] The device collects the user's facial expressions and voice using a camera and microphone. Specifically, when the user is using an e-commerce site or content distribution app, the camera captures an image of the user's face and the microphone records the user's voice. The collected data is sent to the server in real time. The input is real-time data from the camera and microphone, and the output is the collected raw data.

[0400] Step 2:

[0401] The server preprocesses the collected facial expression data using OpenCV. Specifically, it converts the image to grayscale and detects the facial area. Next, it resizes the facial area to a size that can be processed by the emotion recognition model. The input is the image data sent from the device, and the output is the resized facial area data.

[0402] Step 3:

[0403] The server analyzes the preprocessed facial data using a Keras model to identify the user's emotional state. Specifically, the resized facial image is input into a Keras emotion recognition model to predict an emotion label, such as happiness, excitement, or confusion. The input is the preprocessed facial image data, and the output is the emotion label.

[0404] Step 4:

[0405] The device collects the user's operation speed and operation history. Specifically, it records the user's operation log, such as scrolling through a web page or clicking on an item. The input is the user's operation data, and the output is the operation log.

[0406] Step 5:

[0407] The server updates the customer profile based on the collected operation logs. Specifically, it uses a machine learning model to update the customer profile in real time based on the user's past browsing history, purchase history, current operation speed, and emotional data. The input is the operation log and emotional data, and the output is the updated customer profile data.

[0408] Step 6:

[0409] When a user searches for a product on an e-commerce site, the server optimizes the search results based on the analyzed profile data and current emotional data. Specifically, it sorts the search results to display the most appropriate products at the top, taking into account the user's preferences and emotional state. The input is the user's search query and profile data, and the output is the optimized search results.

[0410] Step 7:

[0411] When a user visits a specific product detail page, the server customizes the information structure of that page. Specifically, if a user prefers high-resolution images, an image gallery may be displayed first, and if detailed technical information needs to be emphasized, it may be brought to the forefront. The input is the user's profile data and emotional data, and the output is a customized product detail page.

[0412] Step 8:

[0413] The server displays product-related recommendations to users who are browsing a particular product. Specifically, it suggests related accessories and additional products while taking into account the user's emotional state. The input is the user's profile data and current emotional data, and the output is a list of recommended products.

[0414] Step 9:

[0415] The server retrains the machine learning model with new purchasing behavior and sentiment data each time the user visits the e-commerce site or content delivery app. This continually updates the profile and provides a more personalized experience. The input is the new purchasing behavior and sentiment data, and the output is the retrained machine learning model.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Second embodiment]

[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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. 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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."

[0432] This invention is a system that collects and analyzes customer purchasing behavior data on e-commerce sites, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language, along with specific examples.

[0433] Data collection

[0434] When a user accesses an e-commerce site, the server automatically collects the following data: visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[0435] Data analysis

[0436] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models to analyze customer behavior patterns and preferences, identifying interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0437] Optimizing search results

[0438] When a user searches for a product on an e-commerce site, the server refers to a pre-created customer profile to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[0439] Customizing your product detail page

[0440] When a user visits a particular product detail page, the server customizes the information structure of that page. For example, if a user prefers high-resolution images, the image gallery might be displayed first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the review section might be brought to the forefront and detailed reviews might be displayed.

[0441] Viewing Recommendations

[0442] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[0443] Continuous learning and optimization

[0444] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more personalized experience.

[0445] Specific examples

[0446] Example 1: Searching for and purchasing a smartphone

[0447] 1. A user searches for "smartphone."

[0448] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[0449] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0450] 4. User clicks on a specific phone to view details.

[0451] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0452] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0453] Example 2: Purchasing a fashion item

[0454] 1. A user searches for "summer dresses."

[0455] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[0456] 3. Casual and affordable dresses will appear at the top of the search results page.

[0457] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0458] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[0459] The above is an embodiment of the present invention. This system provides a UI and UX that are optimized for each customer, and is expected to improve purchase rates.

[0460] The processing flow will be explained below.

[0461] Step 1:

[0462] A user accesses an e-commerce site and enters search keywords.

[0463] Step 2:

[0464] The server automatically collects and logs users' search keywords and access information (such as visit time, IP address, and referring URL).

[0465] Step 3:

[0466] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from the database.

[0467] Step 4:

[0468] The server analyzes the collected data in real time and identifies user preferences and behavioral patterns based on machine learning models.

[0469] Step 5:

[0470] The server uses the customer profile generated from the analysis results to optimize the search results, specifically sorting products that are likely to interest the user to the top.

[0471] Step 6:

[0472] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[0473] Step 7:

[0474] When a user clicks to view a particular product detail page, the server customizes the information on that page, for example, changing the image gallery, review section, or product specifications.

[0475] Step 8:

[0476] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[0477] Step 9:

[0478] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[0479] Step 10:

[0480] When a user adds an item to their cart, the server records that information and updates the customer profile.

[0481] Step 11:

[0482] The server periodically retrains the machine learning model based on new purchasing behavior data to improve the accuracy of the profile.

[0483] These are the specific processing steps for a system that provides an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[0484] Example 1

[0485] 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."

[0486] Conventional e-commerce sites face the challenge of being unable to provide a personalized user interface (UI) or user experience (UX) based on each individual customer's purchasing behavior and preferences. Furthermore, because continuous optimization through real-time data processing and retraining of machine learning models is not performed, they are unable to quickly respond to changes in customer interests and purchasing trends. A system that can solve these problems and increase customer purchase rates is needed.

[0487] 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.

[0488] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, means for using a machine learning model to analyze customer behavior patterns and preferences, means for processing data in real time, and means for generating a profile for each customer and storing it in a database. This makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[0489] "Customer purchasing behavior data" refers to information about a customer's behavior on a website, such as the time of visit, IP address, referring URL, search keywords, ID of the viewed product, viewing time, and cart addition information.

[0490] "Analysis means" refers to the technical means for processing collected customer purchasing behavior data and identifying customer behavior patterns and preferences.

[0491] "User interface" refers to the interactive elements that customers directly touch and manipulate when searching, browsing, and purchasing products through a website.

[0492] "User experience" refers to the overall experience and feeling a customer has when using a website, including the site's structure, design, usability, and the quality of the information provided.

[0493] A "machine learning model" is an algorithm or technology that learns from collected data and enables future predictions and classifications.

[0494] A "profile" is a collection of data that includes each customer's preferences and behavioral patterns, created based on the results of analysis.

[0495] A "database" is a system that stores and manages data based on a certain structure, enabling efficient searching and updating.

[0496] "Optimization" refers to maximizing the efficiency of what is provided to customers based on collected data and analysis results, and providing the most appropriate information and context for each individual customer.

[0497] "Processing data in real time" refers to a series of processes in which collected data is analyzed immediately and the results are reflected immediately.

[0498] "Recommended information" is information that presents highly relevant products and services based on a customer's current browsing and purchasing behavior.

[0499] "Retraining" is the process of retraining an existing machine learning model using new data to improve the model's accuracy and effectiveness.

[0500] The present invention is a system that collects and analyzes customer purchasing behavior data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Specific embodiments of the system are described below.

[0501] Data collection

[0502] When a user visits an e-commerce site, the server automatically collects the following data: time of visit, IP address, referring URL, search keywords, viewed product ID, viewing time, add-to-cart information, etc. This information is collected using web server software such as Apache or Nginx.

[0503] Data analysis

[0504] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences and identify interests and purchasing trends. The analysis results are stored in a relational database (e.g., MySQL or PostgreSQL) as a profile for each customer.

[0505] Optimizing search results

[0506] When a user searches for a product on an e-commerce site, the server refers to the user profile created in advance to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[0507] Customizing your product detail page

[0508] When a user visits a particular product detail page, the server customizes the page's information structure based on the user's preferences. For example, if a user prefers high-resolution images, the server might display an image gallery first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the server might bring the review section to the forefront and display detailed reviews.

[0509] Viewing Recommendations

[0510] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[0511] Continuous learning and optimization

[0512] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more personalized experience.

[0513] Specific examples

[0514] Example 1: Searching for and purchasing a smartphone

[0515] 1. A user searches for "smartphone."

[0516] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[0517] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0518] 4. User clicks on a specific phone to view details.

[0519] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0520] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0521] Example 2: Purchasing a fashion item

[0522] 1. A user searches for "summer dresses."

[0523] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[0524] 3. Casual and affordable dresses will appear at the top of the search results page.

[0525] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0526] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[0527] This system can stimulate individual users' purchasing desire and increase the value of the EC site, which is expected to lead to increased sales and customer satisfaction.

[0528] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0529] Step 1:

[0530] A user accesses an e-commerce site.

[0531] Input: The user enters the URL of the e-commerce site using a browser.

[0532] Action: The server receives an access request.

[0533] Output: The server prepares to record the user's visit information.

[0534] Step 2:

[0535] The server collects user visit information.

[0536] Input: Access request and associated metadata (e.g., time of visit, IP address, referring URL, etc.).

[0537] How it works: The server uses web server software such as Apache or Nginx to record visit times, IP addresses, referring URLs, search keywords, viewed product IDs, viewed times, add-to-cart information, etc.

[0538] Output: The collected visit information is stored in a database.

[0539] Step 3:

[0540] The data collected by the server is analyzed using machine learning models.

[0541] Input: User purchasing behavior data collected in a database.

[0542] How it works: The server sends data to a machine learning model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences.

[0543] Output: The analysis results are generated and stored in a database as a profile for each customer.

[0544] Step 4:

[0545] The user searches for a product.

[0546] Input: A user enters a product name or keyword into the search box of an e-commerce site.

[0547] Operation: A server receives a search query.

[0548] Output: The search query is prepared for analysis.

[0549] Step 5:

[0550] The server optimizes search results based on user profiles.

[0551] Input: Search query and user profile.

[0552] How it works: The server looks up your profile and sorts the search results to bring the most relevant products to the top.

[0553] Output: The optimized search results are displayed in the user's browser.

[0554] Step 6:

[0555] A user visits a specific product detail page.

[0556] Input: User clicks on a specific product from the search results.

[0557] What happens: The server retrieves the product details and renders the page.

[0558] Output: Detail page information is prepared.

[0559] Step 7:

[0560] The server customizes the product detail page based on the user's preferences.

[0561] Input: User profile and product details.

[0562] How it works: The server dynamically changes the layout and content of the page based on user preferences, highlighting high-resolution image galleries for image-focused users and highlighting reviews for review-focused users.

[0563] Output: A customized product detail page is displayed to the user.

[0564] Step 8:

[0565] The server displays related information about the product being viewed.

[0566] Input: Viewed product information and user profile.

[0567] How it works: The server collects information about related products and displays them on the page you are viewing. For example, on a smartphone detail page, it might recommend cases and screen protectors specifically for that model.

[0568] Output: Related product information is displayed to the user.

[0569] Step 9:

[0570] The server retrains the machine learning model with the new behavioral data.

[0571] Input: New purchasing behavior data.

[0572] How it works: The server retrains the machine learning model with newly collected data, improving the model's accuracy.

[0573] Output: Updated customer profile and optimization algorithm.

[0574] Through these steps, the present invention makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[0575] (Application example 1)

[0576] 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."

[0577] In online shopping, the challenge is to improve customer satisfaction by efficiently collecting customer behavior data and providing individually optimized user interfaces (UIs) and user experiences (UXs) based on that data. Furthermore, there is a need to increase purchasing motivation by analyzing customer interests and purchasing trends in real time and providing personalized recommendations.

[0578] 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.

[0579] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, and means for automatically generating an optimal user interface and user experience for the customer based on the analysis results. This makes it possible to analyze each customer's behavior data in real time using machine learning and provide a personalized experience in conjunction with an application installed on the smart device. In addition, by optimizing the display order of search results and displaying individually optimized product detail pages and related recommended information, it is possible to simultaneously improve customer satisfaction and purchasing motivation.

[0580] "Customer purchasing behavior data" refers to data that indicates the actions that customers take on an e-commerce site, such as browsing, searching, adding to cart, and purchasing.

[0581] "Means of collection" refers to the functions of systems and software that record and store customer behavior data when accessing an e-commerce site.

[0582] "Means of analysis" refers to machine learning models and algorithms used to analyze collected customer purchasing behavior data in real time and identify customer interests and preferences.

[0583] "User interface (UI)" refers to the screen layout and operation methods that customers see when using an e-commerce site or app.

[0584] "User experience (UX)" refers to the overall sense of use and satisfaction that customers feel in the process of using an e-commerce site or app.

[0585] "Optimization measures" refers to the function of adjusting the order in which search results and pages are displayed based on data for each customer, and presenting the most appropriate content.

[0586] "Search result display order" refers to the order in which products are displayed when a customer searches for a product using keywords.

[0587] A "product detail page" refers to a web page or app screen that contains detailed information about a specific product.

[0588] "Information structure" refers to the layout and display format of information such as images, reviews, specifications, and recommended information on product detail pages.

[0589] "Applications installed on smart devices" refers to software programs installed on mobile devices such as smartphones and tablets.

[0590] "Analyzing behavioral data in real time using machine learning" refers to the process of collecting various operations performed by customers on a website or app in real time and instantly analyzing them using a machine learning model.

[0591] "Means of linking" refers to a mechanism by which applications on smart devices automatically generate and provide optimal UI and UX based on the analysis results.

[0592] "Recommended information" refers to information that suggests related products and services based on the products a customer is viewing and their past behavioral patterns.

