system

Abstract

We provide the system. [Solution] A means for obtaining the customer's past transaction history and preference data, A means of analyzing acquired data and recommending the most suitable products based on customer preferences, A means of comparing information from multiple e-commerce sites and providing more advantageous product information, A method for automatically adjusting the price of products based on acquired sales promotion information, A means of notifying customers of recommended product information on their devices, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern e-commerce, various product information is flooding, making it difficult for customers to quickly find the optimal products that suit their preferences. Furthermore, for customers, the effort required to select the most advantageous products is increasing, such as price fluctuations, information acquisition from multiple EC sites, and coupon applications. Also, there is a problem that general recommendation functions lack proposals that fully consider customers' detailed preferences.

Means for Solving the Problems

[0005] This invention provides a system that automatically recommends the most suitable products to customers by acquiring and analyzing their past transaction history and preference data. Specifically, it includes means for comparing product information provided from multiple e-commerce sites to identify advantageous products, and means for automatically adjusting product prices based on sales promotion information. Furthermore, recommended product information is notified to the customer's terminal, and the system improves the accuracy of future recommendations by accumulating customer interaction information, while also having the ability to analyze trend information in real time and identify new products.

[0006] A "customer" refers to an individual or organization that purchases a particular product or service.

[0007] "Transaction history" refers to records of purchases and service usage that a customer has made in the past.

[0008] "Preference data" refers to information about the preferences and interests that customers show towards specific categories or brands.

[0009] "Analysis" refers to the process of understanding patterns and trends using statistical and mathematical methods based on collected data.

[0010] "Merchandise" refers to the general term for the products that are sold.

[0011] "Recommendation" refers to presenting options that are deemed appropriate based on specific conditions.

[0012] An "e-commerce site" refers to a website that provides goods and services via the internet.

[0013] "Information" as a "profitable commodity" refers to a product that is judged to be beneficial to the customer from the perspective of price, quality, etc.

[0014] "Acquisition" refers to gathering and obtaining necessary data or information.

[0015] "Notification" refers to the act of transmitting important information or messages to the recipient.

[0016] "Dialogue information" refers to information including opinions and feedback obtained through communication with customers.

[0017] "Popularity information" refers to information indicating current market trends and popularity trends.

[0018] "Analysis" refers to the act of analyzing data by statistical methods and other means to extract hidden patterns and significant information.

[0019] "Identification" refers to clearly identifying based on certain criteria.

Brief Description of Drawings

[0020] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10]Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0024] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] This invention provides an AI-powered personal shopping assistant system to improve the customer purchasing experience in the field of e-commerce. The roles of the server, terminal, and user are described in the implementation of this system.

[0042] Server Role

[0043] The server plays a central role in the system, handling all data processing and analysis. First, it retrieves customers' past transaction history, preference data, and browsing history from the database. Based on this data, it uses AI algorithms to build customer profiles and analyze individual preferences and past purchase patterns. Furthermore, the server collects real-time trend information from the internet and analyzes this information to identify recommended products.

[0044] The server also utilizes APIs from multiple e-commerce sites to collect price and inventory information for identified products. This allows it to automatically identify the most advantageous pricing for customers. It retrieves promotional information and coupons from its database and adjusts prices to ensure the best possible deal.

[0045] Terminal role

[0046] The terminal's role is to present recommended product information sent from the server to the user. The terminal's interface is interactive, displaying detailed information such as product descriptions, pricing, and coupon application status. The terminal also sends user feedback and conversational information to the server, which is used to improve the accuracy of future recommendations.

[0047] It features a notification function, allowing users to set up notifications to receive alerts under specific conditions. For example, users can receive notifications when the price of a particular product drops or when a new campaign starts.

[0048] User roles

[0049] Users access the system daily through their devices. They can view recommended products and access detailed information on their devices. Users make the final decision on whether to purchase the recommended products and complete their orders through the platform.

[0050] For example, if a user has frequently purchased outdoor equipment in the past, the server can use that data to notify the user's device of new product releases and sales information on related items, helping the user enjoy a more advantageous shopping experience. In this way, the system of the present invention can make customer purchasing behavior more efficient and satisfying.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] The server retrieves customers' past transaction history, preference data, and browsing history from a database. In addition, it collects the latest trend information from social media and news sites on the internet.

[0054] Step 2:

[0055] The server analyzes the acquired data using AI algorithms to build a customer preference profile. This profile includes the customer's preferred brands, product categories, price range, and purchase frequency.

[0056] Step 3:

[0057] The server identifies the most suitable recommended products for the customer based on the established preference profile. It also analyzes trend information collected during this process to select the most relevant products.

[0058] Step 4:

[0059] The server collects information on identified products from multiple e-commerce sites and compares prices and inventory information. This allows it to list products that are advantageous to the customer.

[0060] Step 5:

[0061] The server checks promotional information and coupons, automatically applies them to the most suitable products, and adjusts prices accordingly. Based on these adjustments, it ultimately determines the product list to present to the customer.

[0062] Step 6:

[0063] The server sends the final list of recommended products to the terminal. The terminal displays the received information to the user and provides product descriptions and pricing information through its interface.

[0064] Step 7:

[0065] Users can view recommended products displayed on their device and access detailed information. If a user is interested in a product, they can proceed directly to the purchase page.

[0066] Step 8:

[0067] User feedback and purchase history are sent to the server via the device. The server uses this information to learn how to improve the accuracy of future recommendations.

[0068] Step 9:

[0069] The device notifies users of price changes and new promotional information for specific products based on real-time notification settings. This feature allows users to always stay up-to-date.

[0070] (Example 1)

[0071] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0072] In modern e-commerce, there is a demand for product recommendations tailored to individual customer preferences. However, existing systems have not been able to adequately achieve highly accurate personalized recommendations and have struggled to respond to real-time price strategies and demand changes. Therefore, the challenge is to provide customers with a more personalized, timely, and optimal purchasing experience.

[0073] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0074] In this invention, the server includes means for obtaining a customer's past transaction history, preference data, and browsing history from a database; means for constructing an individual customer profile using a generative AI model based on the obtained data; and means for analyzing trend information obtained from multiple data sources in real time to identify new products suitable for the customer. This makes it possible to provide personalized product recommendations for each customer and to provide optimal product information in response to ever-changing consumer trends.

[0075] A "database" is a digital store that systematically organizes information so that it can be efficiently accessed and managed later.

[0076] A "generative AI model" is an algorithm that uses artificial intelligence to learn patterns from large amounts of data and makes predictions and decisions based on new data.

[0077] A "profile" is a collection of detailed information about an individual customer, including their preferences and behavioral patterns, which enables personalized product recommendations.

[0078] "Trend information" refers to information about the trends of products and services that are gaining popularity at a particular time, and is used to identify new products that will attract customer interest.

[0079] An "API" is an interface for exchanging information and functions between different software programs, and a means of integrating with third-party services.

[0080] "GUI" is an abbreviation for Graphical User Interface, which is a user interface that can be operated intuitively using visual elements.

[0081] "Feedback" refers to the opinions and reactions provided by users after they have used a product, and it serves as a valuable source of information for improving the system.

[0082] "Real-time" means that a computer system has the ability to react instantly and process data without time delay.

[0083] The system in this invention provides an optimal purchasing experience in e-commerce through the mutual cooperation of a server, terminal, and user. Specific embodiments will be described below.

[0084] The server plays a central role in the system, efficiently retrieving customers' past transaction history, preference data, and browsing history from the database. This involves using a database management system and methods such as SQL queries to aggregate the desired data. The retrieved data is then used to build and refine individual customer profiles using a generation AI model, enabling the provision of products tailored to individual preferences and behavioral patterns.

[0085] Furthermore, the server collects trend information in real time via the internet. This trend information is continuously obtained using scraping technology to grasp the latest trends, and by analyzing it, new products in the market are identified. Another important function is the ability to obtain and compare product prices and inventory information in real time using APIs from online marketplaces.

[0086] The terminals that present products to users visually display recommended product information from the server. GUI technology is used to provide an intuitive interface for customers. For example, sending notifications when prices drop can further pique user interest.

[0087] Users utilize the system daily through their devices to select products, provide feedback, and make purchase decisions. This feedback is sent to the server and used to improve the accuracy of future recommendations by the generated AI model.

[0088] Thus, the system of the present invention is designed to make customer purchasing behavior more efficient and fulfilling, with servers and terminals functioning harmoniously in providing information and understanding customer needs.

[0089] Example of a prompt:

[0090] "Recommend new products related to items that customers have frequently purchased in the past. Use an AI algorithm that considers the latest trends and pricing information to suggest the best products for each customer."

[0091] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0092] Step 1:

[0093] The server retrieves the customer's past transaction history, preference data, and browsing history from the database. It uses SQL queries to search for the necessary data and temporarily loads it into data processing memory. The retrieved data is used as input to a generative AI model. The output at this stage is the input dataset for creating customer profiles.

[0094] Step 2:

[0095] The server uses a generated AI model to construct customer profiles based on the data acquired in Step 1. Specifically, it analyzes the data using machine learning algorithms to reveal customer preferences and purchasing patterns. As output, a detailed profile for each customer is generated and used as the basis data for the next analysis step.

[0096] Step 3:

[0097] The server analyzes real-time trend information obtained from the internet and uses it to recommend products based on customer profiles. By collecting data using scraping techniques and analyzing its contents, it identifies trending products suitable for each customer. The output of this step is a personalized list of recommended products.

[0098] Step 4:

[0099] The server collects price and inventory information for products from online marketplaces via an API. This collected data is analyzed by a real-time price comparison algorithm and processed to enable customers to make advantageous product selections. The output is a list containing the best prices and inventory information for recommended products.

[0100] Step 5:

[0101] The terminal displays recommended product information received from the server on its user interface. GUI technology is used to present the product information in a way that users can intuitively understand. For example, notification features are used to communicate price changes and campaign information to the user in a way that encourages purchase decisions. The output is a simple and easy-to-understand product display screen for the user.

[0102] Step 6:

[0103] Through the steps described above, the user reviews the products displayed on their device and provides feedback. The device sends this feedback to the server, which is used to train the generating AI model. This improves the accuracy of future recommendations. As output, the collected feedback data is stored on the server.

[0104] Step 7:

[0105] The user selects recommended products and completes the purchase process through the terminal. The server securely performs the necessary payment processing using security protocols based on the entered order information. The output is a confirmation and completion message from the user.

[0106] (Application Example 1)

[0107] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0108] In e-commerce, there is a growing need to provide customers with a more personalized shopping experience and increase their purchasing intent. Furthermore, the information overload in the market makes it difficult to select the optimal product, creating a need for systems that can provide customers with an efficient and satisfying shopping experience.

[0109] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0110] In this invention, the server includes means for acquiring customer transaction history and preference information, means for analyzing the acquired information to build a customer profile and recommend products based on preferences, means for referencing information from multiple e-commerce platforms to present more profitable product information, means for automatically adjusting product prices based on sales promotion information, means for notifying the user's terminal of the recommended product information, and means for analyzing trends acquired in real time to identify new products that will attract customer interest. This makes it possible to provide customers with the most suitable products in a timely manner and to personalize and streamline the purchasing experience.

[0111] "Customer transaction history" refers to records of products a user has purchased in the past, and by analyzing this data, it is used to understand purchasing trends.

[0112] "Preference information" refers to data about customers' preferences and interests, and is used to recommend products that are suitable for each customer.

[0113] An "e-commerce platform" is an online system used to buy and sell goods and services over the internet.

[0114] "Methods for recommending products" refer to technologies that suggest the most suitable products to users based on their preferences and past purchase history.

[0115] "Sales promotion information" refers to information about promotions that increase customer purchasing intent, such as coupons and discounts.

[0116] "Methods for automatically adjusting prices" refer to systems that automatically change the price of a product based on sales promotion information and market trends.

[0117] "Means of notifying the device" refers to messaging functions for providing information to customers in real time.

[0118] "Methods for analyzing trends" refer to technologies that analyze market and consumer trends in real time and provide customers with new information based on this analysis.

[0119] To realize this system, the server, terminals, and users must cooperate and fulfill their respective roles. The server first retrieves customer transaction history and preference information from a database and analyzes it using an AI algorithm. This analysis makes it possible to build customer profiles and recommend products based on preferences. Furthermore, the server collects information from multiple e-commerce platforms to form the basis for providing optimal product information.

[0120] Next, the server sends recommended product information to the terminal. The terminal presents this information to the user and collects user feedback using an interactive interface. The feedback information is sent to the server and used to improve the accuracy of product recommendations in the future. The terminal also has the function of notifying the user of price changes and promotion information in real time.

[0121] The server analyzes trend information in real time and uses this to identify new products that will attract customer interest. Data analysis tools and AI models are used in this analysis to provide customers with the latest and most useful information. Specifically, cloud computing technology (such as AWS®) is used as hardware, and MySQL® is used for database management. AI algorithms such as TENSORFLOW® and scikit-learn are utilized.

[0122] For example, if a user has previously purchased sports-related products, the server uses that data to send push notifications to their device about newly released sports equipment and ongoing campaigns. This allows users to efficiently receive more accurate product information, thereby promoting purchasing behavior. Prompts such as, "Based on the user's purchase history and current trends, please recommend the three most relevant products," are supplied to the generating AI model, enabling personalized product recommendations.

