system

Abstract

We provide a system that enables accurate product recommendations. [Solution] A system comprising: means for acquiring user profile information stored in a database and analyzing the user's preferences and needs; means for receiving real-time environmental information from multiple sensor devices and understanding the user's context; means for analyzing image data provided by the user and identifying the product categories the user requires; means for searching a product database based on the preferences, needs, context, and product categories and generating a product recommendation list; means for providing an interactive interface to the user, explaining product information, and presenting information to promote purchase; and means for collecting user feedback, storing it in a database, and analyzing it.

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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 an e-commerce system, in the conventional approach where consumers search for products based on subjective knowledge and limited information, there is a problem that appropriate products that meet true needs cannot be found. Furthermore, there is also a problem that it is difficult to effectively reflect the user feedback obtained after purchase in the next purchase experience.

Means for Solving the Problems

[0005] This invention provides a means to enable accurate product recommendations by analyzing user preferences and needs based on user profile information stored in a database, and by analyzing real-time environmental information obtained from multiple sensor devices and image data provided by the user. This allows for product recommendations tailored to the user's preferences and current context. It also provides product information through an interactive interface to promote purchases. Within this process, the system collects user feedback, stores it in a database, and analyzes it to improve the accuracy of future recommendations.

[0006] A "database" is a system that systematically manages information and data, allowing for efficient access, searching, and updating.

[0007] "Profile information" refers to attribute data related to individual users, including age, gender, interests, and purchase history.

[0008] "Preferences" refer to specific tendencies or tastes regarding products and services that users enjoy.

[0009] "Needs" refer to items that indicate the demands and necessities that users have.

[0010] A "sensor device" is a device that detects physical or environmental elements, converts them into digital data, and transmits it.

[0011] "Real-time environmental information" refers to data that shows the user's current situation, including location information, temperature, and time.

[0012] "Image data" refers to digital data that includes visual information, such as products and related visual materials.

[0013] A "product category" is a standard used to classify products, grouping items based on specific attributes or uses.

[0014] A "product database" is a digital repository in which information about a specific product is systematically compiled.

[0015] A "product recommendation list" is a list of products presented by the system based on the user's needs and preferences, intended to encourage purchases.

[0016] An "interactive interface" is a platform that allows a system and a user to communicate with each other using natural language.

[0017] "Feedback" refers to evaluations and opinions about products and services received from users, and is information used to improve the system. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] Displays an emotion map on which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 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.

Mode for Carrying Out the Invention

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be of one type of arithmetic unit or a combination of a plurality of 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.

[0022] 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.

[0023] 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.

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention provides a method for recommending the most suitable products to users in an e-commerce system and improving the purchasing experience. Specific embodiments for carrying out this invention are described below.

[0040] The server retrieves user profile information stored in the database and analyzes user preferences and needs. This analysis includes sentiment and intent derived from the user's past search history and reviews, using natural language processing techniques. Furthermore, the server receives real-time environmental information from multiple sensor devices. This allows the server to understand the user's current context and incorporate this into the recommendation algorithm.

[0041] Furthermore, the terminal uploads image data provided by the user to the server. This data is analyzed using computer vision technology to help identify product categories and styles. In this way, by comprehensively considering the user's preferences, needs, real-time environmental information, and image data analysis results, the server selects the most suitable products and generates a recommendation list.

[0042] This recommendation list is presented to the user through an interactive, conversational interface. Through this interface, users can obtain detailed information about products and ask additional questions. The server confirms the user's purchasing intent through interaction and provides concierge-like support as needed.

[0043] After purchase, the server collects feedback from the user and stores it in a database. This feedback is analyzed using big data technology and used to improve the accuracy of recommendations for future purchases.

[0044] As a concrete example, let's assume a user is looking for a new smartphone. In this case, the server can recommend products suitable for the user's current location and communication environment in real time, while also considering the user's past purchase history and brand preferences. Furthermore, it can use images taken by the user to identify smartphones with the design and color they desire. This allows users to find products that meet their needs more accurately and quickly.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The user accesses the e-commerce site using their device and logs in. The user enters or selects their profile information and desired product criteria. This information is processed together with the user's past purchase history and preference data.

[0048] Step 2:

[0049] The server retrieves user profile information and historical data from the database. This allows it to analyze user preferences and purchasing patterns and identify potential needs.

[0050] Step 3:

[0051] The server receives real-time environmental information from the user via the terminal. This includes location information, device usage, and time of day. Based on this information, the server understands the user's current status.

[0052] Step 4:

[0053] Users upload reference images of products and event photos to the server using their devices. The server uses computer vision technology to analyze these images and identify product categories and styles.

[0054] Step 5:

[0055] The server integrates user preferences, needs, context, and image analysis results, and queries the relevant product database. Based on this data, the server generates a list of products best suited to the user.

[0056] Step 6:

[0057] The server presents the user with a generated list of product recommendations. Through an interactive interface, the server provides detailed explanations of the product's features and appeal, offering information to increase the user's desire to purchase.