[0593] "Continuous learning" refers to the process of retraining machine learning models based on newly collected data to improve analysis accuracy.

[0594] This invention is a system that collects and analyzes purchasing behavior data on e-commerce sites and provides customers with an optimized user interface and user experience through an application installed on a smart device. An embodiment of this system will be described in detail.

[0595] Hardware and software used

[0596] Hardware: Smartphone (iOS, Android), server

[0597] Software: Python, TensorFlow / Keras (machine learning libraries), Firebase (data collection and management)

[0598] Data collection

[0599] Customer purchasing behavior data for e-commerce sites is automatically collected in real time via Firebase, including visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[0600] Data analysis

[0601] The collected data is analyzed on the server. Machine learning models are run using Python and TensorFlow / Keras to analyze each customer's behavioral patterns and preferences. The analysis results identify the customer's interests and purchasing trends and are stored as a profile in Firebase. For example, a customer identified as being interested in "beachwear" will be prioritized in the display of products in that category.

[0602] Generate optimized search results and product detail pages

[0603] When a customer searches for a product, the server optimizes the order of search results based on the profile it creates. When the user visits a product detail page, the information on that page is also customized based on the profile, displaying information tailored to the customer's preferences, such as high-resolution images or expert reviews.

[0604] Viewing Recommendations

[0605] In addition, the server recommends items related to the product being viewed. For example, if you are viewing a smartphone, cases and screen protectors for that model will be displayed, encouraging customers to make a purchase.

[0606] Continuous learning and optimization

[0607] The system continuously learns to deliver a more personalized experience. Every time a user interacts with a site or application, new behavioral data is collected and the machine learning model is retrained, ensuring customer profiles are always up-to-date and enabling further optimization.

[0608] Specific examples

[0609] Example 1: Searching for and purchasing a smartphone

[0610] When a user searches for "smartphone," the server determines from their browsing history that they are interested in the latest, high-performance smartphones. The search results page will display new products and highly rated smartphones at the top of the results. When a user visits the detail page for a specific smartphone, high-resolution images are prioritized and expert reviews are highlighted. Related accessories are also recommended.

[0611] Prompt Sentence Examples

[0612] When a user searches for "summer clothes":

[0613] "When a user searches for summer clothes, what data in particular do you collect and how do you analyze it?"

[0614] "Write a prompt recommending appropriate items for users interested in beachwear."

[0615] In this way, the system of the present invention provides users with an optimized UI and UX, increasing customer satisfaction.

[0616] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0617] Step 1:

[0618] When a user accesses an e-commerce site, the device collects purchasing behavior data such as visit time, IP address, referral URL, search keywords, viewed product ID, viewing time, and cart addition information. This data is sent to Firebase in real time. The input is user behavior data, and the output is the collected data stored in Firebase.

[0619] Step 2:

[0620] The server analyzes the purchasing behavior data stored in Firebase. It applies machine learning models using Python and TensorFlow / Keras to analyze customer behavior patterns and preferences. The machine learning models process the data using neural networks and save it as a customer profile. The input is the collected user data, and the output is the analysis results generated as a customer profile.

[0621] Step 3:

[0622] When a user searches for a product on an e-commerce site, the server references the customer profile in Firebase to optimize the search results. The input is the user's search keywords and customer profile, and the output is optimized search results that are displayed to the user. The server calculates the ranking of related products and adjusts the display order.

[0623] Step 4:

[0624] When a user visits a particular product detail page, the server customizes the information structure of that page. First, the server prioritizes displaying information tailored to the customer's interests, such as high-resolution images and a review section. The input is the customer profile and product detail page data, and the output is a customized page displayed on the user's device.

[0625] Step 5:

[0626] The server displays recommendations related to the specific product the user is viewing, for example, accessories specific to that model while browsing a smartphone. The input is the currently viewed product information and a customer profile, and the output is generated and presented to the user with recommendations for related products and accessories.

[0627] Step 6:

[0628] Every time a user interacts with the e-commerce site, the server collects new behavioral data and retrains the machine learning model, ensuring that the customer profile is always up to date. The input is the user's new behavioral data, and the output is an updated machine learning model and customer profile. This step allows for further optimization.

[0629] 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.

[0630] This invention is a system that collects and analyzes customer purchasing behavior and emotion data on e-commerce sites to automatically generate and provide a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language and provide specific examples.

[0631] Data collection and emotion recognition

[0632] When a user accesses an e-commerce site and enters a search keyword, the server automatically collects the following data: visit time, IP address, referring URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. The emotion engine analyzes this data and identifies emotional states such as joy, excitement, and confusion.

[0633] Data analysis and profile generation

[0634] The collected purchasing behavior and emotional data is analyzed in real time. The server uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0635] Optimizing search results

[0636] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[0637] Customizing your product detail page

[0638] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[0639] Viewing Recommendations

[0640] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[0641] Continuous learning and optimization

[0642] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[0643] Specific examples

[0644] Example 1: Searching for and purchasing a smartphone

[0645] 1. A user searches for "smartphone."

[0646] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[0647] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0648] 4. User clicks on a specific phone to view details.

[0649] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0650] 6. The emotion engine recognizes that the user is curious and displays more detailed technical information and related videos.

[0651] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0652] Example 2: Purchasing a fashion item

[0653] 1. A user searches for "summer dresses."

[0654] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[0655] 3. Casual and affordable dresses will appear at the top of the search results page.

[0656] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0657] 5. If the sentiment engine detects that the user is confused, it will highlight detailed product descriptions and reviews.

[0658] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[0659] The above is an embodiment of the present invention. This system provides a UI and UX optimized for each customer, which is expected to improve purchase rates. By combining it with an emotion engine, a more personalized experience can be provided that responds to the customer's momentary emotional state.

[0660] The processing flow will be explained below.

[0661] Step 1:

[0662] A user accesses an e-commerce site and enters search keywords.

[0663] Step 2:

[0664] The server automatically collects and logs access information such as the user's search keywords, visit time, IP address, and referring URL.

[0665] Step 3:

[0666] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from a database, and the emotion engine collects emotional data such as the user's facial expressions, voice, and operation speed through the device's camera, microphone, and sensors.

[0667] Step 4:

[0668] The server analyzes purchasing behavior data and emotional data in real time and uses machine learning models to identify user preferences, behavioral patterns, and emotional states.

[0669] Step 5:

[0670] The server generates optimal search results for users based on the customer profile and emotion data generated from the analysis results, specifically sorting products of interest to the top.

[0671] Step 6:

[0672] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[0673] Step 7:

[0674] When a user clicks to view a particular product detail page, the server customizes the information structure on that page, for example displaying an image gallery first if the user prefers high-resolution images, or highlighting expert reviews.

[0675] Step 8:

[0676] Based on the user's emotional state (e.g., confused) recognized by the emotion engine, the server highlights detailed product descriptions and usage instructions.

[0677] Step 9:

[0678] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[0679] Step 10:

[0680] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[0681] Step 11:

[0682] The emotion engine adjusts the type and timing of recommendations based on the user's emotional state. For example, if the user is excited, it will display related products at an earlier stage, with higher prices.

[0683] Step 12:

[0684] When a user adds an item to their cart, the server records that information and updates the customer profile.

[0685] Step 13:

[0686] The server periodically retrains the machine learning model with new purchasing behavior and sentiment data to improve the accuracy of the profiles.

[0687] These are the specific processing steps of a system that combines an emotion engine to provide an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[0688] Example 2

[0689] 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."

[0690] Conventional e-commerce sites typically attempt to optimize the user experience by using only customer purchasing behavior data. However, this makes it difficult to achieve detailed personalization based on the customer's emotional state, and further improvements in purchase rates cannot be expected. The purpose of this invention is to solve this problem and achieve even more accurate personalization by utilizing each customer's emotional data.

[0691] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting customer purchasing behavior data, means for collecting customer emotion data, means for analyzing the collected purchasing behavior data and emotion data, means for generating and updating a customer profile based on the analysis results, means for automatically generating an optimal user interface and user experience for the customer, and means for providing an optimal user interface and user experience for the customer. This enables personalization that takes into account the emotional state of the customer, making it possible to improve the purchase rate.

[0692] "Customer" refers to a user who uses an e-commerce site to search for, browse, and purchase products and services.

[0693] "Purchasing behavior data" refers to the behavioral history of customers on e-commerce sites, such as search keywords, viewed product IDs, viewing times, and cart addition information.

[0694] "Emotion data" is data that expresses the emotional state of the customer, obtained from facial expressions, voice, operation speed, etc.

[0695] "Analysis" is the process of identifying customer preferences, behavioral patterns, and emotional states based on collected data.

[0696] A "profile" is data that compiles information such as each customer's preferences, behavioral patterns, and emotional state.

[0697] A "user interface" refers to the screen layout and operational elements that customers interact with visually and operationally when using an e-commerce site.

[0698] "User experience" is a concept that refers to the overall satisfaction and usability that customers feel when using an e-commerce site.

[0699] "Optimization" is the process of adjusting search results, product detail pages, and even recommendations based on each customer's individual profile.

[0700] "Automatic generation" refers to the operation in which the system performs settings and output based on specific conditions and data without human intervention.

[0701] "Recommendations" are additional suggestions or information displayed related to the product or service a customer is viewing.

[0702] A "machine learning model" is a collection of algorithms used to predict or classify specific outcomes based on data.

[0703] MODE FOR CARRYING OUT THE INVENTION

[0704] This invention is a system that collects and analyzes customer purchasing behavior data and emotion data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. A specific embodiment of this system is described below.

[0705] Data collection and emotion recognition

[0706] A user accesses an e-commerce site and enters a search keyword. At this point, the server automatically collects purchasing behavior data, such as the visit time, IP address, referrer URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the server uses the device's built-in camera, microphone, and sensors to collect real-time emotional data, such as the user's facial expression, voice, and operation speed. This data is analyzed by an emotion engine to identify the user's emotional state, such as joy, excitement, or confusion.

[0707] Data analysis and profile generation

[0708] The collected purchasing behavior and emotional data is analyzed in real time by a server. The server uses machine learning models, such as generative AI models, to perform detailed analysis of customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0709] Optimizing search results

[0710] When a user searches for a product on an e-commerce site, the server compares pre-generated customer profiles with real-time emotional data to optimize search results. For example, if a user searches for "smartphone," the server will display the latest models and feature-rich smartphones at the top of the results based on past data and the user's current emotional state.

[0711] Customizing your product detail page

[0712] When a user visits a particular product detail page, the server customizes the information on that page. For example, if a user prefers high-resolution images, the product detail page might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, detailed product descriptions and usage instructions might be highlighted.

[0713] Viewing Recommendations

[0714] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state.

[0715] Continuous learning and optimization

[0716] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model. This process continually updates customer profiles, providing an even more accurate and personalized experience.

[0717] Adding specific examples

[0718] Example 1: Searching for and purchasing a smartphone

[0719] 1. A user searches for "smartphone."

[0720] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[0721] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0722] 4. User clicks on a specific phone to view details.

[0723] 5. Product detail pages highlight high-resolution images first, followed by expert reviews.

[0724] 6. The emotion engine recognizes that the user is curious and displays detailed technical information and related videos.

[0725] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0726] Example 2: Purchasing a fashion item

[0727] 1. A user searches for "summer dresses."

[0728] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[0729] 3. Casual and affordable dresses will appear at the top of the search results page.

[0730] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0731] 5. If the emotion engine detects that the user is confused, detailed product descriptions and reviews will be highlighted.

[0732] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[0733] The system of the present invention provides a user interface and user experience that is optimized for each individual customer, which is expected to increase purchase rates. By combining it with an emotion engine, a more personalized experience that responds to the customer's momentary emotional state becomes possible.

[0734] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0735] Step 1: Collecting user access and sentiment data

[0736] A user accesses an e-commerce site and enters search keywords. The device records purchasing behavior data such as visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information, and sends this data to the server. At the same time, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. This data is collected to identify the user's emotional state. The input is the user's behavior and the data sensed by the device, and the output is a set of these data.

[0737] Step 2: Temporary storage and initial analysis of data

[0738] The server temporarily stores the collected access data and emotion data in a database. It then performs initial analysis, checks data consistency, and fills in missing values. Specifically, it performs anomaly detection, statistical analysis, and necessary preprocessing on the collected data. The input is the collected raw data, and the output is preprocessed data.

[0739] Step 3: Analyze purchasing behavior and sentiment using machine learning models

[0740] The server analyzes the collected purchasing behavior and emotional data using a pre-built generative AI model. The model analyzes users' preferences, behavioral patterns, and emotional states to identify their interests and purchasing tendencies. Specific operations include data preprocessing, feature extraction, model input, and obtaining prediction results. The input is the preprocessed data, and the output is the analysis results.

[0741] Step 4: Generate and update customer profiles

[0742] Based on the analysis results, the server generates a profile for each individual user and stores or updates it in a database. The profile includes the user's preferences, behavioral patterns, emotional state, etc. Specifically, this involves organizing and storing the analysis results, merging them with existing data, and updating the profile as needed. The input is the analysis results, and the output is an updated customer profile.

[0743] Step 5: Optimize search results

[0744] When a user searches for a product, the server matches the pre-generated customer profile with real-time emotional data to optimize the search results. For example, if a user searches for "smartphone," the most suitable products will be displayed at the top based on past data and current emotional state. Specifically, this includes calculating the degree of match between the profile data and the search query, setting priorities, and adjusting the display order of the search results. The input is the search query and customer profile, and the output is an optimized list of search results.