[0123] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0124] Step 1:

[0125] The server retrieves customer transaction history and preference information from a database. It receives a user ID as input and extracts historical transaction data and preference patterns associated with this ID. As output, it generates a set of customer transaction history and preference data. This data is retrieved using a database management system (such as MySQL).

[0126] Step 2:

[0127] The server analyzes acquired transaction history and preference information to build customer profiles. It receives transaction history and preference data as input and performs analysis using an AI algorithm (TensorFlow or scikit-learn). The output is profile data that shows the customer's interests and tendencies. This profile is used for personalized product recommendations.

[0128] Step 3:

[0129] The server collects product information from multiple e-commerce platforms. It queries each platform using API keys and authentication information as input. The output is a list of product information for each platform. This forms the basis for the product information presented to the user.

[0130] Step 4:

[0131] The server recommends personalized products based on customer profiles and collected product information. Using customer profiles and product information as input, the AI ​​model generates prompts (e.g., "Recommend the three most relevant products based on the user's purchase history and current trends."). The output is a list of recommended products tailored to the user.

[0132] Step 5:

[0133] The server sends the generated recommendation list to the terminal, and the terminal notifies the user. The server receives the recommendation list as input and communicates the information to the user in real time through the terminal's notification function. The output provides the user with information on recommended products. The user can then consider purchasing based on this information.

[0134] Step 6:

[0135] Users view detailed information through their device and enter purchase feedback. The device receives user feedback and dialogue information as input and sends it to the server. The output is feedback data, which is used to improve the accuracy of product recommendations for future purchases.

[0136] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0137] This invention relates to a personal shopping assistant system that integrates a customer emotion recognition system to improve the purchasing experience in e-commerce. The roles of four parties—server, terminal, user, and emotion engine—are described in the implementation of this system.

[0138] Server Role

[0139] The server retrieves customer purchase history, preference data, and browsing history from a database. In addition, it collects and analyzes the latest trend information from various sources on the internet. Using AI algorithms, it builds customer profiles based on the acquired data. Furthermore, it processes data received from the emotion engine to understand the customer's emotional state.

[0140] Specifically, the server adjusts product recommendations based on the output of the emotion engine. This adjustment includes factors such as price, brand, and category, and has the function to optimize suggestions according to the customer's emotions.

[0141] The role of the emotional engine

[0142] The emotion engine acquires data such as the user's facial expressions, voice tone, and input timing on the device to determine the user's current emotional state. These emotions are identified in various forms, such as stress, excitement, and interest, and transmitted to the server in real time. The emotion engine also analyzes past emotional patterns to understand the customer's long-term emotional trends, thereby improving the accuracy of future recommendations.

[0143] Terminal role

[0144] The device displays a list of recommended products sent from the server. In doing so, the device also takes into account the output of the emotion engine, providing an optimal interface display tailored to the user's emotional state. For example, if the user is relaxed, it might display bolder recommendations.

[0145] The device also has a function to receive user feedback. This feedback is sent to a server and used to make future suggestions.

[0146] User roles

[0147] Users can view recommended products on their devices and receive optimal product information based on their emotions. For example, if a user is feeling anxious, the system can recommend products of consistent quality. Users can experience recommendations that adapt to their changing emotions and ultimately purchase products that suit their preferences.

[0148] Overall, this system can significantly improve the customer experience in e-commerce by leveraging emotion recognition technology. For example, it can enhance the quality of the user experience by avoiding re-proposing products that the user has previously expressed negative emotions about.

[0149] The following describes the processing flow.

[0150] Step 1:

[0151] The server retrieves the user's past transaction history, preference data, and browsing history from a database. It also collects the latest data from various online sources, including social media and trend information.

[0152] Step 2:

[0153] The emotion engine activates, recognizing the user's current emotional state in real time through facial recognition and voice tone analysis on the device. This allows the user's level of relaxation and stress to be quantified.

[0154] Step 3:

[0155] The server uses an AI algorithm to analyze collected preference data and emotional data provided by the emotion engine. This analysis constructs a product profile that is tailored to the user's emotional state.

[0156] Step 4:

[0157] Based on the established profile, the server collects information from multiple e-commerce sites and identifies recommended products tailored to the user's emotional state. It also obtains price and inventory information in real time to provide more advantageous choices.

[0158] Step 5:

[0159] The server takes into account promotional information and valid coupons, and adjusts prices according to the user's emotional state. It then sends a list of recommended products, including these adjustments, to the user's device.

[0160] Step 6:

[0161] The device displays a list of recommended products received by the user. The display method is customized according to the user's mood; an intuitive design is used when the user is relaxed, while a simple design with less information is used when the user is stressed.

[0162] Step 7:

[0163] Users view details of recommended products through their devices and decide whether or not to proceed with a purchase. User feedback and analysis results are sent to the server and used to improve the recommendation system for future updates.

[0164] Step 8:

[0165] The device notifies users of new trending information and recommended products, ensuring they always receive the latest information. The timing and content of notifications are also optimized based on sentiment data.

[0166] (Example 2)

[0167] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0168] In today's e-commerce environment, there is a demand for optimal product recommendations that cater to the diverse preferences and emotions of customers. However, existing systems typically rely on fixed algorithms and are unable to respond flexibly to the emotions and real-time trends of individual customers. This makes it difficult to quickly and appropriately suggest products that customers want, resulting in a challenge in improving the purchasing experience.

[0169] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0170] In this invention, the server includes means for acquiring information on a customer's past activities, means for analyzing the acquired information and suggesting the most suitable products based on the customer's preferences, and means for analyzing information from external media collected in real time and identifying new products that will interest the customer. This enables flexible product suggestions that cater to the diverse preferences and emotions of customers.

[0171] "Customer past activity information" refers to the customer's past purchase history and online activity history.

[0172] "A means of analyzing acquired information and proposing the optimal product based on customer preferences" refers to a method of analyzing collected customer data and selecting products that are suitable for the user's interests and preferences.

[0173] "A method for analyzing information collected in real time from external media to identify new products that will attract customer interest" refers to a method of instantly acquiring the latest trends and fashion information from external data sources and selecting products that will attract interest based on that information.

[0174] "Means of acquiring and analyzing a user's biometric information to determine the customer's emotional state" refers to a method of acquiring biometric data such as the user's facial expressions and tone of voice, and analyzing it to evaluate their current emotions.

[0175] "Means of adjusting and optimizing product suggestions based on emotional state" refers to technologies that modify suggestions according to the user's emotions to show the most suitable product.

[0176] "Means of notifying the customer's device of recommended product information" refers to a mechanism that transmits selected product information from the server directly to the user's device.

[0177] "Means of dynamically changing the output interface according to the user's emotional state" refers to technologies that change the design and content of the displayed interface based on the user's emotions.

[0178] This invention provides a personal shopping assistant system that uses emotion recognition technology to improve the customer purchasing experience. The system mainly consists of a server, a terminal, a user, and an emotion recognition engine.

[0179] The server retrieves data from databases and external information sources to aggregate past customer activity information. This process involves extracting customer data by executing SQL queries using Python and employing web scraping techniques to obtain the latest trend information from external websites. The server also analyzes the retrieved data using machine learning frameworks (such as TensorFlow) to analyze customer preferences. This allows the server to suggest products optimized for each customer.

[0180] The emotion recognition engine acquires biometric information using the camera and microphone on the user's device and determines the user's emotional state. This data is transmitted to the server in real time. By using libraries such as OpenCV to extract feature points of facial expressions and analyzing emotions with a dedicated algorithm, the engine identifies the user's current emotion.

[0181] The device displays products recommended by the server in the user interface. This display also includes emotion recognition data, and the optimal interface is dynamically adjusted according to the user's emotions. The device uses HTML and JavaScript (registered trademark) to display product information and changes the interface's color and layout according to the user's emotional state.

[0182] For example, if the emotion recognition engine determines that the user is in a relaxed state, the server will notify the device of recommendations for bright colors or new brands of products. The device then collects feedback from the user and forwards it to the server, which is used to improve the accuracy of future recommendations.

[0183] An example of a prompt message is, "Create a program that generates customer profiles using Python and TensorFlow." Such a system configuration makes it possible to quickly and effectively provide product recommendations tailored to individual customers.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The server retrieves past customer activity information from the database. Using the customer ID as input, it executes SQL queries to extract purchase and browsing history. The output includes a list of the customer's purchased items and browsing history. Specifically, it uses the Python SQLalchemy library to connect to the database and execute queries.

[0187] Step 2:

[0188] The server analyzes the acquired data and profiles customer preferences using an AI algorithm. It uses the output from step 1 as input and performs clustering and pattern recognition through a machine learning framework (e.g., TensorFlow). The output generates individual customer profiles and recommended product lists. Specifically, it uses principal component analysis and K-means algorithms to organize the data and classify customer behavior patterns.

[0189] Step 3:

[0190] The emotion recognition engine acquires biometric information from the user's device. As input, it captures the user's face and voice data in real time from a webcam and microphone. The output is an analysis result indicating the user's current emotional state. Specifically, it uses the OpenCV library to extract facial feature points and a voice analysis algorithm to determine tone.

[0191] Step 4:

[0192] The server receives emotional data and adjusts product recommendations based on those emotions. It uses the recommended product list from step 2 and the emotional analysis results from step 3 as input. After data processing, optimized product recommendations are generated as output. Specifically, it quantifies emotional states and adjusts the priority and category of products based on these quantifications.

[0193] Step 5:

[0194] The terminal displays an optimized product list sent from the server in its user interface. It receives a recommended list from the server as input and displays it on the screen using HTML and JavaScript. The output is product information that visually appeals to the user. Specifically, it performs coloring and layout adjustments based on sentiment analysis results.

[0195] Step 6:

[0196] Users review product suggestions and provide feedback via their devices. They submit their opinions based on the product information displayed on their devices as input, and this feedback is sent to the server as output. Specifically, users submit comments and ratings through a dedicated feedback input form.

[0197] This entire process enables the system to offer personalized product suggestions to individual customers and provide an emotionally resonant shopping experience.

[0198] (Application Example 2)

[0199] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0200] In recent years, the use of e-commerce has surged, creating a demand for providing customers with a comfortable shopping experience. However, existing systems struggle to provide flexible product recommendations that take customer emotions into account, potentially leading to customer stress and dissatisfaction. Solutions to these problems are needed.

[0201] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0202] In this invention, the server includes means for acquiring past customer information, means for analyzing the acquired information and recommending the most suitable products based on the customer's preferences, and means for collecting user emotional information and recommending products based on those emotions to improve the customer experience. This makes it possible to recommend products that take the customer's emotional state into account, thereby providing a more personalized purchasing experience.

[0203] "Past customer information" refers to data on a customer's transaction history and preferences that they have acquired to date.

[0204] "Optimal products based on preferences" refers to products that suit the individual interests and preferences of the customer.

[0205] An "e-commerce platform" refers to a digital environment for selling goods or services online.

[0206] "Sales promotion information" refers to various types of information used to promote the sale of products and services.

[0207] A "terminal" refers to a device used by a customer to receive information and perform operations.

[0208] "Emotional information" refers to data that indicates a customer's current emotional state, and is obtained based on facial expressions, voice, and other physiological responses.

[0209] A "personalized shopping experience" refers to a shopping experience that provides the most relevant information and services to each individual customer.

[0210] To implement this invention, a server is central to the system. The server retrieves past customer transaction information and preference data from a database and uses this to build a customer profile. The server also receives customer emotion data transmitted from the emotion engine and performs calculations in real time. This allows the system to recommend the most suitable products while considering the customer's emotional state. Specifically, the server implements AI algorithms using programming languages ​​such as Python, and emotion recognition software such as Microsoft® Azure® Face API or Google® Cloud Speech-to-Text can be used.

[0211] The device is responsible for displaying product information recommended by the server to the user. This device could be a smartphone or tablet, allowing the user to actually view product information and receive emotion-based recommendations. The device also utilizes the smartphone's camera and microphone to collect the user's facial expressions and voice, and transmits this information to the emotion engine.

[0212] Users can review product information provided through their device and select products that fit their current emotional state. This enables a personalized experience based on emotions, such as recommending relaxing products if the user is stressed, or new or trendy products if their curiosity is heightened. For example, if the emotional state is determined to be "stressed," the prompt might read, "What relaxing products would you recommend when the user is feeling stressed?"

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The server retrieves past customer transaction information and preference data from the database. Based on this input data, it performs data processing and statistical analysis to build a customer profile, and outputs it as profile data.

[0216] Step 2:

[0217] The user's device uses its camera and microphone to capture the user's facial expressions and voice data in real time and transmit it to the emotion engine. The input is the user's facial expressions and voice, and the output is emotion data. This data is analyzed to determine the user's emotional state through an emotion recognition algorithm.

[0218] Step 3:

[0219] The emotion engine determines the user's emotional state based on the received facial and audio data and sends the result to the server. The input is facial and audio data for emotion analysis, and the output is data indicating the emotional state. This process is performed using an AI model.

[0220] Step 4:

[0221] The server combines customer profiles and emotional state data and uses an AI algorithm to generate optimal product recommendations. The input is profile data and emotional state data, and the output is a list of recommended products. This step includes data integration and analysis, as well as the utilization of a generative AI model.