[0058] Step 7:

[0059] Users can view product details and compare options through the interface. Users can also ask the server further questions as needed to receive assistance in their purchasing decision.

[0060] Step 8:

[0061] When a user purchases a product, the server records the purchase information and sends a confirmation email. The server then sends a message to the user to collect post-purchase feedback.

[0062] Step 9:

[0063] After using the product, users enter feedback and send it to the server via their device. The server analyzes this feedback and stores it in a database.

[0064] Step 10:

[0065] The server uses the collected feedback and purchase data to update its preference model and improve the accuracy of product suggestions in the next recommendation process.

[0066] (Example 1)

[0067] 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."

[0068] Traditional e-commerce systems could only suggest products based on users' purchase history and basic preferences, making it difficult to provide accurate recommendations that considered users' real-time situations and detailed tastes. Furthermore, it was difficult for users to quickly find products that met their needs, resulting in a less-than-satisfactory shopping experience. Additionally, effective use of user feedback to improve the accuracy of future recommendations was insufficient.

[0069] 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.

[0070] In this invention, the server includes means for acquiring user identification information stored in a data set and analyzing the user's preferences and needs; means for receiving real-time situational information from multiple detection devices and understanding the user's situation; and means for analyzing visual data provided by the user and identifying the product category the user is seeking. This enables product suggestions that comprehensively consider diverse user information, making it possible to provide a more personalized purchasing experience.

[0071] A "data set" refers to a collection of information that is systematically stored and can be searched or retrieved later.

[0072] "User" refers to an individual or legal entity that uses the system, and the subject whose preferences and behavioral data are managed as a profile.

[0073] "Identification information" refers to data used to identify a user, and includes information that is associated with an individual's preferences and past behavioral history.

[0074] "Preference" refers to the individual user's tastes and preferences for products and services, and the factors that influence their decision-making.

[0075] "Necessity" refers to the demands and conditions that users have for a product or service, and is a need based on their intention to purchase.

[0076] A "detection device" refers to a device such as a sensor that senses the user's surroundings and actions in real time and collects that information.

[0077] "Situational information" refers to real-time background information such as the user's current location, surrounding environmental conditions, and behavioral state.

[0078] "Visual data" refers to photographs and image information provided by users, and includes information about the visual characteristics of a product.

[0079] "Product classification" refers to the criteria used to categorize products based on their type and characteristics.

[0080] A "product collection" refers to the entire set of product information managed within the system, including data used to suggest products to users.

[0081] A "product suggestion list" refers to a list of products selected based on the user's preferences and needs, and is a proposal document intended to promote purchases.

[0082] "Interactive display means" refers to a form of interface that allows users to interactively view and manipulate product information.

[0083] "Evaluation information" refers to feedback and reviews that users have given to products and services, and includes information that contributes to improving the accuracy of future recommendations.

[0084] This invention provides a method for suggesting optimal products to users and improving the purchasing experience in an e-commerce system.

[0085] The server first retrieves user identification information stored in a data set. A database management system is used for this process. Next, the server utilizes natural language processing techniques using Python to analyze the user's preferences and needs. This makes it possible to extract sentiments and intentions derived from past reviews and search history.

[0086] Furthermore, the server receives real-time status information from multiple detection devices. This information includes environmental conditions and communication status at the user's current location. Real-time data streaming technologies such as Apache® Kafka are used to ensure immediacy.

[0087] The terminal uploads visual data captured by the user, such as photos taken with a smartphone, to the server. The server uses computer vision technologies such as OpenCV to analyze the images and identify product categories. This makes it possible to understand the user's preferred designs and colors.

[0088] The server integrates all this information and generates a list of optimal product suggestions by running a machine learning model using TENSORFLOW®. This list is presented to the user through an interactive display using JavaScript® and React. Users can use this interface to view product information and ask questions.

[0089] Furthermore, after a user makes a purchase, the server collects user feedback and stores it in a data set. This feedback data is analyzed using Hadoop and Spark and used to improve the accuracy of future recommendation processes.

[0090] As a concrete example, consider a user looking for a new laptop. The server can consider the user's past purchase history and usage patterns to recommend a product suitable for the network conditions in the user's location. Furthermore, based on images of the laptop the user has taken, it can identify the user's preferred design and color. In this way, the user can quickly find a product that meets their needs.

[0091] An example of a prompt statement to be used as input to a generative AI model is: "Please provide an algorithm for recommending products on an e-commerce platform that utilizes user history and real-time data."

[0092] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0093] Step 1:

[0094] The server retrieves user identification information from the data set. This information includes the user's past purchase history, search history, and review history. Based on the user ID as input, it executes SQL queries to extract relevant information. The output is a dataset for identifying the user's preferences and needs. The server uses this information to analyze the user's preferences and purchase motivations.