[0745] Step 6: Customize your product detail page

[0746] When a user visits a specific product detail page, the server customizes the information on that page. For example, if the user prefers high-resolution images, an image gallery might be displayed first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, a detailed description of the product and its usage might be highlighted. The input is a customer profile and real-time emotion data; the output is a customized product detail page.

[0747] Step 7: View recommendations

[0748] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state. The input is information about the product being viewed, a customer profile, and emotional data, and the output is dynamically generated recommended information.

[0749] Step 8: Continuous learning and optimization

[0750] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected, and the server retrains the machine learning model based on this data. This continuously updates the customer profile, providing an even more accurate and personalized experience. Specifically, this involves preparing new data, retraining the model, and regenerating the profile. The input is the latest purchasing behavior and sentiment data, and the output is an updated machine learning model and customer profile.

[0751] (Application example 2)

[0752] 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."

[0753] Modern e-commerce sites and content distribution services are required to provide a user interface (UI) and user experience (UX) that is optimized for each individual customer. However, current systems have difficulty effectively utilizing customer emotional data to generate the optimal UI and UX in real time according to the situation. As a result, there is an issue that customer satisfaction, purchase rates, and viewer ratings are not being improved as effectively as expected.

[0754] 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 customer purchasing behavior data, means for analyzing the collected purchasing behavior data and emotional data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, and means for collecting user viewing behavior data and emotional data and recommending optimal content for the content distribution service based on the data. This solves the problems faced by conventional systems and makes it possible to provide each customer with an optimal UI and UX in real time, taking emotional data into consideration.

[0755] "Customer purchasing behavior data" refers to information about customer behavior history and transaction history on e-commerce sites.

[0756] "Emotion data" is data that identifies the emotional state of a customer extracted from their facial expressions, voice, operation speed, etc.

[0757] "User interface" refers to the entire interface that customers come into visual and operational contact with when using an e-commerce site or content distribution service.

[0758] "User experience" refers to the overall experience and evaluation that customers have when using an e-commerce site or content distribution service.

[0759] "Means for collection" refers to systems and devices for acquiring customer purchasing behavior data and emotional data.

[0760] "Means of analysis" refers to systems or devices that analyze collected data using machine learning models, etc., to reveal customer preferences and behavioral patterns.

[0761] "Automatic generation means" refers to a system or device that automatically designs and configures a user interface and user experience based on the analysis results.

[0762] "Providing means" refers to a system or device that displays or provides the generated user interface and user experience to a customer.

[0763] "Viewing behavior data" refers to information relating to the history, duration, and frequency of viewing of content viewed by a user in a content distribution service.

[0764] "Recommendation means" refers to a system or device that automatically selects optimal content based on analyzed data and suggests it to users.

[0765] This invention is a system for collecting and analyzing customer purchasing behavior data and emotion data on e-commerce sites and content distribution services, and automatically generating and providing a UI (user interface) and UX (user experience) optimized for each individual customer. Specific embodiments for implementing this invention are described below.

[0766] Data collection and emotion recognition

[0767] The device uses the camera, microphone, and sensors on the user's smartphone or computer to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. Purchasing behavior data, such as visit time, IP address, referring URL, search keywords, viewed product ID, viewing time, and cart addition information, is also collected at the same time. An emotion engine is used to analyze this data and identify emotional states such as joy, excitement, and confusion.

[0768] Data analysis and profile generation

[0769] The server analyzes the collected purchasing behavior and emotional data in real time. It uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0770] Optimizing search results

[0771] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[0772] Customizing your product detail page

[0773] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[0774] Viewing Recommendations

[0775] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[0776] Continuous learning and optimization

[0777] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[0778] Specific example of content distribution service

[0779] When a user opens a content distribution app, the server identifies videos or movies the user might want to watch based on their past viewing history and current emotional state (e.g., relaxed). The app's home screen displays movies and TV shows that match the user's mood and preferences at the time, and when the user clicks on a specific movie or TV show, the details page displays interesting trailers and cast information. The emotion engine monitors the user's reactions and adjusts the content it suggests.

[0780] Hardware and software used

[0781] Camera: Captures the user's facial expressions using the device's built-in camera.

[0782] Microphone: Collecting user feedback.

[0783] OpenCV: Image processing library for facial expression detection and preprocessing.

[0784] Keras: A framework for sentiment analysis models.

[0785] TensorFlow: Used to retrain machine learning models.

[0786] Emotion engine: Identify the user's emotional state.

[0787] Examples of prompts with concrete examples

[0788] An example of a prompt is:

[0789] Develop a system that suggests the best movies for users who are relaxing, based on their viewing history and facial expression data. Design an algorithm that recommends content tailored to each individual user, based on their viewing history and real-time emotional data.

[0790] The above is an embodiment of the present invention. This system makes it possible to provide each customer with an optimal UI and UX in real time, taking into account their emotional data.

[0791] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0792] Step 1:

[0793] The device collects the user's facial expressions and voice using a camera and microphone. Specifically, when the user is using an e-commerce site or content distribution app, the camera captures an image of the user's face and the microphone records the user's voice. The collected data is sent to the server in real time. The input is real-time data from the camera and microphone, and the output is the collected raw data.

[0794] Step 2:

[0795] The server preprocesses the collected facial expression data using OpenCV. Specifically, it converts the image to grayscale and detects the facial area. Next, it resizes the facial area to a size that can be processed by the emotion recognition model. The input is the image data sent from the device, and the output is the resized facial area data.

[0796] Step 3:

[0797] The server analyzes the preprocessed facial data using a Keras model to identify the user's emotional state. Specifically, the resized facial image is input into a Keras emotion recognition model to predict an emotion label, such as happiness, excitement, or confusion. The input is the preprocessed facial image data, and the output is the emotion label.

[0798] Step 4:

[0799] The device collects the user's operation speed and operation history. Specifically, it records the user's operation log, such as scrolling through a web page or clicking on an item. The input is the user's operation data, and the output is the operation log.

[0800] Step 5:

[0801] The server updates the customer profile based on the collected operation logs. Specifically, it uses a machine learning model to update the customer profile in real time based on the user's past browsing history, purchase history, current operation speed, and emotional data. The input is the operation log and emotional data, and the output is the updated customer profile data.

[0802] Step 6:

[0803] When a user searches for a product on an e-commerce site, the server optimizes the search results based on the analyzed profile data and current emotional data. Specifically, it sorts the search results to display the most appropriate products at the top, taking into account the user's preferences and emotional state. The input is the user's search query and profile data, and the output is the optimized search results.

[0804] Step 7:

[0805] When a user visits a specific product detail page, the server customizes the information structure of that page. Specifically, if a user prefers high-resolution images, an image gallery may be displayed first, and if detailed technical information needs to be emphasized, it may be brought to the forefront. The input is the user's profile data and emotional data, and the output is a customized product detail page.

[0806] Step 8:

[0807] The server displays product-related recommendations to users who are browsing a particular product. Specifically, it suggests related accessories and additional products while taking into account the user's emotional state. The input is the user's profile data and current emotional data, and the output is a list of recommended products.

[0808] Step 9:

[0809] The server retrains the machine learning model with new purchasing behavior and sentiment data each time the user visits the e-commerce site or content delivery app. This continually updates the profile and provides a more personalized experience. The input is the new purchasing behavior and sentiment data, and the output is the retrained machine learning model.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] [Third embodiment]

[0814] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0815] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0816] 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).

[0817] 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.

[0818] 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.

[0819] 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).

[0820] 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. 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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."

[0826] This invention is a system that collects and analyzes customer purchasing behavior data on e-commerce sites, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language, along with specific examples.

[0827] Data collection

[0828] When a user accesses an e-commerce site, the server automatically collects the following data: visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[0829] Data analysis

[0830] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models to analyze customer behavior patterns and preferences, identifying interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[0831] Optimizing search results

[0832] When a user searches for a product on an e-commerce site, the server refers to a pre-created customer profile to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[0833] Customizing your product detail page

[0834] When a user visits a particular product detail page, the server customizes the information structure of that page. For example, if a user prefers high-resolution images, the image gallery might be displayed first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the review section might be brought to the forefront and detailed reviews might be displayed.

[0835] Viewing Recommendations

[0836] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[0837] Continuous learning and optimization

[0838] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more personalized experience.

[0839] Specific examples

[0840] Example 1: Searching for and purchasing a smartphone

[0841] 1. A user searches for "smartphone."

[0842] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[0843] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0844] 4. User clicks on a specific phone to view details.

[0845] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0846] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0847] Example 2: Purchasing a fashion item

[0848] 1. A user searches for "summer dresses."

[0849] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[0850] 3. Casual and affordable dresses will appear at the top of the search results page.

[0851] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0852] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[0853] The above is an embodiment of the present invention. This system provides a UI and UX that are optimized for each customer, and is expected to improve purchase rates.

[0854] The processing flow will be explained below.

[0855] Step 1:

[0856] A user accesses an e-commerce site and enters search keywords.

[0857] Step 2:

[0858] The server automatically collects and logs users' search keywords and access information (such as visit time, IP address, and referring URL).

[0859] Step 3:

[0860] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from the database.

[0861] Step 4:

[0862] The server analyzes the collected data in real time and identifies user preferences and behavioral patterns based on machine learning models.

[0863] Step 5:

[0864] The server uses the customer profile generated from the analysis results to optimize the search results, specifically sorting products that are likely to interest the user to the top.

[0865] Step 6:

[0866] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[0867] Step 7:

[0868] When a user clicks to view a particular product detail page, the server customizes the information on that page, for example, changing the image gallery, review section, or product specifications.

[0869] Step 8:

[0870] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[0871] Step 9:

[0872] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[0873] Step 10:

[0874] When a user adds an item to their cart, the server records that information and updates the customer profile.

[0875] Step 11:

[0876] The server periodically retrains the machine learning model based on new purchasing behavior data to improve the accuracy of the profile.

[0877] These are the specific processing steps for a system that provides an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[0878] Example 1

[0879] 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."

[0880] Conventional e-commerce sites face the challenge of being unable to provide a personalized user interface (UI) or user experience (UX) based on each individual customer's purchasing behavior and preferences. Furthermore, because continuous optimization through real-time data processing and retraining of machine learning models is not performed, they are unable to quickly respond to changes in customer interests and purchasing trends. A system that can solve these problems and increase customer purchase rates is needed.

[0881] 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.

[0882] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, means for using a machine learning model to analyze customer behavior patterns and preferences, means for processing data in real time, and means for generating a profile for each customer and storing it in a database. This makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[0883] "Customer purchasing behavior data" refers to information about a customer's behavior on a website, such as the time of visit, IP address, referring URL, search keywords, ID of the viewed product, viewing time, and cart addition information.

[0884] "Analysis means" refers to the technical means for processing collected customer purchasing behavior data and identifying customer behavior patterns and preferences.

[0885] "User interface" refers to the interactive elements that customers directly touch and manipulate when searching, browsing, and purchasing products through a website.

[0886] "User experience" refers to the overall experience and feeling a customer has when using a website, including the site's structure, design, usability, and the quality of the information provided.

[0887] A "machine learning model" is an algorithm or technology that learns from collected data and enables future predictions and classifications.

[0888] A "profile" is a collection of data that includes each customer's preferences and behavioral patterns, created based on the results of analysis.

[0889] A "database" is a system that stores and manages data based on a certain structure, enabling efficient searching and updating.

[0890] "Optimization" refers to maximizing the efficiency of what is provided to customers based on collected data and analysis results, and providing the most appropriate information and context for each individual customer.

[0891] "Processing data in real time" refers to a series of processes in which collected data is analyzed immediately and the results are reflected immediately.

[0892] "Recommended information" is information that presents highly relevant products and services based on a customer's current browsing and purchasing behavior.

[0893] "Retraining" is the process of retraining an existing machine learning model using new data to improve the model's accuracy and effectiveness.

[0894] The present invention is a system that collects and analyzes customer purchasing behavior data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Specific embodiments of the system are described below.

[0895] Data collection

[0896] When a user visits an e-commerce site, the server automatically collects the following data: time of visit, IP address, referring URL, search keywords, viewed product ID, viewing time, add-to-cart information, etc. This information is collected using web server software such as Apache or Nginx.

[0897] Data analysis

[0898] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences and identify interests and purchasing trends. The analysis results are stored in a relational database (e.g., MySQL or PostgreSQL) as a profile for each customer.

[0899] Optimizing search results

[0900] When a user searches for a product on an e-commerce site, the server refers to the user profile created in advance to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[0901] Customizing your product detail page

[0902] When a user visits a particular product detail page, the server customizes the page's information structure based on the user's preferences. For example, if a user prefers high-resolution images, the server might display an image gallery first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the server might bring the review section to the forefront and display detailed reviews.

[0903] Viewing Recommendations

[0904] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[0905] Continuous learning and optimization

[0906] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more personalized experience.

[0907] Specific examples

[0908] Example 1: Searching for and purchasing a smartphone

[0909] 1. A user searches for "smartphone."

[0910] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[0911] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[0912] 4. User clicks on a specific phone to view details.

[0913] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[0914] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[0915] Example 2: Purchasing a fashion item

[0916] 1. A user searches for "summer dresses."

[0917] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[0918] 3. Casual and affordable dresses will appear at the top of the search results page.

[0919] 4. Product detail pages place particular emphasis on material information and coordination examples.