[0222] Step 5:

[0223] The terminal displays a list of recommended products sent from the server to the user. This screen display receives data as input to select the interface best suited to the user's emotional state and outputs product information that is visually optimized for the user.

[0224] Step 6:

[0225] The user reviews the recommended products displayed on their device and selects the product that best suits their feelings and preferences. By making a final purchase choice, the user provides their preference data to the system as input and sends it to the server as feedback.

[0226] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0227] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0228] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0232] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0233] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0234] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0235] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0236] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0237] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0238] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0239] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0240] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0241] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0242] This invention provides an AI-powered personal shopping assistant system to improve the customer purchasing experience in the field of e-commerce. The roles of the server, terminal, and user are described in the implementation of this system.

[0243] Server Role

[0244] The server plays a central role in the system, handling all data processing and analysis. First, it retrieves customers' past transaction history, preference data, and browsing history from the database. Based on this data, it uses AI algorithms to build customer profiles and analyze individual preferences and past purchase patterns. Furthermore, the server collects real-time trend information from the internet and analyzes this information to identify recommended products.

[0245] The server also utilizes APIs from multiple e-commerce sites to collect price and inventory information for identified products. This allows it to automatically identify the most advantageous pricing for customers. It retrieves promotional information and coupons from its database and adjusts prices to ensure the best possible deal.

[0246] Terminal role

[0247] The terminal's role is to present recommended product information sent from the server to the user. The terminal's interface is interactive, displaying detailed information such as product descriptions, pricing, and coupon application status. The terminal also sends user feedback and conversational information to the server, which is used to improve the accuracy of future recommendations.

[0248] It features a notification function, allowing users to set up notifications to receive alerts under specific conditions. For example, users can receive notifications when the price of a particular product drops or when a new campaign starts.

[0249] User roles

[0250] Users access the system daily through their devices. They can view recommended products and access detailed information on their devices. Users make the final decision on whether to purchase the recommended products and complete their orders through the platform.

[0251] For example, if a user has frequently purchased outdoor equipment in the past, the server can use that data to notify the user's device of new product releases and sales information on related items, helping the user enjoy a more advantageous shopping experience. In this way, the system of the present invention can make customer purchasing behavior more efficient and satisfying.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server retrieves customers' past transaction history, preference data, and browsing history from a database. In addition, it collects the latest trend information from social media and news sites on the internet.

[0255] Step 2:

[0256] The server analyzes the acquired data using AI algorithms to build a customer preference profile. This profile includes the customer's preferred brands, product categories, price range, and purchase frequency.

[0257] Step 3:

[0258] The server identifies the most suitable recommended products for the customer based on the established preference profile. It also analyzes trend information collected during this process to select the most relevant products.

[0259] Step 4:

[0260] The server collects information on identified products from multiple e-commerce sites and compares prices and inventory information. This allows it to list products that are advantageous to the customer.

[0261] Step 5:

[0262] The server checks promotional information and coupons, automatically applies them to the most suitable products, and adjusts prices accordingly. Based on these adjustments, it ultimately determines the product list to present to the customer.

[0263] Step 6:

[0264] The server sends the final list of recommended products to the terminal. The terminal displays the received information to the user and provides product descriptions and pricing information through its interface.

[0265] Step 7:

[0266] Users can view recommended products displayed on their device and access detailed information. If a user is interested in a product, they can proceed directly to the purchase page.

[0267] Step 8:

[0268] User feedback and purchase history are sent to the server via the device. The server uses this information to learn how to improve the accuracy of future recommendations.

[0269] Step 9:

[0270] The device notifies users of price changes and new promotional information for specific products based on real-time notification settings. This feature allows users to always stay up-to-date.

[0271] (Example 1)

[0272] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] In modern e-commerce, there is a demand for product recommendations tailored to individual customer preferences. However, existing systems have not been able to adequately achieve highly accurate personalized recommendations and have struggled to respond to real-time price strategies and demand changes. Therefore, the challenge is to provide customers with a more personalized, timely, and optimal purchasing experience.

[0274] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0275] In this invention, the server includes means for obtaining a customer's past transaction history, preference data, and browsing history from a database; means for constructing an individual customer profile using a generative AI model based on the obtained data; and means for analyzing trend information obtained from multiple data sources in real time to identify new products suitable for the customer. This makes it possible to provide personalized product recommendations for each customer and to provide optimal product information in response to ever-changing consumer trends.

[0276] A "database" is a digital store that systematically organizes information so that it can be efficiently accessed and managed later.

[0277] A "generative AI model" is an algorithm that uses artificial intelligence to learn patterns from large amounts of data and makes predictions and decisions based on new data.

[0278] A "profile" is a collection of detailed information about an individual customer, including their preferences and behavioral patterns, which enables personalized product recommendations.

[0279] "Trend information" refers to information about the trends of products and services that are gaining popularity at a particular time, and is used to identify new products that will attract customer interest.

[0280] "API" refers to an interface for information and function exchange between different software, and is a means to enable integration with third-party services.

[0281] "GUI" is an abbreviation for Graphical User Interface, which is a user interface that can be intuitively operated using visual elements.

[0282] "Feedback" refers to the opinions and reactions provided by users after use, and serves as a valuable source of information for system improvement.

[0283] "Real-time" means that a computer system has the ability to respond immediately and process data without time delay.

[0284] The system in this invention enables the server, terminal, and user to cooperate with each other to provide an optimal purchasing experience in e-commerce. Hereinafter, specific embodiments will be described.

[0285] The server plays a central role in the system and efficiently obtains customers' past transaction histories, preference data, and browsing histories from the database. At this time, a database management system is used to aggregate the target data by means such as SQL queries. The acquired data is used to construct and improve each customer's profile using a generative AI model, enabling the provision of products tailored to individual preferences and behavior patterns.

[0286] Furthermore, the server collects real-time fashion information via the Internet. This fashion information is sequentially obtained using scraping technology to grasp the latest trends, and new products in the market are identified through analysis. It is also an important function to utilize the API from the e-market to obtain and compare product prices and inventory information in real-time.

[0287] The terminals that present products to users visually display recommended product information from the server. GUI technology is used to provide an intuitive interface for customers. For example, sending notifications when prices drop can further pique user interest.

[0288] Users utilize the system daily through their devices to select products, provide feedback, and make purchase decisions. This feedback is sent to the server and used to improve the accuracy of future recommendations by the generated AI model.

[0289] Thus, the system of the present invention is designed to make customer purchasing behavior more efficient and fulfilling, with servers and terminals functioning harmoniously in providing information and understanding customer needs.

[0290] Example of a prompt:

[0291] "Recommend new products related to items that customers have frequently purchased in the past. Use an AI algorithm that considers the latest trends and pricing information to suggest the best products for each customer."

[0292] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0293] Step 1:

[0294] The server retrieves the customer's past transaction history, preference data, and browsing history from the database. It uses SQL queries to search for the necessary data and temporarily loads it into data processing memory. The retrieved data is used as input to a generative AI model. The output at this stage is the input dataset for creating customer profiles.

[0295] Step 2:

[0296] The server uses a generated AI model to construct customer profiles based on the data acquired in Step 1. Specifically, it analyzes the data using machine learning algorithms to reveal customer preferences and purchasing patterns. As output, a detailed profile for each customer is generated and used as the basis data for the next analysis step.

[0297] Step 3:

[0298] The server analyzes real-time trend information obtained from the internet and uses it to recommend products based on customer profiles. By collecting data using scraping techniques and analyzing its contents, it identifies trending products suitable for each customer. The output of this step is a personalized list of recommended products.

[0299] Step 4:

[0300] The server collects price and inventory information for products from online marketplaces via an API. This collected data is analyzed by a real-time price comparison algorithm and processed to enable customers to make advantageous product selections. The output is a list containing the best prices and inventory information for recommended products.

[0301] Step 5:

[0302] The terminal displays recommended product information received from the server on its user interface. GUI technology is used to present the product information in a way that users can intuitively understand. For example, notification features are used to communicate price changes and campaign information to the user in a way that encourages purchase decisions. The output is a simple and easy-to-understand product display screen for the user.

[0303] Step 6:

[0304] The user checks the products displayed on the terminal through the above steps and provides feedback. The terminal sends this feedback to the server and is used for the learning of the generative AI model. As a result, the recommendation accuracy for subsequent times is improved. As output, the collected feedback data is stored in the server.

[0305] Step 7:

[0306] The user selects the recommended product and completes the purchase process through the terminal. The server securely performs the necessary payment processing based on the input order information using a security protocol. The output is a confirmation and completion message of the order by the user.

[0307] (Application Example 1)

[0308] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] In e-commerce, it is required to provide a more personalized purchasing experience for customers and enhance their purchasing desire. Also, due to the excessive amount of market information, it has become difficult to select the optimal product, and a system that can provide an efficient and satisfactory shopping experience for customers is needed.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0311] In this invention, the server includes means for acquiring customer transaction history and preference information, means for analyzing the acquired information to build a customer profile and recommend products based on preferences, means for referencing information from multiple e-commerce platforms to present more profitable product information, means for automatically adjusting product prices based on sales promotion information, means for notifying the user's terminal of the recommended product information, and means for analyzing trends acquired in real time to identify new products that will attract customer interest. This makes it possible to provide customers with the most suitable products in a timely manner and to personalize and streamline the purchasing experience.

[0312] "Customer transaction history" refers to records of products a user has purchased in the past, and by analyzing this data, it is used to understand purchasing trends.

[0313] "Preference information" refers to data about customers' preferences and interests, and is used to recommend products that are suitable for each customer.

[0314] An "e-commerce platform" is an online system used to buy and sell goods and services over the internet.

[0315] "Methods for recommending products" refer to technologies that suggest the most suitable products to users based on their preferences and past purchase history.

[0316] "Sales promotion information" refers to information about promotions that increase customer purchasing intent, such as coupons and discounts.

[0317] "Methods for automatically adjusting prices" refer to systems that automatically change the price of a product based on sales promotion information and market trends.

[0318] "Means of notifying the device" refers to messaging functions for providing information to customers in real time.

[0319] "Methods for analyzing trends" refer to technologies that analyze market and consumer trends in real time and provide customers with new information based on this analysis.

[0320] To realize this system, the server, terminals, and users must cooperate and fulfill their respective roles. The server first retrieves customer transaction history and preference information from a database and analyzes it using an AI algorithm. This analysis makes it possible to build customer profiles and recommend products based on preferences. Furthermore, the server collects information from multiple e-commerce platforms to form the basis for providing optimal product information.

[0321] Next, the server sends recommended product information to the terminal. The terminal presents this information to the user and collects user feedback using an interactive interface. The feedback information is sent to the server and used to improve the accuracy of product recommendations in the future. The terminal also has the function of notifying the user of price changes and promotion information in real time.

[0322] The server analyzes trend information in real time and uses this to identify new products that will attract customer interest. Data analysis tools and AI models are used in this analysis to provide customers with the latest and most useful information. Specifically, cloud computing technology (such as AWS) is used, and MySQL is used for database management. TensorFlow and scikit-learn are utilized for AI algorithms.

[0323] For example, if a user has previously purchased sports-related products, the server uses that data to send push notifications to their device about newly released sports equipment and ongoing campaigns. This allows users to efficiently receive more accurate product information, thereby promoting purchasing behavior. Prompts such as, "Based on the user's purchase history and current trends, please recommend the three most relevant products," are supplied to the generating AI model, enabling personalized product recommendations.

[0324] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0325] Step 1:

[0326] The server retrieves customer transaction history and preference information from a database. It receives a user ID as input and extracts historical transaction data and preference patterns associated with this ID. As output, it generates a set of customer transaction history and preference data. This data is retrieved using a database management system (such as MySQL).

[0327] Step 2:

[0328] The server analyzes acquired transaction history and preference information to build customer profiles. It receives transaction history and preference data as input and performs analysis using an AI algorithm (TensorFlow or scikit-learn). The output is profile data that shows the customer's interests and tendencies. This profile is used for personalized product recommendations.

[0329] Step 3:

[0330] The server collects product information from multiple e-commerce platforms. It queries each platform using API keys and authentication information as input. The output is a list of product information for each platform. This forms the basis for the product information presented to the user.

[0331] Step 4:

[0332] The server recommends personalized products based on customer profiles and collected product information. Using customer profiles and product information as input, the AI ​​model generates prompts (e.g., "Recommend the three most relevant products based on the user's purchase history and current trends."). The output is a list of recommended products tailored to the user.

[0333] Step 5:

[0334] The server sends the generated recommendation list to the terminal, and the terminal notifies the user. The server receives the recommendation list as input and communicates the information to the user in real time through the terminal's notification function. The output provides the user with information on recommended products. The user can then consider purchasing based on this information.

[0335] Step 6:

[0336] Users view detailed information through their device and enter purchase feedback. The device receives user feedback and dialogue information as input and sends it to the server. The output is feedback data, which is used to improve the accuracy of product recommendations for future purchases.

[0337] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0338] This invention relates to a personal shopping assistant system that integrates a customer emotion recognition system to improve the purchasing experience in e-commerce. The roles of four parties—server, terminal, user, and emotion engine—are described in the implementation of this system.