[0920] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[0921] This system can stimulate individual users' purchasing desire and increase the value of the EC site, which is expected to lead to increased sales and customer satisfaction.

[0922] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0923] Step 1:

[0924] A user accesses an e-commerce site.

[0925] Input: The user enters the URL of the e-commerce site using a browser.

[0926] Action: The server receives an access request.

[0927] Output: The server prepares to record the user's visit information.

[0928] Step 2:

[0929] The server collects user visit information.

[0930] Input: Access request and associated metadata (e.g., time of visit, IP address, referring URL, etc.).

[0931] How it works: The server uses web server software such as Apache or Nginx to record visit times, IP addresses, referring URLs, search keywords, viewed product IDs, viewed times, add-to-cart information, etc.

[0932] Output: The collected visit information is stored in a database.

[0933] Step 3:

[0934] The data collected by the server is analyzed using machine learning models.

[0935] Input: User purchasing behavior data collected in a database.

[0936] How it works: The server sends data to a machine learning model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences.

[0937] Output: The analysis results are generated and stored in a database as a profile for each customer.

[0938] Step 4:

[0939] The user searches for a product.

[0940] Input: A user enters a product name or keyword into the search box of an e-commerce site.

[0941] Operation: A server receives a search query.

[0942] Output: The search query is prepared for analysis.

[0943] Step 5:

[0944] The server optimizes search results based on user profiles.

[0945] Input: Search query and user profile.

[0946] How it works: The server looks up your profile and sorts the search results to bring the most relevant products to the top.

[0947] Output: The optimized search results are displayed in the user's browser.

[0948] Step 6:

[0949] A user visits a specific product detail page.

[0950] Input: User clicks on a specific product from the search results.

[0951] What happens: The server retrieves the product details and renders the page.

[0952] Output: Detail page information is prepared.

[0953] Step 7:

[0954] The server customizes the product detail page based on the user's preferences.

[0955] Input: User profile and product details.

[0956] How it works: The server dynamically changes the layout and content of the page based on user preferences, highlighting high-resolution image galleries for image-focused users and highlighting reviews for review-focused users.

[0957] Output: A customized product detail page is displayed to the user.

[0958] Step 8:

[0959] The server displays related information about the product being viewed.

[0960] Input: Viewed product information and user profile.

[0961] How it works: The server collects information about related products and displays them on the page you are viewing. For example, on a smartphone detail page, it might recommend cases and screen protectors specifically for that model.

[0962] Output: Related product information is displayed to the user.

[0963] Step 9:

[0964] The server retrains the machine learning model with the new behavioral data.

[0965] Input: New purchasing behavior data.

[0966] How it works: The server retrains the machine learning model with newly collected data, improving the model's accuracy.

[0967] Output: Updated customer profile and optimization algorithm.

[0968] Through these steps, the present invention makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[0969] (Application example 1)

[0970] 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."

[0971] In online shopping, the challenge is to improve customer satisfaction by efficiently collecting customer behavior data and providing individually optimized user interfaces (UIs) and user experiences (UXs) based on that data. Furthermore, there is a need to increase purchasing motivation by analyzing customer interests and purchasing trends in real time and providing personalized recommendations.

[0972] 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.

[0973] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, and means for automatically generating an optimal user interface and user experience for the customer based on the analysis results. This makes it possible to analyze each customer's behavior data in real time using machine learning and provide a personalized experience in conjunction with an application installed on the smart device. In addition, by optimizing the display order of search results and displaying individually optimized product detail pages and related recommended information, it is possible to simultaneously improve customer satisfaction and purchasing motivation.

[0974] "Customer purchasing behavior data" refers to data that indicates the actions that customers take on an e-commerce site, such as browsing, searching, adding to cart, and purchasing.

[0975] "Means of collection" refers to the functions of systems and software that record and store customer behavior data when accessing an e-commerce site.

[0976] "Means of analysis" refers to machine learning models and algorithms used to analyze collected customer purchasing behavior data in real time and identify customer interests and preferences.

[0977] "User interface (UI)" refers to the screen layout and operation methods that customers see when using an e-commerce site or app.

[0978] "User experience (UX)" refers to the overall sense of use and satisfaction that customers feel in the process of using an e-commerce site or app.

[0979] "Optimization measures" refers to the function of adjusting the order in which search results and pages are displayed based on data for each customer, and presenting the most appropriate content.

[0980] "Search result display order" refers to the order in which products are displayed when a customer searches for a product using keywords.

[0981] A "product detail page" refers to a web page or app screen that contains detailed information about a specific product.

[0982] "Information structure" refers to the layout and display format of information such as images, reviews, specifications, and recommended information on product detail pages.

[0983] "Applications installed on smart devices" refers to software programs installed on mobile devices such as smartphones and tablets.

[0984] "Analyzing behavioral data in real time using machine learning" refers to the process of collecting various operations performed by customers on a website or app in real time and instantly analyzing them using a machine learning model.

[0985] "Means of linking" refers to a mechanism by which applications on smart devices automatically generate and provide optimal UI and UX based on the analysis results.

[0986] "Recommended information" refers to information that suggests related products and services based on the products a customer is viewing and their past behavioral patterns.

[0987] "Continuous learning" refers to the process of retraining machine learning models based on newly collected data to improve analysis accuracy.

[0988] This invention is a system that collects and analyzes purchasing behavior data on e-commerce sites and provides customers with an optimized user interface and user experience through an application installed on a smart device. An embodiment of this system will be described in detail.

[0989] Hardware and software used

[0990] Hardware: Smartphone (iOS, Android), server

[0991] Software: Python, TensorFlow / Keras (machine learning libraries), Firebase (data collection and management)

[0992] Data collection

[0993] Customer purchasing behavior data for e-commerce sites is automatically collected in real time via Firebase, including visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[0994] Data analysis

[0995] The collected data is analyzed on the server. Machine learning models are run using Python and TensorFlow / Keras to analyze each customer's behavioral patterns and preferences. The analysis results identify the customer's interests and purchasing trends and are stored as a profile in Firebase. For example, a customer identified as being interested in "beachwear" will be prioritized in the display of products in that category.

[0996] Generate optimized search results and product detail pages

[0997] When a customer searches for a product, the server optimizes the order of search results based on the profile it creates. When the user visits a product detail page, the information on that page is also customized based on the profile, displaying information tailored to the customer's preferences, such as high-resolution images or expert reviews.

[0998] Viewing Recommendations

[0999] In addition, the server recommends items related to the product being viewed. For example, if you are viewing a smartphone, cases and screen protectors for that model will be displayed, encouraging customers to make a purchase.

[1000] Continuous learning and optimization

[1001] The system continuously learns to deliver a more personalized experience. Every time a user interacts with a site or application, new behavioral data is collected and the machine learning model is retrained, ensuring customer profiles are always up-to-date and enabling further optimization.

[1002] Specific examples

[1003] Example 1: Searching for and purchasing a smartphone

[1004] When a user searches for "smartphone," the server determines from their browsing history that they are interested in the latest, high-performance smartphones. The search results page will display new products and highly rated smartphones at the top of the results. When a user visits the detail page for a specific smartphone, high-resolution images are prioritized and expert reviews are highlighted. Related accessories are also recommended.

[1005] Prompt Sentence Examples

[1006] When a user searches for "summer clothes":

[1007] "When a user searches for summer clothes, what data in particular do you collect and how do you analyze it?"

[1008] "Write a prompt recommending appropriate items for users interested in beachwear."

[1009] In this way, the system of the present invention provides users with an optimized UI and UX, increasing customer satisfaction.

[1010] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1011] Step 1:

[1012] When a user accesses an e-commerce site, the device collects purchasing behavior data such as visit time, IP address, referral URL, search keywords, viewed product ID, viewing time, and cart addition information. This data is sent to Firebase in real time. The input is user behavior data, and the output is the collected data stored in Firebase.

[1013] Step 2:

[1014] The server analyzes the purchasing behavior data stored in Firebase. It applies machine learning models using Python and TensorFlow / Keras to analyze customer behavior patterns and preferences. The machine learning models process the data using neural networks and save it as a customer profile. The input is the collected user data, and the output is the analysis results generated as a customer profile.

[1015] Step 3:

[1016] When a user searches for a product on an e-commerce site, the server references the customer profile in Firebase to optimize the search results. The input is the user's search keywords and customer profile, and the output is optimized search results that are displayed to the user. The server calculates the ranking of related products and adjusts the display order.

[1017] Step 4:

[1018] When a user visits a particular product detail page, the server customizes the information structure of that page. First, the server prioritizes displaying information tailored to the customer's interests, such as high-resolution images and a review section. The input is the customer profile and product detail page data, and the output is a customized page displayed on the user's device.

[1019] Step 5:

[1020] The server displays recommendations related to the specific product the user is viewing, for example, accessories specific to that model while browsing a smartphone. The input is the currently viewed product information and a customer profile, and the output is generated and presented to the user with recommendations for related products and accessories.

[1021] Step 6:

[1022] Every time a user interacts with the e-commerce site, the server collects new behavioral data and retrains the machine learning model, ensuring that the customer profile is always up to date. The input is the user's new behavioral data, and the output is an updated machine learning model and customer profile. This step allows for further optimization.

[1023] 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.

[1024] This invention is a system that collects and analyzes customer purchasing behavior and emotion data on e-commerce sites to automatically generate and provide a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language and provide specific examples.

[1025] Data collection and emotion recognition

[1026] When a user accesses an e-commerce site and enters a search keyword, the server automatically collects the following data: visit time, IP address, referring URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. The emotion engine analyzes this data and identifies emotional states such as joy, excitement, and confusion.

[1027] Data analysis and profile generation

[1028] The collected purchasing behavior and emotional data is analyzed in real time. The server uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[1029] Optimizing search results

[1030] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[1031] Customizing your product detail page

[1032] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[1033] Viewing Recommendations

[1034] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[1035] Continuous learning and optimization

[1036] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[1037] Specific examples

[1038] Example 1: Searching for and purchasing a smartphone

[1039] 1. A user searches for "smartphone."

[1040] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[1041] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[1042] 4. User clicks on a specific phone to view details.

[1043] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[1044] 6. The emotion engine recognizes that the user is curious and displays more detailed technical information and related videos.

[1045] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[1046] Example 2: Purchasing a fashion item

[1047] 1. A user searches for "summer dresses."

[1048] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[1049] 3. Casual and affordable dresses will appear at the top of the search results page.

[1050] 4. Product detail pages place particular emphasis on material information and coordination examples.

[1051] 5. If the sentiment engine detects that the user is confused, it will highlight detailed product descriptions and reviews.

[1052] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[1053] The above is an embodiment of the present invention. This system provides a UI and UX optimized for each customer, which is expected to improve purchase rates. By combining it with an emotion engine, a more personalized experience can be provided that responds to the customer's momentary emotional state.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] A user accesses an e-commerce site and enters search keywords.

[1057] Step 2:

[1058] The server automatically collects and logs access information such as the user's search keywords, visit time, IP address, and referring URL.

[1059] Step 3:

[1060] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from a database, and the emotion engine collects emotional data such as the user's facial expressions, voice, and operation speed through the device's camera, microphone, and sensors.

[1061] Step 4:

[1062] The server analyzes purchasing behavior data and emotional data in real time and uses machine learning models to identify user preferences, behavioral patterns, and emotional states.

[1063] Step 5:

[1064] The server generates optimal search results for users based on the customer profile and emotion data generated from the analysis results, specifically sorting products of interest to the top.

[1065] Step 6:

[1066] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[1067] Step 7:

[1068] When a user clicks to view a particular product detail page, the server customizes the information structure on that page, for example displaying an image gallery first if the user prefers high-resolution images, or highlighting expert reviews.

[1069] Step 8:

[1070] Based on the user's emotional state (e.g., confused) recognized by the emotion engine, the server highlights detailed product descriptions and usage instructions.

[1071] Step 9:

[1072] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[1073] Step 10:

[1074] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[1075] Step 11:

[1076] The emotion engine adjusts the type and timing of recommendations based on the user's emotional state. For example, if the user is excited, it will display related products at an earlier stage, with higher prices.

[1077] Step 12:

[1078] When a user adds an item to their cart, the server records that information and updates the customer profile.

[1079] Step 13:

[1080] The server periodically retrains the machine learning model with new purchasing behavior and sentiment data to improve the accuracy of the profiles.

[1081] These are the specific processing steps of a system that combines an emotion engine to provide an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[1082] Example 2

[1083] 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."

[1084] Conventional e-commerce sites typically attempt to optimize the user experience by using only customer purchasing behavior data. However, this makes it difficult to achieve detailed personalization based on the customer's emotional state, and further improvements in purchase rates cannot be expected. The purpose of this invention is to solve this problem and achieve even more accurate personalization by utilizing each customer's emotional data.

[1085] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting customer purchasing behavior data, means for collecting customer emotion data, means for analyzing the collected purchasing behavior data and emotion data, means for generating and updating a customer profile based on the analysis results, means for automatically generating an optimal user interface and user experience for the customer, and means for providing an optimal user interface and user experience for the customer. This enables personalization that takes into account the emotional state of the customer, making it possible to improve the purchase rate.

[1086] "Customer" refers to a user who uses an e-commerce site to search for, browse, and purchase products and services.

[1087] "Purchasing behavior data" refers to the behavioral history of customers on e-commerce sites, such as search keywords, viewed product IDs, viewing times, and cart addition information.

[1088] "Emotion data" is data that expresses the emotional state of the customer, obtained from facial expressions, voice, operation speed, etc.

[1089] "Analysis" is the process of identifying customer preferences, behavioral patterns, and emotional states based on collected data.

[1090] A "profile" is data that compiles information such as each customer's preferences, behavioral patterns, and emotional state.

[1091] A "user interface" refers to the screen layout and operational elements that customers interact with visually and operationally when using an e-commerce site.

[1092] "User experience" is a concept that refers to the overall satisfaction and usability that customers feel when using an e-commerce site.

[1093] "Optimization" is the process of adjusting search results, product detail pages, and even recommendations based on each customer's individual profile.

[1094] "Automatic generation" refers to the operation in which the system performs settings and output based on specific conditions and data without human intervention.

[1095] "Recommendations" are additional suggestions or information displayed related to the product or service a customer is viewing.

[1096] A "machine learning model" is a collection of algorithms used to predict or classify specific outcomes based on data.

[1097] MODE FOR CARRYING OUT THE INVENTION

[1098] This invention is a system that collects and analyzes customer purchasing behavior data and emotion data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. A specific embodiment of this system is described below.

[1099] Data collection and emotion recognition

[1100] A user accesses an e-commerce site and enters a search keyword. At this point, the server automatically collects purchasing behavior data, such as the visit time, IP address, referrer URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the server uses the device's built-in camera, microphone, and sensors to collect real-time emotional data, such as the user's facial expression, voice, and operation speed. This data is analyzed by an emotion engine to identify the user's emotional state, such as joy, excitement, or confusion.

[1101] Data analysis and profile generation

[1102] The collected purchasing behavior and emotional data is analyzed in real time by a server. The server uses machine learning models, such as generative AI models, to perform detailed analysis of customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[1103] Optimizing search results

[1104] When a user searches for a product on an e-commerce site, the server compares pre-generated customer profiles with real-time emotional data to optimize search results. For example, if a user searches for "smartphone," the server will display the latest models and feature-rich smartphones at the top of the results based on past data and the user's current emotional state.

[1105] Customizing your product detail page

[1106] When a user visits a particular product detail page, the server customizes the information on that page. For example, if a user prefers high-resolution images, the product detail page might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, detailed product descriptions and usage instructions might be highlighted.

[1107] Viewing Recommendations

[1108] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state.

[1109] Continuous learning and optimization

[1110] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model. This process continually updates customer profiles, providing an even more accurate and personalized experience.

[1111] Adding specific examples

[1112] Example 1: Searching for and purchasing a smartphone

[1113] 1. A user searches for "smartphone."

[1114] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[1115] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[1116] 4. User clicks on a specific phone to view details.

[1117] 5. Product detail pages highlight high-resolution images first, followed by expert reviews.

[1118] 6. The emotion engine recognizes that the user is curious and displays detailed technical information and related videos.

[1119] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[1120] Example 2: Purchasing a fashion item

[1121] 1. A user searches for "summer dresses."

[1122] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[1123] 3. Casual and affordable dresses will appear at the top of the search results page.

[1124] 4. Product detail pages place particular emphasis on material information and coordination examples.

[1125] 5. If the emotion engine detects that the user is confused, detailed product descriptions and reviews will be highlighted.

[1126] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[1127] The system of the present invention provides a user interface and user experience that is optimized for each individual customer, which is expected to increase purchase rates. By combining it with an emotion engine, a more personalized experience that responds to the customer's momentary emotional state becomes possible.

[1128] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1129] Step 1: Collecting user access and sentiment data

[1130] A user accesses an e-commerce site and enters search keywords. The device records purchasing behavior data such as visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information, and sends this data to the server. At the same time, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. This data is collected to identify the user's emotional state. The input is the user's behavior and the data sensed by the device, and the output is a set of these data.

[1131] Step 2: Temporary storage and initial analysis of data

[1132] The server temporarily stores the collected access data and emotion data in a database. It then performs initial analysis, checks data consistency, and fills in missing values. Specifically, it performs anomaly detection, statistical analysis, and necessary preprocessing on the collected data. The input is the collected raw data, and the output is preprocessed data.

[1133] Step 3: Analyze purchasing behavior and sentiment using machine learning models

[1134] The server analyzes the collected purchasing behavior and emotional data using a pre-built generative AI model. The model analyzes users' preferences, behavioral patterns, and emotional states to identify their interests and purchasing tendencies. Specific operations include data preprocessing, feature extraction, model input, and obtaining prediction results. The input is the preprocessed data, and the output is the analysis results.

[1135] Step 4: Generate and update customer profiles

[1136] Based on the analysis results, the server generates a profile for each individual user and stores or updates it in a database. The profile includes the user's preferences, behavioral patterns, emotional state, etc. Specifically, this involves organizing and storing the analysis results, merging them with existing data, and updating the profile as needed. The input is the analysis results, and the output is an updated customer profile.

[1137] Step 5: Optimize search results

[1138] When a user searches for a product, the server matches the pre-generated customer profile with real-time emotional data to optimize the search results. For example, if a user searches for "smartphone," the most suitable products will be displayed at the top based on past data and current emotional state. Specifically, this includes calculating the degree of match between the profile data and the search query, setting priorities, and adjusting the display order of the search results. The input is the search query and customer profile, and the output is an optimized list of search results.

[1139] Step 6: Customize your product detail page

[1140] When a user visits a specific product detail page, the server customizes the information on that page. For example, if the user prefers high-resolution images, an image gallery might be displayed first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, a detailed description of the product and its usage might be highlighted. The input is a customer profile and real-time emotion data; the output is a customized product detail page.

[1141] Step 7: View recommendations

[1142] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state. The input is information about the product being viewed, a customer profile, and emotional data, and the output is dynamically generated recommended information.

[1143] Step 8: Continuous learning and optimization

[1144] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected, and the server retrains the machine learning model based on this data. This continuously updates the customer profile, providing an even more accurate and personalized experience. Specifically, this involves preparing new data, retraining the model, and regenerating the profile. The input is the latest purchasing behavior and sentiment data, and the output is an updated machine learning model and customer profile.

[1145] (Application example 2)

[1146] 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."

[1147] Modern e-commerce sites and content distribution services are required to provide a user interface (UI) and user experience (UX) that is optimized for each individual customer. However, current systems have difficulty effectively utilizing customer emotional data to generate the optimal UI and UX in real time according to the situation. As a result, there is an issue that customer satisfaction, purchase rates, and viewer ratings are not being improved as effectively as expected.

[1148] 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 customer purchasing behavior data, means for analyzing the collected purchasing behavior data and emotional data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, and means for collecting user viewing behavior data and emotional data and recommending optimal content for the content distribution service based on the data. This solves the problems faced by conventional systems and makes it possible to provide each customer with an optimal UI and UX in real time, taking emotional data into consideration.

[1149] "Customer purchasing behavior data" refers to information about customer behavior history and transaction history on e-commerce sites.

[1150] "Emotion data" is data that identifies the emotional state of a customer extracted from their facial expressions, voice, operation speed, etc.

[1151] "User interface" refers to the entire interface that customers come into visual and operational contact with when using an e-commerce site or content distribution service.

[1152] "User experience" refers to the overall experience and evaluation that customers have when using an e-commerce site or content distribution service.

[1153] "Means for collection" refers to systems and devices for acquiring customer purchasing behavior data and emotional data.

[1154] "Means of analysis" refers to systems or devices that analyze collected data using machine learning models, etc., to reveal customer preferences and behavioral patterns.

[1155] "Automatic generation means" refers to a system or device that automatically designs and configures a user interface and user experience based on the analysis results.

[1156] "Providing means" refers to a system or device that displays or provides the generated user interface and user experience to a customer.

[1157] "Viewing behavior data" refers to information relating to the history, duration, and frequency of viewing of content viewed by a user in a content distribution service.

[1158] "Recommendation means" refers to a system or device that automatically selects optimal content based on analyzed data and suggests it to users.

[1159] This invention is a system for collecting and analyzing customer purchasing behavior data and emotion data on e-commerce sites and content distribution services, and automatically generating and providing a UI (user interface) and UX (user experience) optimized for each individual customer. Specific embodiments for implementing this invention are described below.

[1160] Data collection and emotion recognition

[1161] The device uses the camera, microphone, and sensors on the user's smartphone or computer to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. Purchasing behavior data, such as visit time, IP address, referring URL, search keywords, viewed product ID, viewing time, and cart addition information, is also collected at the same time. An emotion engine is used to analyze this data and identify emotional states such as joy, excitement, and confusion.

[1162] Data analysis and profile generation

[1163] The server analyzes the collected purchasing behavior and emotional data in real time. It uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[1164] Optimizing search results

[1165] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[1166] Customizing your product detail page

[1167] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[1168] Viewing Recommendations

[1169] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[1170] Continuous learning and optimization

[1171] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[1172] Specific example of content distribution service

[1173] When a user opens a content distribution app, the server identifies videos or movies the user might want to watch based on their past viewing history and current emotional state (e.g., relaxed). The app's home screen displays movies and TV shows that match the user's mood and preferences at the time, and when the user clicks on a specific movie or TV show, the details page displays interesting trailers and cast information. The emotion engine monitors the user's reactions and adjusts the content it suggests.

[1174] Hardware and software used

[1175] Camera: Captures the user's facial expressions using the device's built-in camera.

[1176] Microphone: Collecting user feedback.

[1177] OpenCV: Image processing library for facial expression detection and preprocessing.

[1178] Keras: A framework for sentiment analysis models.

[1179] TensorFlow: Used to retrain machine learning models.

[1180] Emotion engine: Identify the user's emotional state.

[1181] Examples of prompts with concrete examples

[1182] An example of a prompt is:

[1183] Develop a system that suggests the best movies for users who are relaxing, based on their viewing history and facial expression data. Design an algorithm that recommends content tailored to each individual user, based on their viewing history and real-time emotional data.

[1184] The above is an embodiment of the present invention. This system makes it possible to provide each customer with an optimal UI and UX in real time, taking into account their emotional data.

[1185] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1186] Step 1:

[1187] The device collects the user's facial expressions and voice using a camera and microphone. Specifically, when the user is using an e-commerce site or content distribution app, the camera captures an image of the user's face and the microphone records the user's voice. The collected data is sent to the server in real time. The input is real-time data from the camera and microphone, and the output is the collected raw data.

[1188] Step 2:

[1189] The server preprocesses the collected facial expression data using OpenCV. Specifically, it converts the image to grayscale and detects the facial area. Next, it resizes the facial area to a size that can be processed by the emotion recognition model. The input is the image data sent from the device, and the output is the resized facial area data.

[1190] Step 3:

[1191] The server analyzes the preprocessed facial data using a Keras model to identify the user's emotional state. Specifically, the resized facial image is input into a Keras emotion recognition model to predict an emotion label, such as happiness, excitement, or confusion. The input is the preprocessed facial image data, and the output is the emotion label.

[1192] Step 4:

[1193] The device collects the user's operation speed and operation history. Specifically, it records the user's operation log, such as scrolling through a web page or clicking on an item. The input is the user's operation data, and the output is the operation log.

[1194] Step 5:

[1195] The server updates the customer profile based on the collected operation logs. Specifically, it uses a machine learning model to update the customer profile in real time based on the user's past browsing history, purchase history, current operation speed, and emotional data. The input is the operation log and emotional data, and the output is the updated customer profile data.

[1196] Step 6:

[1197] When a user searches for a product on an e-commerce site, the server optimizes the search results based on the analyzed profile data and current emotional data. Specifically, it sorts the search results to display the most appropriate products at the top, taking into account the user's preferences and emotional state. The input is the user's search query and profile data, and the output is the optimized search results.

[1198] Step 7:

[1199] When a user visits a specific product detail page, the server customizes the information structure of that page. Specifically, if a user prefers high-resolution images, an image gallery may be displayed first, and if detailed technical information needs to be emphasized, it may be brought to the forefront. The input is the user's profile data and emotional data, and the output is a customized product detail page.

[1200] Step 8:

[1201] The server displays product-related recommendations to users who are viewing a particular product. Specifically, it suggests related accessories and additional products while taking into account the user's emotional state. The input is the user's profile data and current emotional data, and the output is a list of recommended products.

[1202] Step 9:

[1203] The server retrains the machine learning model with new purchasing behavior and sentiment data each time the user visits the e-commerce site or content delivery app. This continually updates the profile and provides a more personalized experience. The input is the new purchasing behavior and sentiment data, and the output is the retrained machine learning model.

[1204] 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.

[1205] 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.

[1206] 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.

[1207] [Fourth embodiment]

[1208] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1209] 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.

[1210] 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).

[1211] 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.

[1212] 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.

[1213] 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).

[1214] 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. 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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."

[1221] This invention is a system that collects and analyzes customer purchasing behavior data on e-commerce sites, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language, along with specific examples.

[1222] Data collection

[1223] When a user accesses an e-commerce site, the server automatically collects the following data: visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[1224] Data analysis

[1225] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models to analyze customer behavior patterns and preferences, identifying interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[1226] Optimizing search results

[1227] When a user searches for a product on an e-commerce site, the server refers to a pre-created customer profile to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[1228] Customizing your product detail page

[1229] When a user visits a particular product detail page, the server customizes the information structure of that page. For example, if a user prefers high-resolution images, the image gallery might be displayed first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the review section might be brought to the forefront and detailed reviews might be displayed.