[0339] Server Role

[0340] The server retrieves customer purchase history, preference data, and browsing history from a database. In addition, it collects and analyzes the latest trend information from various sources on the internet. Using AI algorithms, it builds customer profiles based on the acquired data. Furthermore, it processes data received from the emotion engine to understand the customer's emotional state.

[0341] Specifically, the server adjusts product recommendations based on the output of the emotion engine. This adjustment includes factors such as price, brand, and category, and has the function to optimize suggestions according to the customer's emotions.

[0342] The role of the emotional engine

[0343] The emotion engine acquires data such as the user's facial expressions, voice tone, and input timing on the device to determine the user's current emotional state. These emotions are identified in various forms, such as stress, excitement, and interest, and transmitted to the server in real time. The emotion engine also analyzes past emotional patterns to understand the customer's long-term emotional trends, thereby improving the accuracy of future recommendations.

[0344] Terminal role

[0345] The device displays a list of recommended products sent from the server. In doing so, the device also takes into account the output of the emotion engine, providing an optimal interface display tailored to the user's emotional state. For example, if the user is relaxed, it might display bolder recommendations.

[0346] The device also has a function to receive user feedback. This feedback is sent to a server and used to make future suggestions.

[0347] User roles

[0348] Users can view recommended products on their devices and receive optimal product information based on their emotions. For example, if a user is feeling anxious, the system can recommend products of consistent quality. Users can experience recommendations that adapt to their changing emotions and ultimately purchase products that suit their preferences.

[0349] Overall, this system can significantly improve the customer experience in e-commerce by leveraging emotion recognition technology. For example, it can enhance the quality of the user experience by avoiding re-proposing products that the user has previously expressed negative emotions about.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] The server retrieves the user's past transaction history, preference data, and browsing history from a database. It also collects the latest data from various online sources, including social media and trend information.

[0353] Step 2:

[0354] The emotion engine activates, recognizing the user's current emotional state in real time through facial recognition and voice tone analysis on the device. This allows the user's level of relaxation and stress to be quantified.

[0355] Step 3:

[0356] The server uses an AI algorithm to analyze collected preference data and emotional data provided by the emotion engine. This analysis constructs a product profile that is tailored to the user's emotional state.

[0357] Step 4:

[0358] Based on the established profile, the server collects information from multiple e-commerce sites and identifies recommended products tailored to the user's emotional state. It also obtains price and inventory information in real time to provide more advantageous choices.

[0359] Step 5:

[0360] The server takes into account promotional information and valid coupons, and adjusts prices according to the user's emotional state. It then sends a list of recommended products, including these adjustments, to the user's device.

[0361] Step 6:

[0362] The device displays a list of recommended products received by the user. The display method is customized according to the user's mood; an intuitive design is used when the user is relaxed, while a simple design with less information is used when the user is stressed.

[0363] Step 7:

[0364] Users view details of recommended products through their devices and decide whether or not to proceed with a purchase. User feedback and analysis results are sent to the server and used to improve the recommendation system for future updates.

[0365] Step 8:

[0366] The device notifies users of new trending information and recommended products, ensuring they always receive the latest information. The timing and content of notifications are also optimized based on sentiment data.

[0367] (Example 2)

[0368] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0369] In today's e-commerce environment, there is a demand for optimal product recommendations that cater to the diverse preferences and emotions of customers. However, existing systems typically rely on fixed algorithms and are unable to respond flexibly to the emotions and real-time trends of individual customers. This makes it difficult to quickly and appropriately suggest products that customers want, resulting in a challenge in improving the purchasing experience.

[0370] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0371] In this invention, the server includes means for acquiring information on a customer's past activities, means for analyzing the acquired information and suggesting the most suitable products based on the customer's preferences, and means for analyzing information from external media collected in real time and identifying new products that will interest the customer. This enables flexible product suggestions that cater to the diverse preferences and emotions of customers.

[0372] "Customer past activity information" refers to the customer's past purchase history and online activity history.

[0373] "A means of analyzing acquired information and proposing the optimal product based on customer preferences" refers to a method of analyzing collected customer data and selecting products that are suitable for the user's interests and preferences.

[0374] "A method for analyzing information collected in real time from external media to identify new products that will attract customer interest" refers to a method of instantly acquiring the latest trends and fashion information from external data sources and selecting products that will attract interest based on that information.

[0375] "Means of acquiring and analyzing a user's biometric information to determine the customer's emotional state" refers to a method of acquiring biometric data such as the user's facial expressions and tone of voice, and analyzing it to evaluate their current emotions.

[0376] "Means of adjusting and optimizing product suggestions based on emotional state" refers to technologies that modify suggestions according to the user's emotions to show the most suitable product.

[0377] "Means of notifying the customer's device of recommended product information" refers to a mechanism that transmits selected product information from the server directly to the user's device.

[0378] "Means of dynamically changing the output interface according to the user's emotional state" refers to technologies that change the design and content of the displayed interface based on the user's emotions.

[0379] This invention provides a personal shopping assistant system that uses emotion recognition technology to improve the customer purchasing experience. The system mainly consists of a server, a terminal, a user, and an emotion recognition engine.

[0380] The server retrieves data from databases and external information sources to aggregate past customer activity information. This process involves extracting customer data by executing SQL queries using Python and employing web scraping techniques to obtain the latest trend information from external websites. The server also analyzes the retrieved data using machine learning frameworks (such as TensorFlow) to analyze customer preferences. This allows the server to suggest products optimized for each customer.

[0381] The emotion recognition engine acquires biometric information using the camera and microphone on the user's device and determines the user's emotional state. This data is transmitted to the server in real time. By using libraries such as OpenCV to extract feature points of facial expressions and analyzing emotions with a dedicated algorithm, the engine identifies the user's current emotion.

[0382] The device displays products recommended by the server in the user interface. This display also includes emotion recognition data, and the optimal interface is dynamically adjusted according to the user's emotions. The device uses HTML and JavaScript to display product information and changes the interface's color and layout according to the user's emotional state.

[0383] For example, if the emotion recognition engine determines that the user is in a relaxed state, the server will notify the device of recommendations for bright colors or new brands of products. The device then collects feedback from the user and forwards it to the server, which is used to improve the accuracy of future recommendations.

[0384] An example of a prompt message is, "Create a program that generates customer profiles using Python and TensorFlow." Such a system configuration makes it possible to quickly and effectively provide product recommendations tailored to individual customers.

[0385] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0386] Step 1:

[0387] The server retrieves past customer activity information from the database. Using the customer ID as input, it executes SQL queries to extract purchase and browsing history. The output includes a list of the customer's purchased items and browsing history. Specifically, it uses the Python SQLalchemy library to connect to the database and execute queries.

[0388] Step 2:

[0389] The server analyzes the acquired data and profiles customer preferences using an AI algorithm. It uses the output from step 1 as input and performs clustering and pattern recognition through a machine learning framework (e.g., TensorFlow). The output generates individual customer profiles and recommended product lists. Specifically, it uses principal component analysis and K-means algorithms to organize the data and classify customer behavior patterns.

[0390] Step 3:

[0391] The emotion recognition engine acquires biometric information from the user's device. As input, it captures the user's face and voice data in real time from a webcam and microphone. The output is an analysis result indicating the user's current emotional state. Specifically, it uses the OpenCV library to extract facial feature points and a voice analysis algorithm to determine tone.

[0392] Step 4:

[0393] The server receives emotional data and adjusts product recommendations based on those emotions. It uses the recommended product list from step 2 and the emotional analysis results from step 3 as input. After data processing, optimized product recommendations are generated as output. Specifically, it quantifies emotional states and adjusts the priority and category of products based on these quantifications.

[0394] Step 5:

[0395] The terminal displays an optimized product list sent from the server in its user interface. It receives a recommended list from the server as input and displays it on the screen using HTML and JavaScript. The output is product information that visually appeals to the user. Specifically, it performs coloring and layout adjustments based on sentiment analysis results.

[0396] Step 6:

[0397] Users review product suggestions and provide feedback via their devices. They submit their opinions based on the product information displayed on their devices as input, and this feedback is sent to the server as output. Specifically, users submit comments and ratings through a dedicated feedback input form.

[0398] This entire process enables the system to offer personalized product suggestions to individual customers and provide an emotionally resonant shopping experience.

[0399] (Application Example 2)

[0400] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0401] In recent years, the use of e-commerce has surged, creating a demand for providing customers with a comfortable shopping experience. However, existing systems struggle to provide flexible product recommendations that take customer emotions into account, potentially leading to customer stress and dissatisfaction. Solutions to these problems are needed.

[0402] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0403] In this invention, the server includes means for acquiring past customer information, means for analyzing the acquired information and recommending the most suitable products based on the customer's preferences, and means for collecting user emotional information and recommending products based on those emotions to improve the customer experience. This makes it possible to recommend products that take the customer's emotional state into account, thereby providing a more personalized purchasing experience.

[0404] "Past customer information" refers to data on a customer's transaction history and preferences that they have acquired to date.

[0405] "Optimal products based on preferences" refers to products that suit the individual interests and preferences of the customer.

[0406] An "e-commerce platform" refers to a digital environment for selling goods or services online.

[0407] "Sales promotion information" refers to various types of information used to promote the sale of products and services.

[0408] A "terminal" refers to a device used by a customer to receive information and perform operations.

[0409] "Emotional information" refers to data that indicates a customer's current emotional state, and is obtained based on facial expressions, voice, and other physiological responses.

[0410] A "personalized shopping experience" refers to a shopping experience that provides the most relevant information and services to each individual customer.

[0411] To implement this invention, a server is central to the system. The server retrieves past customer transaction information and preference data from a database and uses this to build a customer profile. The server also receives customer emotion data transmitted from the emotion engine and performs calculations in real time. This allows the system to recommend the most suitable products while considering the customer's emotional state. Specifically, the server implements AI algorithms using programming languages ​​such as Python, and emotion recognition software such as Microsoft Azure Face API or Google Cloud Speech-to-Text can be used.

[0412] The device is responsible for displaying product information recommended by the server to the user. This device could be a smartphone or tablet, allowing the user to actually view product information and receive emotion-based recommendations. The device also utilizes the smartphone's camera and microphone to collect the user's facial expressions and voice, and transmits this information to the emotion engine.

[0413] Users can review product information provided through their device and select products that fit their current emotional state. This enables a personalized experience based on emotions, such as recommending relaxing products if the user is stressed, or new or trendy products if their curiosity is heightened. For example, if the emotional state is determined to be "stressed," the prompt might read, "What relaxing products would you recommend when the user is feeling stressed?"

[0414] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0415] Step 1:

[0416] The server retrieves past customer transaction information and preference data from the database. Based on this input data, it performs data processing and statistical analysis to build a customer profile, and outputs it as profile data.

[0417] Step 2:

[0418] The user's device uses its camera and microphone to capture the user's facial expressions and voice data in real time and transmit it to the emotion engine. The input is the user's facial expressions and voice, and the output is emotion data. This data is analyzed to determine the user's emotional state through an emotion recognition algorithm.

[0419] Step 3:

[0420] The emotion engine determines the user's emotional state based on the received facial and audio data and sends the result to the server. The input is facial and audio data for emotion analysis, and the output is data indicating the emotional state. This process is performed using an AI model.

[0421] Step 4:

[0422] The server combines customer profiles and emotional state data and uses an AI algorithm to generate optimal product recommendations. The input is profile data and emotional state data, and the output is a list of recommended products. This step includes data integration and analysis, as well as the utilization of a generative AI model.

[0423] Step 5:

[0424] The terminal displays a list of recommended products sent from the server to the user. This screen display receives data as input to select the interface best suited to the user's emotional state and outputs product information that is visually optimized for the user.

[0425] Step 6:

[0426] The user reviews the recommended products displayed on their device and selects the product that best suits their feelings and preferences. By making a final purchase choice, the user provides their preference data to the system as input and sends it to the server as feedback.

[0427] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0428] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0429] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0430] [Third Embodiment]

[0431] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0432] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0433] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0434] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0435] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0436] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0437] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0438] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0439] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0440] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0441] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0442] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0443] This invention provides an AI-powered personal shopping assistant system to improve the customer purchasing experience in the field of e-commerce. The roles of the server, terminal, and user are described in the implementation of this system.

[0444] Server Role

[0445] The server plays a central role in the system, handling all data processing and analysis. First, it retrieves customers' past transaction history, preference data, and browsing history from the database. Based on this data, it uses AI algorithms to build customer profiles and analyze individual preferences and past purchase patterns. Furthermore, the server collects real-time trend information from the internet and analyzes this information to identify recommended products.

[0446] The server also utilizes APIs from multiple e-commerce sites to collect price and inventory information for identified products. This allows it to automatically identify the most advantageous pricing for customers. It retrieves promotional information and coupons from its database and adjusts prices to ensure the best possible deal.

[0447] Terminal role

[0448] The terminal's role is to present recommended product information sent from the server to the user. The terminal's interface is interactive, displaying detailed information such as product descriptions, pricing, and coupon application status. The terminal also sends user feedback and conversational information to the server, which is used to improve the accuracy of future recommendations.

[0449] It features a notification function, allowing users to set up notifications to receive alerts under specific conditions. For example, users can receive notifications when the price of a particular product drops or when a new campaign starts.

[0450] User roles

[0451] Users access the system daily through their devices. They can view recommended products and access detailed information on their devices. Users make the final decision on whether to purchase the recommended products and complete their orders through the platform.

[0452] For example, if a user has frequently purchased outdoor equipment in the past, the server can use that data to notify the user's device of new product releases and sales information on related items, helping the user enjoy a more advantageous shopping experience. In this way, the system of the present invention can make customer purchasing behavior more efficient and satisfying.

[0453] The following describes the processing flow.

[0454] Step 1:

[0455] The server retrieves customers' past transaction history, preference data, and browsing history from a database. In addition, it collects the latest trend information from social media and news sites on the internet.

[0456] Step 2:

[0457] The server analyzes the acquired data using AI algorithms to build a customer preference profile. This profile includes the customer's preferred brands, product categories, price range, and purchase frequency.

[0458] Step 3:

[0459] The server identifies the most suitable recommended products for the customer based on the established preference profile. It also analyzes trend information collected during this process to select the most relevant products.

[0460] Step 4:

[0461] The server collects information on identified products from multiple e-commerce sites and compares prices and inventory information. This allows it to list products that are advantageous to the customer.

[0462] Step 5:

[0463] The server checks promotional information and coupons, automatically applies them to the most suitable products, and adjusts prices accordingly. Based on these adjustments, it ultimately determines the product list to present to the customer.

[0464] Step 6:

[0465] The server sends the final list of recommended products to the terminal. The terminal displays the received information to the user and provides product descriptions and pricing information through its interface.

[0466] Step 7:

[0467] Users can view recommended products displayed on their device and access detailed information. If a user is interested in a product, they can proceed directly to the purchase page.

[0468] Step 8:

[0469] User feedback and purchase history are sent to the server via the device. The server uses this information to learn how to improve the accuracy of future recommendations.

[0470] Step 9:

[0471] The device notifies users of price changes and new promotional information for specific products based on real-time notification settings. This feature allows users to always stay up-to-date.

[0472] (Example 1)

[0473] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0474] In modern e-commerce, there is a demand for product recommendations tailored to individual customer preferences. However, existing systems have not been able to adequately achieve highly accurate personalized recommendations and have struggled to respond to real-time price strategies and demand changes. Therefore, the challenge is to provide customers with a more personalized, timely, and optimal purchasing experience.

[0475] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0476] In this invention, the server includes means for obtaining a customer's past transaction history, preference data, and browsing history from a database; means for constructing an individual customer profile using a generative AI model based on the obtained data; and means for analyzing trend information obtained from multiple data sources in real time to identify new products suitable for the customer. This makes it possible to provide personalized product recommendations for each customer and to provide optimal product information in response to ever-changing consumer trends.

[0477] A "database" is a digital store that systematically organizes information so that it can be efficiently accessed and managed later.

[0478] A "generative AI model" is an algorithm that uses artificial intelligence to learn patterns from large amounts of data and makes predictions and decisions based on new data.

[0479] A "profile" is a collection of detailed information about an individual customer, including their preferences and behavioral patterns, which enables personalized product recommendations.

[0480] "Trend information" refers to information about the trends of products and services that are gaining popularity at a particular time, and is used to identify new products that will attract customer interest.

[0481] An "API" is an interface for exchanging information and functions between different software programs, and a means of integrating with third-party services.

[0482] "GUI" is an abbreviation for Graphical User Interface, which is a user interface that can be operated intuitively using visual elements.

[0483] "Feedback" refers to the opinions and reactions provided by users after they have used a product, and it serves as a valuable source of information for improving the system.

[0484] "Real-time" means that a computer system has the ability to react instantly and process data without time delay.

[0485] The system in this invention provides an optimal purchasing experience in e-commerce through the mutual cooperation of a server, terminal, and user. Specific embodiments will be described below.

[0486] The server plays a central role in the system, efficiently retrieving customers' past transaction history, preference data, and browsing history from the database. This involves using a database management system and methods such as SQL queries to aggregate the desired data. The retrieved data is then used to build and refine individual customer profiles using a generation AI model, enabling the provision of products tailored to individual preferences and behavioral patterns.

[0487] Furthermore, the server collects trend information in real time via the internet. This trend information is continuously obtained using scraping technology to grasp the latest trends, and by analyzing it, new products in the market are identified. Another important function is the ability to obtain and compare product prices and inventory information in real time using APIs from online marketplaces.

[0488] The terminals that present products to users visually display recommended product information from the server. GUI technology is used to provide an intuitive interface for customers. For example, sending notifications when prices drop can further pique user interest.

[0489] Users utilize the system daily through their devices to select products, provide feedback, and make purchase decisions. This feedback is sent to the server and used to improve the accuracy of future recommendations by the generated AI model.

[0490] Thus, the system of the present invention is designed to make customer purchasing behavior more efficient and fulfilling, with servers and terminals functioning harmoniously in providing information and understanding customer needs.

[0491] Example of a prompt:

[0492] "Recommend new products related to items that customers have frequently purchased in the past. Use an AI algorithm that considers the latest trends and pricing information to suggest the best products for each customer."

[0493] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0494] Step 1:

[0495] The server retrieves the customer's past transaction history, preference data, and browsing history from the database. It uses SQL queries to search for the necessary data and temporarily loads it into data processing memory. The retrieved data is used as input to a generative AI model. The output at this stage is the input dataset for creating customer profiles.

[0496] Step 2:

[0497] The server uses a generated AI model to construct customer profiles based on the data acquired in Step 1. Specifically, it analyzes the data using machine learning algorithms to reveal customer preferences and purchasing patterns. As output, a detailed profile for each customer is generated and used as the basis data for the next analysis step.

[0498] Step 3:

[0499] The server analyzes real-time trend information obtained from the internet and uses it to recommend products based on customer profiles. By collecting data using scraping techniques and analyzing its contents, it identifies trending products suitable for each customer. The output of this step is a personalized list of recommended products.

[0500] Step 4:

[0501] The server collects price and inventory information for products from online marketplaces via an API. This collected data is analyzed by a real-time price comparison algorithm and processed to enable customers to make advantageous product selections. The output is a list containing the best prices and inventory information for recommended products.

[0502] Step 5:

[0503] The terminal displays recommended product information received from the server on its user interface. GUI technology is used to present the product information in a way that users can intuitively understand. For example, notification features are used to communicate price changes and campaign information to the user in a way that encourages purchase decisions. The output is a simple and easy-to-understand product display screen for the user.

[0504] Step 6:

[0505] Through the steps described above, the user reviews the products displayed on their device and provides feedback. The device sends this feedback to the server, which is used to train the generating AI model. This improves the accuracy of future recommendations. As output, the collected feedback data is stored on the server.

[0506] Step 7:

[0507] The user selects recommended products and completes the purchase process through the terminal. The server securely performs the necessary payment processing using security protocols based on the entered order information. The output is a confirmation and completion message from the user.

[0508] (Application Example 1)

[0509] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0510] In e-commerce, there is a growing need to provide customers with a more personalized shopping experience and increase their purchasing intent. Furthermore, the information overload in the market makes it difficult to select the optimal product, creating a need for systems that can provide customers with an efficient and satisfying shopping experience.

[0511] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0512] In this invention, the server includes means for acquiring customer transaction history and preference information, means for analyzing the acquired information to build a customer profile and recommend products based on preferences, means for referencing information from multiple e-commerce platforms to present more profitable product information, means for automatically adjusting product prices based on sales promotion information, means for notifying the user's terminal of the recommended product information, and means for analyzing trends acquired in real time to identify new products that will attract customer interest. This makes it possible to provide customers with the most suitable products in a timely manner and to personalize and streamline the purchasing experience.

[0513] "Customer transaction history" refers to records of products a user has purchased in the past, and by analyzing this data, it is used to understand purchasing trends.

[0514] "Preference information" refers to data about customers' preferences and interests, and is used to recommend products that are suitable for each customer.

[0515] An "e-commerce platform" is an online system used to buy and sell goods and services over the internet.

[0516] "Methods for recommending products" refer to technologies that suggest the most suitable products to users based on their preferences and past purchase history.

[0517] "Sales promotion information" refers to information about promotions that increase customer purchasing intent, such as coupons and discounts.

[0518] "Methods for automatically adjusting prices" refer to systems that automatically change the price of a product based on sales promotion information and market trends.

[0519] "Means of notifying the device" refers to messaging functions for providing information to customers in real time.

[0520] "Methods for analyzing trends" refer to technologies that analyze market and consumer trends in real time and provide customers with new information based on this analysis.

[0521] To realize this system, the server, terminals, and users must cooperate and fulfill their respective roles. The server first retrieves customer transaction history and preference information from a database and analyzes it using an AI algorithm. This analysis makes it possible to build customer profiles and recommend products based on preferences. Furthermore, the server collects information from multiple e-commerce platforms to form the basis for providing optimal product information.

[0522] Next, the server sends recommended product information to the terminal. The terminal presents this information to the user and collects user feedback using an interactive interface. The feedback information is sent to the server and used to improve the accuracy of product recommendations in the future. The terminal also has the function of notifying the user of price changes and promotion information in real time.

[0523] The server analyzes trend information in real time and uses this to identify new products that will attract customer interest. Data analysis tools and AI models are used in this analysis to provide customers with the latest and most useful information. Specifically, cloud computing technology (such as AWS) is used, and MySQL is used for database management. TensorFlow and scikit-learn are utilized for AI algorithms.

[0524] For example, if a user has previously purchased sports-related products, the server uses that data to send push notifications to their device about newly released sports equipment and ongoing campaigns. This allows users to efficiently receive more accurate product information, thereby promoting purchasing behavior. Prompts such as, "Based on the user's purchase history and current trends, please recommend the three most relevant products," are supplied to the generating AI model, enabling personalized product recommendations.

[0525] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0526] Step 1:

[0527] The server retrieves customer transaction history and preference information from a database. It receives a user ID as input and extracts historical transaction data and preference patterns associated with this ID. As output, it generates a set of customer transaction history and preference data. This data is retrieved using a database management system (such as MySQL).

[0528] Step 2:

[0529] The server analyzes acquired transaction history and preference information to build customer profiles. It receives transaction history and preference data as input and performs analysis using an AI algorithm (TensorFlow or scikit-learn). The output is profile data that shows the customer's interests and tendencies. This profile is used for personalized product recommendations.

[0530] Step 3:

[0531] The server collects product information from multiple e-commerce platforms. It queries each platform using API keys and authentication information as input. The output is a list of product information for each platform. This forms the basis for the product information presented to the user.

[0532] Step 4:

[0533] The server recommends personalized products based on customer profiles and collected product information. Using customer profiles and product information as input, the AI ​​model generates prompts (e.g., "Recommend the three most relevant products based on the user's purchase history and current trends."). The output is a list of recommended products tailored to the user.

[0534] Step 5:

[0535] The server sends the generated recommendation list to the terminal, and the terminal notifies the user. The server receives the recommendation list as input and communicates the information to the user in real time through the terminal's notification function. The output provides the user with information on recommended products. The user can then consider purchasing based on this information.

[0536] Step 6:

[0537] Users view detailed information through their device and enter purchase feedback. The device receives user feedback and dialogue information as input and sends it to the server. The output is feedback data, which is used to improve the accuracy of product recommendations for future purchases.

[0538] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0539] This invention relates to a personal shopping assistant system that integrates a customer emotion recognition system to improve the purchasing experience in e-commerce. The roles of four parties—server, terminal, user, and emotion engine—are described in the implementation of this system.

[0540] Server Role

[0541] The server retrieves customer purchase history, preference data, and browsing history from a database. In addition, it collects and analyzes the latest trend information from various sources on the internet. Using AI algorithms, it builds customer profiles based on the acquired data. Furthermore, it processes data received from the emotion engine to understand the customer's emotional state.

[0542] Specifically, the server adjusts product recommendations based on the output of the emotion engine. This adjustment includes factors such as price, brand, and category, and has the function to optimize suggestions according to the customer's emotions.

[0543] The role of the emotional engine

[0544] The emotion engine acquires data such as the user's facial expressions, voice tone, and input timing on the device to determine the user's current emotional state. These emotions are identified in various forms, such as stress, excitement, and interest, and transmitted to the server in real time. The emotion engine also analyzes past emotional patterns to understand the customer's long-term emotional trends, thereby improving the accuracy of future recommendations.

[0545] Terminal role

[0546] The device displays a list of recommended products sent from the server. In doing so, the device also takes into account the output of the emotion engine, providing an optimal interface display tailored to the user's emotional state. For example, if the user is relaxed, it might display bolder recommendations.

[0547] The device also has a function to receive user feedback. This feedback is sent to a server and used to make future suggestions.

[0548] User roles

[0549] Users can view recommended products on their devices and receive optimal product information based on their emotions. For example, if a user is feeling anxious, the system can recommend products of consistent quality. Users can experience recommendations that adapt to their changing emotions and ultimately purchase products that suit their preferences.