[1230] Viewing Recommendations

[1231] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[1232] Continuous learning and optimization

[1233] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more personalized experience.

[1234] Specific examples

[1235] Example 1: Searching for and purchasing a smartphone

[1236] 1. A user searches for "smartphone."

[1237] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[1238] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[1239] 4. User clicks on a specific phone to view details.

[1240] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[1241] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[1242] Example 2: Purchasing a fashion item

[1243] 1. A user searches for "summer dresses."

[1244] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[1245] 3. Casual and affordable dresses will appear at the top of the search results page.

[1246] 4. Product detail pages place particular emphasis on material information and coordination examples.

[1247] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[1248] The above is an embodiment of the present invention. This system provides a UI and UX that are optimized for each customer, and is expected to improve purchase rates.

[1249] The processing flow will be explained below.

[1250] Step 1:

[1251] A user accesses an e-commerce site and enters search keywords.

[1252] Step 2:

[1253] The server automatically collects and logs users' search keywords and access information (such as visit time, IP address, and referring URL).

[1254] Step 3:

[1255] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from the database.

[1256] Step 4:

[1257] The server analyzes the collected data in real time and identifies user preferences and behavioral patterns based on machine learning models.

[1258] Step 5:

[1259] The server uses the customer profile generated from the analysis results to optimize the search results, specifically sorting products that are likely to interest the user to the top.

[1260] Step 6:

[1261] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[1262] Step 7:

[1263] When a user clicks to view a particular product detail page, the server customizes the information on that page, for example, changing the image gallery, review section, or product specifications.

[1264] Step 8:

[1265] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[1266] Step 9:

[1267] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[1268] Step 10:

[1269] When a user adds an item to their cart, the server records that information and updates the customer profile.

[1270] Step 11:

[1271] The server periodically retrains the machine learning model based on new purchasing behavior data to improve the accuracy of the profile.

[1272] These are the specific processing steps for a system that provides an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[1273] Example 1

[1274] 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."

[1275] Conventional e-commerce sites face the challenge of being unable to provide a personalized user interface (UI) or user experience (UX) based on each individual customer's purchasing behavior and preferences. Furthermore, because continuous optimization through real-time data processing and retraining of machine learning models is not performed, they are unable to quickly respond to changes in customer interests and purchasing trends. A system that can solve these problems and increase customer purchase rates is needed.

[1276] 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.

[1277] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, means for using a machine learning model to analyze customer behavior patterns and preferences, means for processing data in real time, and means for generating a profile for each customer and storing it in a database. This makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[1278] "Customer purchasing behavior data" refers to information about a customer's behavior on a website, such as the time of visit, IP address, referring URL, search keywords, ID of the viewed product, viewing time, and cart addition information.

[1279] "Analysis means" refers to the technical means for processing collected customer purchasing behavior data and identifying customer behavior patterns and preferences.

[1280] "User interface" refers to the interactive elements that customers directly touch and manipulate when searching, browsing, and purchasing products through a website.

[1281] "User experience" refers to the overall experience and feeling a customer has when using a website, including the site's structure, design, usability, and the quality of the information provided.

[1282] A "machine learning model" is an algorithm or technology that learns from collected data and enables future predictions and classifications.

[1283] A "profile" is a collection of data that includes each customer's preferences and behavioral patterns, created based on the results of analysis.

[1284] A "database" is a system that stores and manages data based on a certain structure, enabling efficient searching and updating.

[1285] "Optimization" refers to maximizing the efficiency of what is provided to customers based on collected data and analysis results, and providing the most appropriate information and context for each individual customer.

[1286] "Processing data in real time" refers to a series of processes in which collected data is analyzed immediately and the results are reflected immediately.

[1287] "Recommended information" is information that presents highly relevant products and services based on a customer's current browsing and purchasing behavior.

[1288] "Retraining" is the process of retraining an existing machine learning model using new data to improve the model's accuracy and effectiveness.

[1289] The present invention is a system that collects and analyzes customer purchasing behavior data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. Specific embodiments of the system are described below.

[1290] Data collection

[1291] When a user visits an e-commerce site, the server automatically collects the following data: time of visit, IP address, referring URL, search keywords, viewed product ID, viewing time, add-to-cart information, etc. This information is collected using web server software such as Apache or Nginx.

[1292] Data analysis

[1293] The collected purchasing behavior data is analyzed in real time. The server uses machine learning models (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences and identify interests and purchasing trends. The analysis results are stored in a relational database (e.g., MySQL or PostgreSQL) as a profile for each customer.

[1294] Optimizing search results

[1295] When a user searches for a product on an e-commerce site, the server refers to the user profile created in advance to optimize the search results. For example, if a user searches for "smartphone," and past data indicates that the user is interested in the latest models or multi-functional smartphones, those products will be displayed at the top of the results.

[1296] Customizing your product detail page

[1297] When a user visits a particular product detail page, the server customizes the page's information structure based on the user's preferences. For example, if a user prefers high-resolution images, the server might display an image gallery first, followed by expert reviews. On the other hand, if a user prioritizes reviews, the server might bring the review section to the forefront and display detailed reviews.

[1298] Viewing Recommendations

[1299] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model are recommended. This can encourage users to make purchases.

[1300] Continuous learning and optimization

[1301] Each time a user interacts with the e-commerce site, new behavioral data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more personalized experience.

[1302] Specific examples

[1303] Example 1: Searching for and purchasing a smartphone

[1304] 1. A user searches for "smartphone."

[1305] 2. The server determines from your past browsing history that you are interested in the latest high-performance smartphones.

[1306] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[1307] 4. User clicks on a specific phone to view details.

[1308] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[1309] 6. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[1310] Example 2: Purchasing a fashion item

[1311] 1. A user searches for "summer dresses."

[1312] 2. Based on past purchasing behavior and browsing history, the server determines that you are particularly interested in casual designs and low prices.

[1313] 3. Casual and affordable dresses will appear at the top of the search results page.

[1314] 4. Product detail pages place particular emphasis on material information and coordination examples.

[1315] 5. Before users add an item to their cart, they will see accessories and items that are discounted when purchased together.

[1316] This system can stimulate individual users' purchasing desire and increase the value of the EC site, which is expected to lead to increased sales and customer satisfaction.

[1317] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] A user accesses an e-commerce site.

[1320] Input: The user enters the URL of the e-commerce site using a browser.

[1321] Action: The server receives an access request.

[1322] Output: The server prepares to record the user's visit information.

[1323] Step 2:

[1324] The server collects user visit information.

[1325] Input: Access request and associated metadata (e.g., time of visit, IP address, referring URL, etc.).

[1326] How it works: The server uses web server software such as Apache or Nginx to record visit times, IP addresses, referring URLs, search keywords, viewed product IDs, viewed times, add-to-cart information, etc.

[1327] Output: The collected visit information is stored in a database.

[1328] Step 3:

[1329] The data collected by the server is analyzed using machine learning models.

[1330] Input: User purchasing behavior data collected in a database.

[1331] How it works: The server sends data to a machine learning model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and preferences.

[1332] Output: The analysis results are generated and stored in a database as a profile for each customer.

[1333] Step 4:

[1334] The user searches for a product.

[1335] Input: A user enters a product name or keyword into the search box of an e-commerce site.

[1336] Operation: A server receives a search query.

[1337] Output: The search query is prepared for analysis.

[1338] Step 5:

[1339] The server optimizes search results based on user profiles.

[1340] Input: Search query and user profile.

[1341] How it works: The server looks up your profile and sorts the search results to bring the most relevant products to the top.

[1342] Output: The optimized search results are displayed in the user's browser.

[1343] Step 6:

[1344] A user visits a specific product detail page.

[1345] Input: User clicks on a specific product from the search results.

[1346] What happens: The server retrieves the product details and renders the page.

[1347] Output: Detail page information is prepared.

[1348] Step 7:

[1349] The server customizes the product detail page based on the user's preferences.

[1350] Input: User profile and product details.

[1351] How it works: The server dynamically changes the layout and content of the page based on user preferences, highlighting high-resolution image galleries for image-focused users and highlighting reviews for review-focused users.

[1352] Output: A customized product detail page is displayed to the user.

[1353] Step 8:

[1354] The server displays related information about the product being viewed.

[1355] Input: Viewed product information and user profile.

[1356] How it works: The server collects information about related products and displays them on the page you are viewing. For example, on a smartphone detail page, it might recommend cases and screen protectors specifically for that model.

[1357] Output: Related product information is displayed to the user.

[1358] Step 9:

[1359] The server retrains the machine learning model with the new behavioral data.

[1360] Input: New purchasing behavior data.

[1361] How it works: The server retrains the machine learning model with newly collected data, improving the model's accuracy.

[1362] Output: Updated customer profile and optimization algorithm.

[1363] Through these steps, the present invention makes it possible to provide personalized services to each customer in real time, promote purchasing behavior, and improve customer satisfaction.

[1364] (Application example 1)

[1365] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1366] In online shopping, the challenge is to improve customer satisfaction by efficiently collecting customer behavior data and providing individually optimized user interfaces (UIs) and user experiences (UXs) based on that data. Furthermore, there is a need to increase purchasing motivation by analyzing customer interests and purchasing trends in real time and providing personalized recommendations.

[1367] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1368] In this invention, the server includes means for collecting customer purchasing behavior data, means for analyzing the collected purchasing behavior data, and means for automatically generating an optimal user interface and user experience for the customer based on the analysis results. This makes it possible to analyze each customer's behavior data in real time using machine learning and provide a personalized experience in conjunction with an application installed on the smart device. In addition, by optimizing the display order of search results and displaying individually optimized product detail pages and related recommended information, it is possible to simultaneously improve customer satisfaction and purchasing motivation.

[1369] "Customer purchasing behavior data" refers to data that indicates the actions that customers take on an e-commerce site, such as browsing, searching, adding to cart, and purchasing.

[1370] "Means of collection" refers to the functions of systems and software that record and store customer behavior data when accessing an e-commerce site.

[1371] "Means of analysis" refers to machine learning models and algorithms used to analyze collected customer purchasing behavior data in real time and identify customer interests and preferences.

[1372] "User interface (UI)" refers to the screen layout and operation methods that customers see when using an e-commerce site or app.

[1373] "User experience (UX)" refers to the overall sense of use and satisfaction that customers feel in the process of using an e-commerce site or app.

[1374] "Optimization measures" refers to the function of adjusting the order in which search results and pages are displayed based on data for each customer, and presenting the most appropriate content.

[1375] "Search result display order" refers to the order in which products are displayed when a customer searches for a product using keywords.

[1376] A "product detail page" refers to a web page or app screen that contains detailed information about a specific product.

[1377] "Information structure" refers to the layout and display format of information such as images, reviews, specifications, and recommended information on product detail pages.

[1378] "Applications installed on smart devices" refers to software programs installed on mobile devices such as smartphones and tablets.

[1379] "Analyzing behavioral data in real time using machine learning" refers to the process of collecting various operations performed by customers on a website or app in real time and instantly analyzing them using a machine learning model.

[1380] "Means of linking" refers to a mechanism by which applications on smart devices automatically generate and provide optimal UI and UX based on the analysis results.

[1381] "Recommended information" refers to information that suggests related products and services based on the products a customer is viewing and their past behavioral patterns.

[1382] "Continuous learning" refers to the process of retraining machine learning models based on newly collected data to improve analysis accuracy.

[1383] This invention is a system that collects and analyzes purchasing behavior data on e-commerce sites and provides customers with an optimized user interface and user experience through an application installed on a smart device. An embodiment of this system will be described in detail.

[1384] Hardware and software used

[1385] Hardware: Smartphone (iOS, Android), server

[1386] Software: Python, TensorFlow / Keras (machine learning libraries), Firebase (data collection and management)

[1387] Data collection

[1388] Customer purchasing behavior data for e-commerce sites is automatically collected in real time via Firebase, including visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information.

[1389] Data analysis

[1390] The collected data is analyzed on the server. Machine learning models are run using Python and TensorFlow / Keras to analyze each customer's behavioral patterns and preferences. The analysis results identify the customer's interests and purchasing trends and are stored as a profile in Firebase. For example, a customer identified as being interested in "beachwear" will be prioritized in the display of products in that category.

[1391] Generate optimized search results and product detail pages

[1392] When a customer searches for a product, the server optimizes the order of search results based on the profile it creates. When the user visits a product detail page, the information on that page is also customized based on the profile, displaying information tailored to the customer's preferences, such as high-resolution images or expert reviews.

[1393] Viewing Recommendations

[1394] In addition, the server recommends items related to the product being viewed. For example, if you are viewing a smartphone, cases and screen protectors for that model will be displayed, encouraging customers to make a purchase.

[1395] Continuous learning and optimization

[1396] The system continuously learns to deliver a more personalized experience. Every time a user interacts with a site or application, new behavioral data is collected and the machine learning model is retrained, ensuring customer profiles are always up-to-date and enabling further optimization.

[1397] Specific examples

[1398] Example 1: Searching for and purchasing a smartphone

[1399] When a user searches for "smartphone," the server determines from their browsing history that they are interested in the latest, high-performance smartphones. The search results page will display new products and highly rated smartphones at the top of the results. When a user visits the detail page for a specific smartphone, high-resolution images are prioritized and expert reviews are highlighted. Related accessories are also recommended.

[1400] Prompt Sentence Examples

[1401] When a user searches for "summer clothes":

[1402] "When a user searches for summer clothes, what data in particular do you collect and how do you analyze it?"