[0550] Overall, this system can significantly improve the customer experience in e-commerce by leveraging emotion recognition technology. For example, it can enhance the quality of the user experience by avoiding re-proposing products that the user has previously expressed negative emotions about.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] The server retrieves the user's past transaction history, preference data, and browsing history from a database. It also collects the latest data from various online sources, including social media and trend information.

[0554] Step 2:

[0555] The emotion engine activates, recognizing the user's current emotional state in real time through facial recognition and voice tone analysis on the device. This allows the user's level of relaxation and stress to be quantified.

[0556] Step 3:

[0557] The server uses an AI algorithm to analyze collected preference data and emotional data provided by the emotion engine. This analysis constructs a product profile that is tailored to the user's emotional state.

[0558] Step 4:

[0559] Based on the established profile, the server collects information from multiple e-commerce sites and identifies recommended products tailored to the user's emotional state. It also obtains price and inventory information in real time to provide more advantageous choices.

[0560] Step 5:

[0561] The server takes into account promotional information and valid coupons, and adjusts prices according to the user's emotional state. It then sends a list of recommended products, including these adjustments, to the user's device.

[0562] Step 6:

[0563] The device displays a list of recommended products received by the user. The display method is customized according to the user's mood; an intuitive design is used when the user is relaxed, while a simple design with less information is used when the user is stressed.

[0564] Step 7:

[0565] Users view details of recommended products through their devices and decide whether or not to proceed with a purchase. User feedback and analysis results are sent to the server and used to improve the recommendation system for future updates.

[0566] Step 8:

[0567] The device notifies users of new trending information and recommended products, ensuring they always receive the latest information. The timing and content of notifications are also optimized based on sentiment data.

[0568] (Example 2)

[0569] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0570] In today's e-commerce environment, there is a demand for optimal product recommendations that cater to the diverse preferences and emotions of customers. However, existing systems typically rely on fixed algorithms and are unable to respond flexibly to the emotions and real-time trends of individual customers. This makes it difficult to quickly and appropriately suggest products that customers want, resulting in a challenge in improving the purchasing experience.

[0571] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0572] In this invention, the server includes means for acquiring information on a customer's past activities, means for analyzing the acquired information and suggesting the most suitable products based on the customer's preferences, and means for analyzing information from external media collected in real time and identifying new products that will interest the customer. This enables flexible product suggestions that cater to the diverse preferences and emotions of customers.

[0573] "Customer past activity information" refers to the customer's past purchase history and online activity history.

[0574] "A means of analyzing acquired information and proposing the optimal product based on customer preferences" refers to a method of analyzing collected customer data and selecting products that are suitable for the user's interests and preferences.

[0575] "A method for analyzing information collected in real time from external media to identify new products that will attract customer interest" refers to a method of instantly acquiring the latest trends and fashion information from external data sources and selecting products that will attract interest based on that information.

[0576] "Means of acquiring and analyzing a user's biometric information to determine the customer's emotional state" refers to a method of acquiring biometric data such as the user's facial expressions and tone of voice, and analyzing it to evaluate their current emotions.

[0577] "Means of adjusting and optimizing product suggestions based on emotional state" refers to technologies that modify suggestions according to the user's emotions to show the most suitable product.

[0578] "Means of notifying the customer's device of recommended product information" refers to a mechanism that transmits selected product information from the server directly to the user's device.

[0579] "Means of dynamically changing the output interface according to the user's emotional state" refers to technologies that change the design and content of the displayed interface based on the user's emotions.

[0580] This invention provides a personal shopping assistant system that uses emotion recognition technology to improve the customer purchasing experience. The system mainly consists of a server, a terminal, a user, and an emotion recognition engine.

[0581] The server retrieves data from databases and external information sources to aggregate past customer activity information. This process involves extracting customer data by executing SQL queries using Python and employing web scraping techniques to obtain the latest trend information from external websites. The server also analyzes the retrieved data using machine learning frameworks (such as TensorFlow) to analyze customer preferences. This allows the server to suggest products optimized for each customer.

[0582] The emotion recognition engine acquires biometric information using the camera and microphone on the user's device and determines the user's emotional state. This data is transmitted to the server in real time. By using libraries such as OpenCV to extract feature points of facial expressions and analyzing emotions with a dedicated algorithm, the engine identifies the user's current emotion.

[0583] The device displays products recommended by the server in the user interface. This display also includes emotion recognition data, and the optimal interface is dynamically adjusted according to the user's emotions. The device uses HTML and JavaScript to display product information and changes the interface's color and layout according to the user's emotional state.

[0584] For example, if the emotion recognition engine determines that the user is in a relaxed state, the server will notify the device of recommendations for bright colors or new brands of products. The device then collects feedback from the user and forwards it to the server, which is used to improve the accuracy of future recommendations.

[0585] An example of a prompt message is, "Create a program that generates customer profiles using Python and TensorFlow." Such a system configuration makes it possible to quickly and effectively provide product recommendations tailored to individual customers.

[0586] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0587] Step 1:

[0588] The server retrieves past customer activity information from the database. Using the customer ID as input, it executes SQL queries to extract purchase and browsing history. The output includes a list of the customer's purchased items and browsing history. Specifically, it uses the Python SQLalchemy library to connect to the database and execute queries.

[0589] Step 2:

[0590] The server analyzes the acquired data and profiles customer preferences using an AI algorithm. It uses the output from step 1 as input and performs clustering and pattern recognition through a machine learning framework (e.g., TensorFlow). The output generates individual customer profiles and recommended product lists. Specifically, it uses principal component analysis and K-means algorithms to organize the data and classify customer behavior patterns.

[0591] Step 3:

[0592] The emotion recognition engine acquires biometric information from the user's device. As input, it captures the user's face and voice data in real time from a webcam and microphone. The output is an analysis result indicating the user's current emotional state. Specifically, it uses the OpenCV library to extract facial feature points and a voice analysis algorithm to determine tone.

[0593] Step 4:

[0594] The server receives emotional data and adjusts product recommendations based on those emotions. It uses the recommended product list from step 2 and the emotional analysis results from step 3 as input. After data processing, optimized product recommendations are generated as output. Specifically, it quantifies emotional states and adjusts the priority and category of products based on these quantifications.

[0595] Step 5:

[0596] The terminal displays an optimized product list sent from the server in its user interface. It receives a recommended list from the server as input and displays it on the screen using HTML and JavaScript. The output is product information that visually appeals to the user. Specifically, it performs coloring and layout adjustments based on sentiment analysis results.

[0597] Step 6:

[0598] Users review product suggestions and provide feedback via their devices. They submit their opinions based on the product information displayed on their devices as input, and this feedback is sent to the server as output. Specifically, users submit comments and ratings through a dedicated feedback input form.

[0599] This entire process enables the system to offer personalized product suggestions to individual customers and provide an emotionally resonant shopping experience.

[0600] (Application Example 2)

[0601] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0602] In recent years, the use of e-commerce has surged, creating a demand for providing customers with a comfortable shopping experience. However, existing systems struggle to provide flexible product recommendations that take customer emotions into account, potentially leading to customer stress and dissatisfaction. Solutions to these problems are needed.

[0603] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0604] In this invention, the server includes means for acquiring past customer information, means for analyzing the acquired information and recommending the most suitable products based on the customer's preferences, and means for collecting user emotional information and recommending products based on those emotions to improve the customer experience. This makes it possible to recommend products that take the customer's emotional state into account, thereby providing a more personalized purchasing experience.

[0605] "Past customer information" refers to data on a customer's transaction history and preferences that they have acquired to date.

[0606] "Optimal products based on preferences" refers to products that suit the individual interests and preferences of the customer.

[0607] An "e-commerce platform" refers to a digital environment for selling goods or services online.

[0608] "Sales promotion information" refers to various types of information used to promote the sale of products and services.

[0609] A "terminal" refers to a device used by a customer to receive information and perform operations.

[0610] "Emotional information" refers to data that indicates a customer's current emotional state, and is obtained based on facial expressions, voice, and other physiological responses.

[0611] A "personalized shopping experience" refers to a shopping experience that provides the most relevant information and services to each individual customer.

[0612] To implement this invention, a server is central to the system. The server retrieves past customer transaction information and preference data from a database and uses this to build a customer profile. The server also receives customer emotion data transmitted from the emotion engine and performs calculations in real time. This allows the system to recommend the most suitable products while considering the customer's emotional state. Specifically, the server implements AI algorithms using programming languages ​​such as Python, and emotion recognition software such as Microsoft Azure Face API or Google Cloud Speech-to-Text can be used.

[0613] The device is responsible for displaying product information recommended by the server to the user. This device could be a smartphone or tablet, allowing the user to actually view product information and receive emotion-based recommendations. The device also utilizes the smartphone's camera and microphone to collect the user's facial expressions and voice, and transmits this information to the emotion engine.

[0614] Users can review product information provided through their device and select products that fit their current emotional state. This enables a personalized experience based on emotions, such as recommending relaxing products if the user is stressed, or new or trendy products if their curiosity is heightened. For example, if the emotional state is determined to be "stressed," the prompt might read, "What relaxing products would you recommend when the user is feeling stressed?"

[0615] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0616] Step 1:

[0617] The server retrieves past customer transaction information and preference data from the database. Based on this input data, it performs data processing and statistical analysis to build a customer profile, and outputs it as profile data.

[0618] Step 2:

[0619] The user's device uses its camera and microphone to capture the user's facial expressions and voice data in real time and transmit it to the emotion engine. The input is the user's facial expressions and voice, and the output is emotion data. This data is analyzed to determine the user's emotional state through an emotion recognition algorithm.

[0620] Step 3:

[0621] The emotion engine determines the user's emotional state based on the received facial and audio data and sends the result to the server. The input is facial and audio data for emotion analysis, and the output is data indicating the emotional state. This process is performed using an AI model.

[0622] Step 4:

[0623] The server combines customer profiles and emotional state data and uses an AI algorithm to generate optimal product recommendations. The input is profile data and emotional state data, and the output is a list of recommended products. This step includes data integration and analysis, as well as the utilization of a generative AI model.

[0624] Step 5:

[0625] The terminal displays a list of recommended products sent from the server to the user. This screen display receives data as input to select the interface best suited to the user's emotional state and outputs product information that is visually optimized for the user.

[0626] Step 6:

[0627] The user reviews the recommended products displayed on their device and selects the product that best suits their feelings and preferences. By making a final purchase choice, the user provides their preference data to the system as input and sends it to the server as feedback.

[0628] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0629] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0630] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0631] [Fourth Embodiment]

[0632] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0633] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0634] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0635] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0636] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0637] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0638] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0639] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0640] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0641] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0642] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0643] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0644] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0645] This invention provides an AI-powered personal shopping assistant system to improve the customer purchasing experience in the field of e-commerce. The roles of the server, terminal, and user are described in the implementation of this system.

[0646] Server Role

[0647] The server plays a central role in the system, handling all data processing and analysis. First, it retrieves customers' past transaction history, preference data, and browsing history from the database. Based on this data, it uses AI algorithms to build customer profiles and analyze individual preferences and past purchase patterns. Furthermore, the server collects real-time trend information from the internet and analyzes this information to identify recommended products.

[0648] The server also utilizes APIs from multiple e-commerce sites to collect price and inventory information for identified products. This allows it to automatically identify the most advantageous pricing for customers. It retrieves promotional information and coupons from its database and adjusts prices to ensure the best possible deal.

[0649] Terminal role

[0650] The terminal's role is to present recommended product information sent from the server to the user. The terminal's interface is interactive, displaying detailed information such as product descriptions, pricing, and coupon application status. The terminal also sends user feedback and conversational information to the server, which is used to improve the accuracy of future recommendations.

[0651] It features a notification function, allowing users to set up notifications to receive alerts under specific conditions. For example, users can receive notifications when the price of a particular product drops or when a new campaign starts.

[0652] User roles

[0653] Users access the system daily through their devices. They can view recommended products and access detailed information on their devices. Users make the final decision on whether to purchase the recommended products and complete their orders through the platform.

[0654] For example, if a user has frequently purchased outdoor equipment in the past, the server can use that data to notify the user's device of new product releases and sales information on related items, helping the user enjoy a more advantageous shopping experience. In this way, the system of the present invention can make customer purchasing behavior more efficient and satisfying.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] The server retrieves customers' past transaction history, preference data, and browsing history from a database. In addition, it collects the latest trend information from social media and news sites on the internet.

[0658] Step 2:

[0659] The server analyzes the acquired data using AI algorithms to build a customer preference profile. This profile includes the customer's preferred brands, product categories, price range, and purchase frequency.

[0660] Step 3:

[0661] The server identifies the most suitable recommended products for the customer based on the established preference profile. It also analyzes trend information collected during this process to select the most relevant products.

[0662] Step 4:

[0663] The server collects information on identified products from multiple e-commerce sites and compares prices and inventory information. This allows it to list products that are advantageous to the customer.

[0664] Step 5:

[0665] The server checks promotional information and coupons, automatically applies them to the most suitable products, and adjusts prices accordingly. Based on these adjustments, it ultimately determines the product list to present to the customer.

[0666] Step 6:

[0667] The server sends the final list of recommended products to the terminal. The terminal displays the received information to the user and provides product descriptions and pricing information through its interface.

[0668] Step 7:

[0669] Users can view recommended products displayed on their device and access detailed information. If a user is interested in a product, they can proceed directly to the purchase page.

[0670] Step 8:

[0671] User feedback and purchase history are sent to the server via the device. The server uses this information to learn how to improve the accuracy of future recommendations.

[0672] Step 9:

[0673] The device notifies users of price changes and new promotional information for specific products based on real-time notification settings. This feature allows users to always stay up-to-date.

[0674] (Example 1)

[0675] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0676] In modern e-commerce, there is a demand for product recommendations tailored to individual customer preferences. However, existing systems have not been able to adequately achieve highly accurate personalized recommendations and have struggled to respond to real-time price strategies and demand changes. Therefore, the challenge is to provide customers with a more personalized, timely, and optimal purchasing experience.

[0677] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0678] In this invention, the server includes means for obtaining a customer's past transaction history, preference data, and browsing history from a database; means for constructing an individual customer profile using a generative AI model based on the obtained data; and means for analyzing trend information obtained from multiple data sources in real time to identify new products suitable for the customer. This makes it possible to provide personalized product recommendations for each customer and to provide optimal product information in response to ever-changing consumer trends.

[0679] A "database" is a digital store that systematically organizes information so that it can be efficiently accessed and managed later.

[0680] A "generative AI model" is an algorithm that uses artificial intelligence to learn patterns from large amounts of data and makes predictions and decisions based on new data.

[0681] A "profile" is a collection of detailed information about an individual customer, including their preferences and behavioral patterns, which enables personalized product recommendations.

[0682] "Trend information" refers to information about the trends of products and services that are gaining popularity at a particular time, and is used to identify new products that will attract customer interest.

[0683] An "API" is an interface for exchanging information and functions between different software programs, and a means of integrating with third-party services.

[0684] "GUI" is an abbreviation for Graphical User Interface, which is a user interface that can be operated intuitively using visual elements.

[0685] "Feedback" refers to the opinions and reactions provided by users after they have used a product, and it serves as a valuable source of information for improving the system.

[0686] "Real-time" means that a computer system has the ability to react instantly and process data without time delay.

[0687] The system in this invention provides an optimal purchasing experience in e-commerce through the mutual cooperation of a server, terminal, and user. Specific embodiments will be described below.

[0688] The server plays a central role in the system, efficiently retrieving customers' past transaction history, preference data, and browsing history from the database. This involves using a database management system and methods such as SQL queries to aggregate the desired data. The retrieved data is then used to build and refine individual customer profiles using a generation AI model, enabling the provision of products tailored to individual preferences and behavioral patterns.

[0689] Furthermore, the server collects trend information in real time via the internet. This trend information is continuously obtained using scraping technology to grasp the latest trends, and by analyzing it, new products in the market are identified. Another important function is the ability to obtain and compare product prices and inventory information in real time using APIs from online marketplaces.

[0690] The terminals that present products to users visually display recommended product information from the server. GUI technology is used to provide an intuitive interface for customers. For example, sending notifications when prices drop can further pique user interest.

[0691] Users utilize the system daily through their devices to select products, provide feedback, and make purchase decisions. This feedback is sent to the server and used to improve the accuracy of future recommendations by the generated AI model.

[0692] Thus, the system of the present invention is designed to make customer purchasing behavior more efficient and fulfilling, with servers and terminals functioning harmoniously in providing information and understanding customer needs.

[0693] Example of a prompt:

[0694] "Recommend new products related to items that customers have frequently purchased in the past. Use an AI algorithm that considers the latest trends and pricing information to suggest the best products for each customer."

[0695] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0696] Step 1:

[0697] The server retrieves the customer's past transaction history, preference data, and browsing history from the database. It uses SQL queries to search for the necessary data and temporarily loads it into data processing memory. The retrieved data is used as input to a generative AI model. The output at this stage is the input dataset for creating customer profiles.

[0698] Step 2:

[0699] The server uses a generated AI model to construct customer profiles based on the data acquired in Step 1. Specifically, it analyzes the data using machine learning algorithms to reveal customer preferences and purchasing patterns. As output, a detailed profile for each customer is generated and used as the basis data for the next analysis step.

[0700] Step 3:

[0701] The server analyzes real-time trend information obtained from the internet and uses it to recommend products based on customer profiles. By collecting data using scraping techniques and analyzing its contents, it identifies trending products suitable for each customer. The output of this step is a personalized list of recommended products.

[0702] Step 4:

[0703] The server collects price and inventory information for products from online marketplaces via an API. This collected data is analyzed by a real-time price comparison algorithm and processed to enable customers to make advantageous product selections. The output is a list containing the best prices and inventory information for recommended products.

[0704] Step 5:

[0705] The terminal displays recommended product information received from the server on its user interface. GUI technology is used to present the product information in a way that users can intuitively understand. For example, notification features are used to communicate price changes and campaign information to the user in a way that encourages purchase decisions. The output is a simple and easy-to-understand product display screen for the user.

[0706] Step 6:

[0707] Through the steps described above, the user reviews the products displayed on their device and provides feedback. The device sends this feedback to the server, which is used to train the generating AI model. This improves the accuracy of future recommendations. As output, the collected feedback data is stored on the server.

[0708] Step 7:

[0709] The user selects recommended products and completes the purchase process through the terminal. The server securely performs the necessary payment processing using security protocols based on the entered order information. The output is a confirmation and completion message from the user.

[0710] (Application Example 1)

[0711] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0712] In e-commerce, there is a growing need to provide customers with a more personalized shopping experience and increase their purchasing intent. Furthermore, the information overload in the market makes it difficult to select the optimal product, creating a need for systems that can provide customers with an efficient and satisfying shopping experience.

[0713] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0714] In this invention, the server includes means for acquiring customer transaction history and preference information, means for analyzing the acquired information to build a customer profile and recommend products based on preferences, means for referencing information from multiple e-commerce platforms to present more profitable product information, means for automatically adjusting product prices based on sales promotion information, means for notifying the user's terminal of the recommended product information, and means for analyzing trends acquired in real time to identify new products that will attract customer interest. This makes it possible to provide customers with the most suitable products in a timely manner and to personalize and streamline the purchasing experience.

[0715] "Customer transaction history" refers to records of products a user has purchased in the past, and by analyzing this data, it is used to understand purchasing trends.

[0716] "Preference information" refers to data about customers' preferences and interests, and is used to recommend products that are suitable for each customer.

[0717] An "e-commerce platform" is an online system used to buy and sell goods and services over the internet.

[0718] "Methods for recommending products" refer to technologies that suggest the most suitable products to users based on their preferences and past purchase history.

[0719] "Sales promotion information" refers to information about promotions that increase customer purchasing intent, such as coupons and discounts.

[0720] "Methods for automatically adjusting prices" refer to systems that automatically change the price of a product based on sales promotion information and market trends.

[0721] "Means of notifying the device" refers to messaging functions for providing information to customers in real time.

[0722] "Methods for analyzing trends" refer to technologies that analyze market and consumer trends in real time and provide customers with new information based on this analysis.

[0723] To realize this system, the server, terminals, and users must cooperate and fulfill their respective roles. The server first retrieves customer transaction history and preference information from a database and analyzes it using an AI algorithm. This analysis makes it possible to build customer profiles and recommend products based on preferences. Furthermore, the server collects information from multiple e-commerce platforms to form the basis for providing optimal product information.

[0724] Next, the server sends recommended product information to the terminal. The terminal presents this information to the user and collects user feedback using an interactive interface. The feedback information is sent to the server and used to improve the accuracy of product recommendations in the future. The terminal also has the function of notifying the user of price changes and promotion information in real time.

[0725] The server analyzes trend information in real time and uses this to identify new products that will attract customer interest. Data analysis tools and AI models are used in this analysis to provide customers with the latest and most useful information. Specifically, cloud computing technology (such as AWS) is used, and MySQL is used for database management. TensorFlow and scikit-learn are utilized for AI algorithms.

[0726] For example, if a user has previously purchased sports-related products, the server uses that data to send push notifications to their device about newly released sports equipment and ongoing campaigns. This allows users to efficiently receive more accurate product information, thereby promoting purchasing behavior. Prompts such as, "Based on the user's purchase history and current trends, please recommend the three most relevant products," are supplied to the generating AI model, enabling personalized product recommendations.

[0727] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0728] Step 1:

[0729] The server retrieves customer transaction history and preference information from a database. It receives a user ID as input and extracts historical transaction data and preference patterns associated with this ID. As output, it generates a set of customer transaction history and preference data. This data is retrieved using a database management system (such as MySQL).

[0730] Step 2:

[0731] The server analyzes acquired transaction history and preference information to build customer profiles. It receives transaction history and preference data as input and performs analysis using an AI algorithm (TensorFlow or scikit-learn). The output is profile data that shows the customer's interests and tendencies. This profile is used for personalized product recommendations.

[0732] Step 3:

[0733] The server collects product information from multiple e-commerce platforms. It queries each platform using API keys and authentication information as input. The output is a list of product information for each platform. This forms the basis for the product information presented to the user.

[0734] Step 4:

[0735] The server recommends personalized products based on customer profiles and collected product information. Using customer profiles and product information as input, the AI ​​model generates prompts (e.g., "Recommend the three most relevant products based on the user's purchase history and current trends."). The output is a list of recommended products tailored to the user.

[0736] Step 5:

[0737] The server sends the generated recommendation list to the terminal, and the terminal notifies the user. The server receives the recommendation list as input and communicates the information to the user in real time through the terminal's notification function. The output provides the user with information on recommended products. The user can then consider purchasing based on this information.

[0738] Step 6:

[0739] Users view detailed information through their device and enter purchase feedback. The device receives user feedback and dialogue information as input and sends it to the server. The output is feedback data, which is used to improve the accuracy of product recommendations for future purchases.

[0740] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0741] This invention relates to a personal shopping assistant system that integrates a customer emotion recognition system to improve the purchasing experience in e-commerce. The roles of four parties—server, terminal, user, and emotion engine—are described in the implementation of this system.

[0742] Server Role

[0743] The server retrieves customer purchase history, preference data, and browsing history from a database. In addition, it collects and analyzes the latest trend information from various sources on the internet. Using AI algorithms, it builds customer profiles based on the acquired data. Furthermore, it processes data received from the emotion engine to understand the customer's emotional state.

[0744] Specifically, the server adjusts product recommendations based on the output of the emotion engine. This adjustment includes factors such as price, brand, and category, and has the function to optimize suggestions according to the customer's emotions.

[0745] The role of the emotional engine

[0746] The emotion engine acquires data such as the user's facial expressions, voice tone, and input timing on the device to determine the user's current emotional state. These emotions are identified in various forms, such as stress, excitement, and interest, and transmitted to the server in real time. The emotion engine also analyzes past emotional patterns to understand the customer's long-term emotional trends, thereby improving the accuracy of future recommendations.

[0747] Terminal role

[0748] The device displays a list of recommended products sent from the server. In doing so, the device also takes into account the output of the emotion engine, providing an optimal interface display tailored to the user's emotional state. For example, if the user is relaxed, it might display bolder recommendations.

[0749] The device also has a function to receive user feedback. This feedback is sent to a server and used to make future suggestions.

[0750] User roles

[0751] Users can view recommended products on their devices and receive optimal product information based on their emotions. For example, if a user is feeling anxious, the system can recommend products of consistent quality. Users can experience recommendations that adapt to their changing emotions and ultimately purchase products that suit their preferences.

[0752] Overall, this system can significantly improve the customer experience in e-commerce by leveraging emotion recognition technology. For example, it can enhance the quality of the user experience by avoiding re-proposing products that the user has previously expressed negative emotions about.

[0753] The following describes the processing flow.

[0754] Step 1:

[0755] The server retrieves the user's past transaction history, preference data, and browsing history from a database. It also collects the latest data from various online sources, including social media and trend information.

[0756] Step 2:

[0757] The emotion engine activates, recognizing the user's current emotional state in real time through facial recognition and voice tone analysis on the device. This allows the user's level of relaxation and stress to be quantified.

[0758] Step 3:

[0759] The server uses an AI algorithm to analyze collected preference data and emotional data provided by the emotion engine. This analysis constructs a product profile that is tailored to the user's emotional state.

[0760] Step 4:

[0761] Based on the established profile, the server collects information from multiple e-commerce sites and identifies recommended products tailored to the user's emotional state. It also obtains price and inventory information in real time to provide more advantageous choices.

[0762] Step 5:

[0763] The server takes into account promotional information and valid coupons, and adjusts prices according to the user's emotional state. It then sends a list of recommended products, including these adjustments, to the user's device.

[0764] Step 6:

[0765] The device displays a list of recommended products received by the user. The display method is customized according to the user's mood; an intuitive design is used when the user is relaxed, while a simple design with less information is used when the user is stressed.

[0766] Step 7:

[0767] Users view details of recommended products through their devices and decide whether or not to proceed with a purchase. User feedback and analysis results are sent to the server and used to improve the recommendation system for future updates.

[0768] Step 8:

[0769] The device notifies users of new trending information and recommended products, ensuring they always receive the latest information. The timing and content of notifications are also optimized based on sentiment data.