[1403] "Write a prompt recommending appropriate items for users interested in beachwear."

[1404] In this way, the system of the present invention provides users with an optimized UI and UX, increasing customer satisfaction.

[1405] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1406] Step 1:

[1407] When a user accesses an e-commerce site, the device collects purchasing behavior data such as visit time, IP address, referral URL, search keywords, viewed product ID, viewing time, and cart addition information. This data is sent to Firebase in real time. The input is user behavior data, and the output is the collected data stored in Firebase.

[1408] Step 2:

[1409] The server analyzes the purchasing behavior data stored in Firebase. It applies machine learning models using Python and TensorFlow / Keras to analyze customer behavior patterns and preferences. The machine learning models process the data using neural networks and save it as a customer profile. The input is the collected user data, and the output is the analysis results generated as a customer profile.

[1410] Step 3:

[1411] When a user searches for a product on an e-commerce site, the server references the customer profile in Firebase to optimize the search results. The input is the user's search keywords and customer profile, and the output is optimized search results that are displayed to the user. The server calculates the ranking of related products and adjusts the display order.

[1412] Step 4:

[1413] When a user visits a particular product detail page, the server customizes the information structure of that page. First, the server prioritizes displaying information tailored to the customer's interests, such as high-resolution images and a review section. The input is the customer profile and product detail page data, and the output is a customized page displayed on the user's device.

[1414] Step 5:

[1415] The server displays recommendations related to the specific product the user is viewing, for example, accessories specific to that model while browsing a smartphone. The input is the currently viewed product information and a customer profile, and the output is generated and presented to the user with recommendations for related products and accessories.

[1416] Step 6:

[1417] Every time a user interacts with the e-commerce site, the server collects new behavioral data and retrains the machine learning model, ensuring that the customer profile is always up to date. The input is the user's new behavioral data, and the output is an updated machine learning model and customer profile. This step allows for further optimization.

[1418] 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.

[1419] This invention is a system that collects and analyzes customer purchasing behavior and emotion data on e-commerce sites to automatically generate and provide a user interface (UI) and user experience (UX) optimized for each individual customer. Below, we will explain the program's processing in natural language and provide specific examples.

[1420] Data collection and emotion recognition

[1421] When a user accesses an e-commerce site and enters a search keyword, the server automatically collects the following data: visit time, IP address, referring URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. The emotion engine analyzes this data and identifies emotional states such as joy, excitement, and confusion.

[1422] Data analysis and profile generation

[1423] The collected purchasing behavior and emotional data is analyzed in real time. The server uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[1424] Optimizing search results

[1425] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[1426] Customizing your product detail page

[1427] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[1428] Viewing Recommendations

[1429] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[1430] Continuous learning and optimization

[1431] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[1432] Specific examples

[1433] Example 1: Searching for and purchasing a smartphone

[1434] 1. A user searches for "smartphone."

[1435] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[1436] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[1437] 4. User clicks on a specific phone to view details.

[1438] 5. Product detail pages highlight numerous high-resolution images first, followed by expert reviews.

[1439] 6. The emotion engine recognizes that the user is curious and displays more detailed technical information and related videos.

[1440] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[1441] Example 2: Purchasing a fashion item

[1442] 1. A user searches for "summer dresses."

[1443] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[1444] 3. Casual and affordable dresses will appear at the top of the search results page.

[1445] 4. Product detail pages place particular emphasis on material information and coordination examples.

[1446] 5. If the sentiment engine detects that the user is confused, it will highlight detailed product descriptions and reviews.

[1447] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[1448] The above is an embodiment of the present invention. This system provides a UI and UX optimized for each customer, which is expected to improve purchase rates. By combining it with an emotion engine, a more personalized experience can be provided that responds to the customer's momentary emotional state.

[1449] The processing flow will be explained below.

[1450] Step 1:

[1451] A user accesses an e-commerce site and enters search keywords.

[1452] Step 2:

[1453] The server automatically collects and logs access information such as the user's search keywords, visit time, IP address, and referring URL.

[1454] Step 3:

[1455] The server retrieves the user's past purchasing behavior data (browsing history, cart addition data, browsing time, etc.) from a database, and the emotion engine collects emotional data such as the user's facial expressions, voice, and operation speed through the device's camera, microphone, and sensors.

[1456] Step 4:

[1457] The server analyzes purchasing behavior data and emotional data in real time and uses machine learning models to identify user preferences, behavioral patterns, and emotional states.

[1458] Step 5:

[1459] The server generates optimal search results for users based on the customer profile and emotion data generated from the analysis results, specifically sorting products of interest to the top.

[1460] Step 6:

[1461] The optimized search results are sent to and displayed on the user's device, allowing the user to prioritize the products that interest them.

[1462] Step 7:

[1463] When a user clicks to view a particular product detail page, the server customizes the information structure on that page, for example displaying an image gallery first if the user prefers high-resolution images, or highlighting expert reviews.

[1464] Step 8:

[1465] Based on the user's emotional state (e.g., confused) recognized by the emotion engine, the server highlights detailed product descriptions and usage instructions.

[1466] Step 9:

[1467] The customized product detail page is sent to and displayed on the user's device, allowing the user to view the information that is of most interest to them first.

[1468] Step 10:

[1469] The server generates recommendations related to the product being viewed (e.g., related products, accessories, etc.) and displays them on the detail page.

[1470] Step 11:

[1471] The emotion engine adjusts the type and timing of recommendations based on the user's emotional state. For example, if the user is excited, it will display related products at an earlier stage, with higher prices.

[1472] Step 12:

[1473] When a user adds an item to their cart, the server records that information and updates the customer profile.

[1474] Step 13:

[1475] The server periodically retrains the machine learning model with new purchasing behavior and sentiment data to improve the accuracy of the profiles.

[1476] These are the specific processing steps of a system that combines an emotion engine to provide an optimized UI and UX for each individual customer. This series of processes allows users to enjoy the shopping experience that best suits them, and is expected to increase their purchase rate.

[1477] Example 2

[1478] 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."

[1479] Conventional e-commerce sites typically attempt to optimize the user experience by using only customer purchasing behavior data. However, this makes it difficult to achieve detailed personalization based on the customer's emotional state, and further improvements in purchase rates cannot be expected. The purpose of this invention is to solve this problem and achieve even more accurate personalization by utilizing each customer's emotional data.

[1480] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting customer purchasing behavior data, means for collecting customer emotion data, means for analyzing the collected purchasing behavior data and emotion data, means for generating and updating a customer profile based on the analysis results, means for automatically generating an optimal user interface and user experience for the customer, and means for providing an optimal user interface and user experience for the customer. This enables personalization that takes into account the emotional state of the customer, making it possible to improve the purchase rate.

[1481] "Customer" refers to a user who uses an e-commerce site to search for, browse, and purchase products and services.

[1482] "Purchasing behavior data" refers to the behavioral history of customers on e-commerce sites, such as search keywords, viewed product IDs, viewing times, and cart addition information.

[1483] "Emotion data" is data that expresses the emotional state of the customer, obtained from facial expressions, voice, operation speed, etc.

[1484] "Analysis" is the process of identifying customer preferences, behavioral patterns, and emotional states based on collected data.

[1485] A "profile" is data that compiles information such as each customer's preferences, behavioral patterns, and emotional state.

[1486] A "user interface" refers to the screen layout and operational elements that customers interact with visually and operationally when using an e-commerce site.

[1487] "User experience" is a concept that refers to the overall satisfaction and usability that customers feel when using an e-commerce site.

[1488] "Optimization" is the process of adjusting search results, product detail pages, and even recommendations based on each customer's individual profile.

[1489] "Automatic generation" refers to the operation in which the system performs settings and output based on specific conditions and data without human intervention.

[1490] "Recommendations" are additional suggestions or information displayed related to the product or service a customer is viewing.

[1491] A "machine learning model" is a collection of algorithms used to predict or classify specific outcomes based on data.

[1492] MODE FOR CARRYING OUT THE INVENTION

[1493] This invention is a system that collects and analyzes customer purchasing behavior data and emotion data on an e-commerce site, automatically generating and providing a user interface (UI) and user experience (UX) optimized for each individual customer. A specific embodiment of this system is described below.

[1494] Data collection and emotion recognition

[1495] A user accesses an e-commerce site and enters a search keyword. At this point, the server automatically collects purchasing behavior data, such as the visit time, IP address, referrer URL, search keyword, viewed product ID, viewing time, and cart addition information. Furthermore, the server uses the device's built-in camera, microphone, and sensors to collect real-time emotional data, such as the user's facial expression, voice, and operation speed. This data is analyzed by an emotion engine to identify the user's emotional state, such as joy, excitement, or confusion.

[1496] Data analysis and profile generation

[1497] The collected purchasing behavior and emotional data is analyzed in real time by a server. The server uses machine learning models, such as generative AI models, to perform detailed analysis of customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[1498] Optimizing search results

[1499] When a user searches for a product on an e-commerce site, the server compares pre-generated customer profiles with real-time emotional data to optimize search results. For example, if a user searches for "smartphone," the server will display the latest models and feature-rich smartphones at the top of the results based on past data and the user's current emotional state.

[1500] Customizing your product detail page

[1501] When a user visits a particular product detail page, the server customizes the information on that page. For example, if a user prefers high-resolution images, the product detail page might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, detailed product descriptions and usage instructions might be highlighted.

[1502] Viewing Recommendations

[1503] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state.

[1504] Continuous learning and optimization

[1505] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model. This process continually updates customer profiles, providing an even more accurate and personalized experience.

[1506] Adding specific examples

[1507] Example 1: Searching for and purchasing a smartphone

[1508] 1. A user searches for "smartphone."

[1509] 2. The server determines that the user is interested in the latest high-performance smartphone based on their past browsing history and current emotional state (e.g., excitement).

[1510] 3. New products and highly rated smartphones will be displayed at the top of the search results page.

[1511] 4. User clicks on a specific phone to view details.

[1512] 5. Product detail pages highlight high-resolution images first, followed by expert reviews.

[1513] 6. The emotion engine recognizes that the user is curious and displays detailed technical information and related videos.

[1514] 7. Related accessories (cases and screen protectors) are recommended before users add the product to their cart.

[1515] Example 2: Purchasing a fashion item

[1516] 1. A user searches for "summer dresses."

[1517] 2. The server determines from past purchasing behavior and emotional data (e.g., confusion) that you are particularly interested in casual designs and low prices.

[1518] 3. Casual and affordable dresses will appear at the top of the search results page.

[1519] 4. Product detail pages place particular emphasis on material information and coordination examples.

[1520] 5. If the emotion engine detects that the user is confused, detailed product descriptions and reviews will be highlighted.

[1521] 6. Before users add an item to their cart, they are shown accessories and items that are discounted when purchased together.

[1522] The system of the present invention provides a user interface and user experience that is optimized for each individual customer, which is expected to increase purchase rates. By combining it with an emotion engine, a more personalized experience that responds to the customer's momentary emotional state becomes possible.

[1523] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1524] Step 1: Collecting user access and sentiment data

[1525] A user accesses an e-commerce site and enters search keywords. The device records purchasing behavior data such as visit time, IP address, referrer URL, search keywords, viewed product ID, viewing time, and cart addition information, and sends this data to the server. At the same time, the device's built-in camera, microphone, and sensors are used to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. This data is collected to identify the user's emotional state. The input is the user's behavior and the data sensed by the device, and the output is a set of these data.

[1526] Step 2: Temporary storage and initial analysis of data

[1527] The server temporarily stores the collected access data and emotion data in a database. It then performs initial analysis, checks data consistency, and fills in missing values. Specifically, it performs anomaly detection, statistical analysis, and necessary preprocessing on the collected data. The input is the collected raw data, and the output is preprocessed data.

[1528] Step 3: Analyze purchasing behavior and sentiment using machine learning models

[1529] The server analyzes the collected purchasing behavior and emotional data using a pre-built generative AI model. The model analyzes users' preferences, behavioral patterns, and emotional states to identify their interests and purchasing tendencies. Specific operations include data preprocessing, feature extraction, model input, and obtaining prediction results. The input is the preprocessed data, and the output is the analysis results.

[1530] Step 4: Generate and update customer profiles

[1531] Based on the analysis results, the server generates a profile for each individual user and stores or updates it in a database. The profile includes the user's preferences, behavioral patterns, emotional state, etc. Specifically, this involves organizing and storing the analysis results, merging them with existing data, and updating the profile as needed. The input is the analysis results, and the output is an updated customer profile.

[1532] Step 5: Optimize search results

[1533] When a user searches for a product, the server matches the pre-generated customer profile with real-time emotional data to optimize the search results. For example, if a user searches for "smartphone," the most suitable products will be displayed at the top based on past data and current emotional state. Specifically, this includes calculating the degree of match between the profile data and the search query, setting priorities, and adjusting the display order of the search results. The input is the search query and customer profile, and the output is an optimized list of search results.

[1534] Step 6: Customize your product detail page

[1535] When a user visits a specific product detail page, the server customizes the information on that page. For example, if the user prefers high-resolution images, an image gallery might be displayed first, followed by expert reviews. On the other hand, if the emotion engine determines that the user is confused, a detailed description of the product and its usage might be highlighted. The input is a customer profile and real-time emotion data; the output is a customized product detail page.

[1536] Step 7: View recommendations

[1537] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. Furthermore, the type and timing of recommended information are dynamically adjusted according to the user's emotional state. The input is information about the product being viewed, a customer profile, and emotional data, and the output is dynamically generated recommended information.

[1538] Step 8: Continuous learning and optimization

[1539] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected, and the server retrains the machine learning model based on this data. This continuously updates the customer profile, providing an even more accurate and personalized experience. Specifically, this involves preparing new data, retraining the model, and regenerating the profile. The input is the latest purchasing behavior and sentiment data, and the output is an updated machine learning model and customer profile.

[1540] (Application example 2)

[1541] 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."

[1542] Modern e-commerce sites and content distribution services are required to provide a user interface (UI) and user experience (UX) that is optimized for each individual customer. However, current systems have difficulty effectively utilizing customer emotional data to generate the optimal UI and UX in real time according to the situation. As a result, there is an issue that customer satisfaction, purchase rates, and viewer ratings are not being improved as effectively as expected.

[1543] 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 customer purchasing behavior data, means for analyzing the collected purchasing behavior data and emotional data, means for automatically generating an optimal user interface and user experience for the customer based on the analysis results, means for providing the optimal user interface and user experience for the customer, and means for collecting user viewing behavior data and emotional data and recommending optimal content for the content distribution service based on the data. This solves the problems faced by conventional systems and makes it possible to provide each customer with an optimal UI and UX in real time, taking emotional data into consideration.

[1544] "Customer purchasing behavior data" refers to information about customer behavior history and transaction history on e-commerce sites.

[1545] "Emotion data" is data that identifies the emotional state of a customer extracted from their facial expressions, voice, operation speed, etc.

[1546] "User interface" refers to the entire interface that customers come into visual and operational contact with when using an e-commerce site or content distribution service.

[1547] "User experience" refers to the overall experience and evaluation that customers have when using an e-commerce site or content distribution service.

[1548] "Means for collection" refers to systems and devices for acquiring customer purchasing behavior data and emotional data.

[1549] "Means of analysis" refers to systems or devices that analyze collected data using machine learning models, etc., to reveal customer preferences and behavioral patterns.

[1550] "Automatic generation means" refers to a system or device that automatically designs and configures a user interface and user experience based on the analysis results.

[1551] "Providing means" refers to a system or device that displays or provides the generated user interface and user experience to a customer.

[1552] "Viewing behavior data" refers to information relating to the history, duration, and frequency of viewing of content viewed by a user in a content distribution service.

[1553] "Recommendation means" refers to a system or device that automatically selects optimal content based on analyzed data and suggests it to users.

[1554] This invention is a system for collecting and analyzing customer purchasing behavior data and emotion data on e-commerce sites and content distribution services, and automatically generating and providing a UI (user interface) and UX (user experience) optimized for each individual customer. Specific embodiments for implementing this invention are described below.

[1555] Data collection and emotion recognition

[1556] The device uses the camera, microphone, and sensors on the user's smartphone or computer to collect emotional data in real time, such as the user's facial expressions, voice, and operation speed. Purchasing behavior data, such as visit time, IP address, referring URL, search keywords, viewed product ID, viewing time, and cart addition information, is also collected at the same time. An emotion engine is used to analyze this data and identify emotional states such as joy, excitement, and confusion.

[1557] Data analysis and profile generation

[1558] The server analyzes the collected purchasing behavior and emotional data in real time. It uses machine learning models to analyze customer preferences, behavioral patterns, and emotional states to identify interests and purchasing trends. The analysis results are stored in a database as individual customer profiles.

[1559] Optimizing search results

[1560] When a user searches for a product on an e-commerce site, the server references pre-generated customer profiles and emotional data to optimize search results. For example, if a user searches for "smartphone," and past data and current emotional state indicate that the user is interested in the latest models and feature-rich smartphones, those products will be displayed at the top of the results.

[1561] Customizing your product detail page

[1562] When a user visits a particular product detail page, the server customizes the information structure on that page. For example, if the user prefers high-resolution images, the server might highlight an image gallery first, followed by expert reviews. On the other hand, if the emotion engine determines the user is confused, the server might highlight a detailed description of the product and how to use it.

[1563] Viewing Recommendations

[1564] The server displays recommended information related to a specific product to a user who is viewing that product. For example, on a smartphone detail page, cases and screen protectors specifically for that model might be recommended. The type and timing of recommended information are also adjusted according to the user's emotional state.

[1565] Continuous learning and optimization

[1566] Each time a user visits the e-commerce site, new purchasing behavior and sentiment data is collected and used by the server to retrain the machine learning model, continually updating the customer profile and delivering an even more accurate and personalized experience.

[1567] Specific example of content distribution service

[1568] When a user opens a content distribution app, the server identifies videos or movies the user might want to watch based on their past viewing history and current emotional state (e.g., relaxed). The app's home screen displays movies and TV shows that match the user's mood and preferences at the time, and when the user clicks on a specific movie or TV show, the details page displays interesting trailers and cast information. The emotion engine monitors the user's reactions and adjusts the content it suggests.

[1569] Hardware and software used

[1570] Camera: Captures the user's facial expressions using the device's built-in camera.

[1571] Microphone: Collecting user feedback.

[1572] OpenCV: Image processing library for facial expression detection and preprocessing.

[1573] Keras: A framework for sentiment analysis models.

[1574] TensorFlow: Used to retrain machine learning models.

[1575] Emotion engine: Identify the user's emotional state.

[1576] Examples of prompts with concrete examples

[1577] An example of a prompt is:

[1578] Develop a system that suggests the best movies for users who are relaxing, based on their viewing history and facial expression data. Design an algorithm that recommends content tailored to each individual user, based on their viewing history and real-time emotional data.

[1579] The above is an embodiment of the present invention. This system makes it possible to provide each customer with an optimal UI and UX in real time, taking into account their emotional data.

[1580] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1581] Step 1:

[1582] The device collects the user's facial expressions and voice using a camera and microphone. Specifically, when the user is using an e-commerce site or content distribution app, the camera captures an image of the user's face and the microphone records the user's voice. The collected data is sent to the server in real time. The input is real-time data from the camera and microphone, and the output is the collected raw data.

[1583] Step 2:

[1584] The server preprocesses the collected facial expression data using OpenCV. Specifically, it converts the image to grayscale and detects the facial area. Next, it resizes the facial area to a size that can be processed by the emotion recognition model. The input is the image data sent from the device, and the output is the resized facial area data.

[1585] Step 3:

[1586] The server analyzes the preprocessed facial data using a Keras model to identify the user's emotional state. Specifically, the resized facial image is input into a Keras emotion recognition model to predict an emotion label, such as happiness, excitement, or confusion. The input is the preprocessed facial image data, and the output is the emotion label.

[1587] Step 4:

[1588] The device collects the user's operation speed and operation history. Specifically, it records the user's operation log, such as scrolling through a web page or clicking on an item. The input is the user's operation data, and the output is the operation log.

[1589] Step 5:

[1590] The server updates the customer profile based on the collected operation logs. Specifically, it uses a machine learning model to update the customer profile in real time based on the user's past browsing history, purchase history, current operation speed, and emotional data. The input is the operation log and emotional data, and the output is the updated customer profile data.

[1591] Step 6:

[1592] When a user searches for a product on an e-commerce site, the server optimizes the search results based on the analyzed profile data and current emotional data. Specifically, it sorts the search results to display the most appropriate products at the top, taking into account the user's preferences and emotional state. The input is the user's search query and profile data, and the output is the optimized search results.

[1593] Step 7:

[1594] When a user visits a specific product detail page, the server customizes the information structure of that page. Specifically, if a user prefers high-resolution images, an image gallery may be displayed first, and if detailed technical information needs to be emphasized, it may be brought to the forefront. The input is the user's profile data and emotional data, and the output is a customized product detail page.

[1595] Step 8:

[1596] The server displays product-related recommendations to users who are viewing a particular product. Specifically, it suggests related accessories and additional products while taking into account the user's emotional state. The input is the user's profile data and current emotional data, and the output is a list of recommended products.

[1597] Step 9:

[1598] The server retrains the machine learning model with new purchasing behavior and sentiment data each time the user visits the e-commerce site or content delivery app. This continually updates the profile and provides a more personalized experience. The input is the new purchasing behavior and sentiment data, and the output is the retrained machine learning model.

[1599] 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.

[1600] 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.

[1601] 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 robot 414.

[1602] 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.

[1603] FIG. 9 is a diagram illustrating 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 actions 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.

[1604] 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.

[1605] 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).

[1606] 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.

[1607] 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."

[1608] 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.

[1609] 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).

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] The following is further disclosed regarding the above embodiment.

[1621] (Claim 1)

[1622] A means of collecting customer purchasing behavior data;

[1623] A means of analyzing the collected purchasing behavior data;

[1624] A means for automatically generating an optimal user interface and user experience for customers based on the analysis results;

[1625] A means of providing customers with an optimal user interface and user experience;

[1626] A system including:

[1627] (Claim 2)

[1628] 10. The system of claim 1, further comprising means for optimizing the display order of search results for each customer.

[1629] (Claim 3)

[1630] 10. The system of claim 1, further comprising means for customizing the information configuration of the product detail page for each customer.

[1631] (Claim 4)

[1632] 10. The system of claim 1, further comprising: means for displaying recommendations to the customer.

[1633] (Claim 5)

[1634] 10. The system of claim 1, further comprising means for generating and updating customer profiles using machine learning models.

[1635] "Example 1"

[1636] (Claim 1)

[1637] A means of collecting customer purchasing behavior data;

[1638] A means of analyzing the collected purchasing behavior data;

[1639] A means for automatically generating an optimal user interface and user experience for customers based on the analysis results;

[1640] A means of providing customers with an optimal user interface and user experience;

[1641] Using machine learning models to analyze customer behavior patterns and preferences;

[1642] a means for processing the data in real time;

[1643] A means for generating and storing a profile for each customer in a database;

[1644] A system including:

[1645] (Claim 2)

[1646] 10. The system of claim 1, further comprising means for optimizing the display order of search results for each customer.

[1647] (Claim 3)

[1648] 10. The system of claim 1, further comprising means for customizing the information configuration of the product detail page for each customer.

[1649] (Claim 4)

[1650] 10. The system of claim 1, further comprising means for recommending related products based on customer interests and purchasing trends.

[1651] (Claim 5)

[1652] 10. The system of claim 1, further comprising means for retraining the machine learning model with the collected new behavioral data.

[1653] "Application Example 1"

[1654] (Claim 1)

[1655] A means of collecting customer purchasing behavior data;

[1656] A means of analyzing the collected purchasing behavior data;

[1657] A means for automatically generating an optimal user interface and user experience for customers based on the analysis results;

[1658] A means of providing customers with an optimal user interface and user experience;

[1659] A means for linking with an application installed on a smart device;

[1660] A means of analyzing customer behavior data in real time using machine learning,

[1661] A system including:

[1662] (Claim 2)

[1663] 10. The system of claim 1, further comprising means for optimizing the order of search results for each customer and displaying recommendations.

[1664] (Claim 3)

[1665] 10. The system of claim 1, further comprising means for customizing the information configuration of the product detail page for each customer and for continuous learning and optimization.

[1666] "Example 2: Combining Emotion Engines"

[1667] (Claim 1)

[1668] A means of collecting customer purchasing behavior data;

[1669] a means of collecting customer sentiment data;

[1670] A means for analyzing the collected purchasing behavior data and emotion data;

[1671] means for generating and updating customer profiles based on the analysis results;

[1672] A means for automatically generating an optimal user interface and user experience for a customer;

[1673] A means of providing customers with an optimal user interface and user experience;

[1674] A system including:

[1675] (Claim 2)

[1676] 10. The system of claim 1, further comprising means for optimizing the display order of search results for each customer.

[1677] (Claim 3)

[1678] 10. The system of claim 1, further comprising means for customizing the information configuration of the product detail page for each customer.

[1679] (Claim 4)

[1680] 10. The system of claim 1, further comprising: means for displaying recommended information to the customer according to the customer's emotional state.

[1681] (Claim 5)

[1682] 10. The system of claim 1, further comprising: means for updating the machine learning model based on the collected purchasing behavior data and sentiment data.

[1683] "Application example 2 when combining emotion engines"

[1684] (Claim 1)

[1685] A means of collecting customer purchasing behavior data;

[1686] A means for analyzing the collected purchasing behavior data and emotion data;

[1687] A means for automatically generating an optimal user interface and user experience for customers based on the analysis results;

[1688] A means of providing customers with an optimal user interface and user experience;

[1689] A means for collecting user viewing behavior data and emotion data and recommending optimal content in a content distribution service based on the collected data;

[1690] A system including:

[1691] (Claim 2)

[1692] 10. The system of claim 1, further comprising means for optimizing the display order of search results for each customer.

[1693] (Claim 3)

[1694] 10. The system of claim 1, further comprising means for customizing the information configuration of the product detail page for each customer. [Explanation of symbols]

[1695] 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 customer purchasing behavior data; A means of analyzing the collected purchasing behavior data; A means for automatically generating an optimal user interface and user experience for customers based on the analysis results; A means of providing customers with an optimal user interface and user experience; A system including:

2. The system of claim 1 , further comprising means for optimizing the display order of search results for each customer.

3. The system of claim 1 , further comprising means for customizing the information configuration of the product detail page for each customer.

4. The system of claim 1 further comprising means for displaying recommendations to the customer.

5. The system of claim 1 , further comprising means for generating and updating customer profiles using machine learning models.

Images