[0770] (Example 2)

[0771] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0772] In today's e-commerce environment, there is a demand for optimal product recommendations that cater to the diverse preferences and emotions of customers. However, existing systems typically rely on fixed algorithms and are unable to respond flexibly to the emotions and real-time trends of individual customers. This makes it difficult to quickly and appropriately suggest products that customers want, resulting in a challenge in improving the purchasing experience.

[0773] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0774] In this invention, the server includes means for acquiring information on a customer's past activities, means for analyzing the acquired information and suggesting the most suitable products based on the customer's preferences, and means for analyzing information from external media collected in real time and identifying new products that will interest the customer. This enables flexible product suggestions that cater to the diverse preferences and emotions of customers.

[0775] "Customer past activity information" refers to the customer's past purchase history and online activity history.

[0776] "A means of analyzing acquired information and proposing the optimal product based on customer preferences" refers to a method of analyzing collected customer data and selecting products that are suitable for the user's interests and preferences.

[0777] "A method for analyzing information collected in real time from external media to identify new products that will attract customer interest" refers to a method of instantly acquiring the latest trends and fashion information from external data sources and selecting products that will attract interest based on that information.

[0778] "Means of acquiring and analyzing a user's biometric information to determine the customer's emotional state" refers to a method of acquiring biometric data such as the user's facial expressions and tone of voice, and analyzing it to evaluate their current emotions.

[0779] "Means of adjusting and optimizing product suggestions based on emotional state" refers to technologies that modify suggestions according to the user's emotions to show the most suitable product.

[0780] "Means of notifying the customer's device of recommended product information" refers to a mechanism that transmits selected product information from the server directly to the user's device.

[0781] "Means of dynamically changing the output interface according to the user's emotional state" refers to technologies that change the design and content of the displayed interface based on the user's emotions.

[0782] This invention provides a personal shopping assistant system that uses emotion recognition technology to improve the customer purchasing experience. The system mainly consists of a server, a terminal, a user, and an emotion recognition engine.

[0783] The server retrieves data from databases and external information sources to aggregate past customer activity information. This process involves extracting customer data by executing SQL queries using Python and employing web scraping techniques to obtain the latest trend information from external websites. The server also analyzes the retrieved data using machine learning frameworks (such as TensorFlow) to analyze customer preferences. This allows the server to suggest products optimized for each customer.

[0784] The emotion recognition engine acquires biometric information using the camera and microphone on the user's device and determines the user's emotional state. This data is transmitted to the server in real time. By using libraries such as OpenCV to extract feature points of facial expressions and analyzing emotions with a dedicated algorithm, the engine identifies the user's current emotion.

[0785] The device displays products recommended by the server in the user interface. This display also includes emotion recognition data, and the optimal interface is dynamically adjusted according to the user's emotions. The device uses HTML and JavaScript to display product information and changes the interface's color and layout according to the user's emotional state.

[0786] For example, if the emotion recognition engine determines that the user is in a relaxed state, the server will notify the device of recommendations for bright colors or new brands of products. The device then collects feedback from the user and forwards it to the server, which is used to improve the accuracy of future recommendations.

[0787] An example of a prompt message is, "Create a program that generates customer profiles using Python and TensorFlow." Such a system configuration makes it possible to quickly and effectively provide product recommendations tailored to individual customers.

[0788] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0789] Step 1:

[0790] The server retrieves past customer activity information from the database. Using the customer ID as input, it executes SQL queries to extract purchase and browsing history. The output includes a list of the customer's purchased items and browsing history. Specifically, it uses the Python SQLalchemy library to connect to the database and execute queries.

[0791] Step 2:

[0792] The server analyzes the acquired data and profiles customer preferences using an AI algorithm. It uses the output from step 1 as input and performs clustering and pattern recognition through a machine learning framework (e.g., TensorFlow). The output generates individual customer profiles and recommended product lists. Specifically, it uses principal component analysis and K-means algorithms to organize the data and classify customer behavior patterns.

[0793] Step 3:

[0794] The emotion recognition engine acquires biometric information from the user's device. As input, it captures the user's face and voice data in real time from a webcam and microphone. The output is an analysis result indicating the user's current emotional state. Specifically, it uses the OpenCV library to extract facial feature points and a voice analysis algorithm to determine tone.

[0795] Step 4:

[0796] The server receives emotional data and adjusts product recommendations based on those emotions. It uses the recommended product list from step 2 and the emotional analysis results from step 3 as input. After data processing, optimized product recommendations are generated as output. Specifically, it quantifies emotional states and adjusts the priority and category of products based on these quantifications.

[0797] Step 5:

[0798] The terminal displays an optimized product list sent from the server in its user interface. It receives a recommended list from the server as input and displays it on the screen using HTML and JavaScript. The output is product information that visually appeals to the user. Specifically, it performs coloring and layout adjustments based on sentiment analysis results.

[0799] Step 6:

[0800] Users review product suggestions and provide feedback via their devices. They submit their opinions based on the product information displayed on their devices as input, and this feedback is sent to the server as output. Specifically, users submit comments and ratings through a dedicated feedback input form.

[0801] This entire process enables the system to offer personalized product suggestions to individual customers and provide an emotionally resonant shopping experience.

[0802] (Application Example 2)

[0803] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0804] In recent years, the use of e-commerce has surged, creating a demand for providing customers with a comfortable shopping experience. However, existing systems struggle to provide flexible product recommendations that take customer emotions into account, potentially leading to customer stress and dissatisfaction. Solutions to these problems are needed.

[0805] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0806] In this invention, the server includes means for acquiring past customer information, means for analyzing the acquired information and recommending the most suitable products based on the customer's preferences, and means for collecting user emotional information and recommending products based on those emotions to improve the customer experience. This makes it possible to recommend products that take the customer's emotional state into account, thereby providing a more personalized purchasing experience.

[0807] "Past customer information" refers to data on a customer's transaction history and preferences that they have acquired to date.

[0808] "Optimal products based on preferences" refers to products that suit the individual interests and preferences of the customer.

[0809] An "e-commerce platform" refers to a digital environment for selling goods or services online.

[0810] "Sales promotion information" refers to various types of information used to promote the sale of products and services.

[0811] A "terminal" refers to a device used by a customer to receive information and perform operations.

[0812] "Emotional information" refers to data that indicates a customer's current emotional state, and is obtained based on facial expressions, voice, and other physiological responses.

[0813] A "personalized shopping experience" refers to a shopping experience that provides the most relevant information and services to each individual customer.

[0814] To implement this invention, a server is central to the system. The server retrieves past customer transaction information and preference data from a database and uses this to build a customer profile. The server also receives customer emotion data transmitted from the emotion engine and performs calculations in real time. This allows the system to recommend the most suitable products while considering the customer's emotional state. Specifically, the server implements AI algorithms using programming languages ​​such as Python, and emotion recognition software such as Microsoft Azure Face API or Google Cloud Speech-to-Text can be used.

[0815] The device is responsible for displaying product information recommended by the server to the user. This device could be a smartphone or tablet, allowing the user to actually view product information and receive emotion-based recommendations. The device also utilizes the smartphone's camera and microphone to collect the user's facial expressions and voice, and transmits this information to the emotion engine.

[0816] Users can review product information provided through their device and select products that fit their current emotional state. This enables a personalized experience based on emotions, such as recommending relaxing products if the user is stressed, or new or trendy products if their curiosity is heightened. For example, if the emotional state is determined to be "stressed," the prompt might read, "What relaxing products would you recommend when the user is feeling stressed?"

[0817] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0818] Step 1:

[0819] The server retrieves past customer transaction information and preference data from the database. Based on this input data, it performs data processing and statistical analysis to build a customer profile, and outputs it as profile data.

[0820] Step 2:

[0821] The user's device uses its camera and microphone to capture the user's facial expressions and voice data in real time and transmit it to the emotion engine. The input is the user's facial expressions and voice, and the output is emotion data. This data is analyzed to determine the user's emotional state through an emotion recognition algorithm.

[0822] Step 3:

[0823] The emotion engine determines the user's emotional state based on the received facial and audio data and sends the result to the server. The input is facial and audio data for emotion analysis, and the output is data indicating the emotional state. This process is performed using an AI model.

[0824] Step 4:

[0825] The server combines customer profiles and emotional state data and uses an AI algorithm to generate optimal product recommendations. The input is profile data and emotional state data, and the output is a list of recommended products. This step includes data integration and analysis, as well as the utilization of a generative AI model.

[0826] Step 5:

[0827] The terminal displays a list of recommended products sent from the server to the user. This screen display receives data as input to select the interface best suited to the user's emotional state and outputs product information that is visually optimized for the user.

[0828] Step 6:

[0829] The user reviews the recommended products displayed on their device and selects the product that best suits their feelings and preferences. By making a final purchase choice, the user provides their preference data to the system as input and sends it to the server as feedback.

[0830] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0831] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0832] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0833] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0834] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0835] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0836] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0837] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0838] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0839] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0840] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0841] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0842] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0843] 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.

[0844] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0845] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0846] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0847] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0848] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0849] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0850] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0851] The following is further disclosed regarding the embodiments described above.

[0852] (Claim 1)

[0853] Means for obtaining customers' past transaction history and preference data,

[0854] A means of analyzing acquired data and recommending the most suitable products based on customer preferences,

[0855] A means of comparing information from multiple e-commerce sites and providing more advantageous product information,

[0856] A method for automatically adjusting the price of products based on acquired sales promotion information,

[0857] A means of notifying customers of recommended product information on their devices,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, which includes means for accumulating customer conversation information and improving the accuracy of future product recommendations based on that information.

[0861] (Claim 3)

[0862] The system according to claim 1, comprising means for analyzing trend information acquired in real time and identifying new products that will attract customer interest.

[0863] "Example 1"

[0864] (Claim 1)

[0865] A means of obtaining a customer's past transaction history, preference data, and browsing history from a database,

[0866] A means of building individual customer profiles using an AI model based on acquired data,

[0867] A means of analyzing trend information obtained from multiple data sources in real time to identify new products suitable for customers,

[0868] A means of obtaining and comparing product prices and inventory information through the acquired electronic marketplace API,

[0869] A means of dynamically adjusting the price of products based on acquired sales promotion information and coupon information,

[0870] A means of notifying customer devices of recommended product information through an interactive interface,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, which includes means for accumulating customer feedback information and using that information to train an AI model to improve the accuracy of recommendations in the future.

[0874] (Claim 3)

[0875] The system according to claim 1, comprising means for identifying new products that are likely to attract customer interest using trend information and customer profiles acquired in real time.

[0876] "Application Example 1"

[0877] (Claim 1)

[0878] Means for obtaining customer transaction history and preference information,

[0879] A means of analyzing acquired information to build customer profiles and recommending products based on preferences,

[0880] A means of referencing information from multiple e-commerce platforms to present more profitable product information,

[0881] A method for automatically adjusting product prices based on sales promotion information,

[0882] A means of notifying the user's device of recommended product information,

[0883] A means of analyzing trends acquired in real time to identify new products that will attract customer interest,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, which includes means for accumulating customer conversation content and improving the accuracy of product recommendations for future purchases.

[0887] (Claim 3)

[0888] The system according to claim 1, comprising means for improving the shopping experience by linking and notifying users of personalized product recommendations and real-time promotional information.

[0889] "Example 2 of combining an emotion engine"

[0890] (Claim 1)

[0891] Means for obtaining information on a customer's past activities,

[0892] A means of analyzing acquired information and proposing the optimal product based on customer preferences,

[0893] A means of identifying new products that will attract customer interest by analyzing information collected in real time from external media,

[0894] In order to determine the emotional state of a customer, a means of acquiring and analyzing the user's biometric information,

[0895] A means of adjusting and optimizing product suggestions based on emotional states,

[0896] A means of notifying the customer's device of recommended product information,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, which includes means for accumulating customer feedback and using that information to improve the accuracy of future proposals.

[0900] (Claim 3)

[0901] The system according to claim 1, comprising means for dynamically changing the output interface according to the user's emotional state.

[0902] "Application example 2 when combining with an emotional engine"

[0903] (Claim 1)

[0904] Means of obtaining past customer information,

[0905] A means of analyzing acquired information and recommending the most suitable products based on customer preferences,

[0906] A means of comparing information from multiple e-commerce platforms and providing more advantageous product information,

[0907] A means of automatically adjusting product prices based on acquired sales promotion information,

[0908] A means of notifying customers of recommended product information on their devices,

[0909] A means of collecting user sentiment information, recommending products based on those sentiments, and improving the customer experience,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, which includes means for accumulating customer interaction information and improving the accuracy of future product recommendations based on that information.

[0913] (Claim 3)

[0914] The system according to claim 1, comprising means for analyzing trend information acquired in real time and identifying new products that will attract customer interest. [Explanation of Symbols]

[0915] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for obtaining customers' past transaction history and preference data, A means of analyzing acquired data and recommending the most suitable products based on customer preferences, A means of comparing information from multiple e-commerce sites and providing more advantageous product information, A method for automatically adjusting the price of products based on acquired sales promotion information, A means of notifying customers of recommended product information on their devices, A system that includes this.

2. The system according to claim 1, which includes means for accumulating customer conversation information and improving the accuracy of future product recommendations based on that information.

3. The system according to claim 1, comprising means for analyzing trend information acquired in real time and identifying new products that will attract customer interest.

Images