[0095] Step 2:

[0096] The server receives real-time contextual information from multiple detection devices. This includes the user's current location, communication status, and weather information. Real-time data obtained through the API serves as supplementary information to understand the user's context. The input contextual data is collected by the server, and the context model is updated as output.

[0097] Step 3:

[0098] Users use their devices to capture visual data of products they are interested in and upload it to the server. For example, they might take a picture of a laptop design with their smartphone. The server receives the input image data and analyzes it using the OpenCV library. The output includes product classification and style information, which the server uses to understand the user's visual preferences.

[0099] Step 4:

[0100] The server integrates the analyzed user preferences, needs, context, and product categories, and generates a list of optimal product suggestions using a machine learning model based on TensorFlow. The input dataset consists of the information obtained in the previous steps. The list of product suggestions generated as a result of the model's calculations is output and used to increase the user's purchasing intent.

[0101] Step 5:

[0102] Users view a list of product suggestions via an interactive display using JavaScript and React on their device. This interface allows them to view detailed product information and ask questions. The server receives user input and provides additional information in real time.

[0103] Step 6:

[0104] Users provide transaction feedback information to the server after purchasing a product. This feedback is uploaded to the server as comments and rating scores. The server stores this data in a data set and performs analysis using Hadoop and Spark. This analysis generates output data to improve the accuracy of future recommendations.

[0105] (Application Example 1)

[0106] 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."

[0107] Traditional e-commerce systems often rely on users' past purchase history and general preferences for product recommendations, failing to fully utilize real-time contextual and image-based style analysis. This makes it difficult for users to quickly and accurately find products that suit their current needs and surrounding environment. Furthermore, the lack of advanced recommendation systems utilizing generative AI models for prompting is also a problem.

[0108] 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.

[0109] In this invention, the server includes means for acquiring profile information stored in a database and analyzing preferences and needs, means for receiving real-time environmental information from multiple sensor devices and understanding the user's context, and means for analyzing image data provided by the user and identifying the required product categories. This enables product recommendations tailored to the user's real-time situation, providing a highly accurate purchasing experience. Furthermore, prompt sentence generation using a generative AI model enhances decision support and realizes optimal product recommendations.

[0110] "Profile information" refers to information stored in a database that includes individual settings such as the user's preferences, needs, and past purchase history.

[0111] A "sensor device" is a device that detects information about the surrounding environment in real time and transmits it to a server.

[0112] "Context" refers to the state that reflects the user's current situation and environmental conditions.

[0113] "Image data" refers to a file format that contains visual information provided by the user.

[0114] A "product category" refers to a group or type used to classify products.

[0115] "Computer vision technology" is a system of technologies used to analyze digital images and videos and extract specific information.

[0116] A "generative AI model" is a computer program that uses artificial intelligence to automatically generate new data and information.

[0117] A "prompt statement" is a sentence that describes the instructions or requests given to a generated AI model when performing a specific task.

[0118] An "interactive interface" is a user interface or platform that allows users to interact with a system in real time.

[0119] "Feedback" refers to information collected from users regarding their reactions and evaluations of the system.

[0120] The system implementing this invention has a configuration in which a server, a terminal, and a user each have their own respective roles.

[0121] The server first retrieves user profile information from the database. This profile information includes the user's preferences, needs, and past purchase history. Based on this information, it analyzes the preferences and needs that the profile brings about. Furthermore, it receives real-time environmental information from multiple sensor devices to understand the user's current context. This enables product recommendations that are tailored to the user's dynamic situation.

[0122] The terminal receives image data provided by the user and analyzes it using computer vision technology. This allows the terminal to identify the user's design preferences and style, and determine the necessary product categories. Based on the analysis results, the server searches the product database and generates a personalized product recommendation list.

[0123] The user receives this recommendation list through an interactive interface. This interface allows the user to view detailed product information and make additional requests. The server uses this interaction to assess the user's purchasing intent and supports decision-making by generating prompts using a generative AI model.

[0124] Furthermore, after a purchase, user feedback is collected and analyzed by the server. This analysis is used to improve the accuracy of future recommendations. The feedback analysis updates the preference model, enabling more appropriate product suggestions.

[0125] For example, if a user is looking for furniture for their living room, they would take a picture of the room using their device and upload it. From this image, the server would identify the style of the room and recommend furniture with a suitable design. An example of a prompt message would be, "Based on the user's image style analysis, please recommend the most suitable interior products."

[0126] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0127] Step 1: The server retrieves user profile information from the database. The user ID is used as input, and the output is profile information associated with that ID. This information includes preferences, needs, and past purchase history. Based on the retrieved data, natural language processing techniques are used to analyze preferences and needs.

[0128] Step 2: The server receives real-time environmental information from multiple sensor devices. The input is information from the sensor devices. The output is detailed contextual information about the environment in which the user is located. This allows the server to understand the user's dynamic situation and recommend products that are appropriate for their current activities and location.

[0129] Step 3: The device analyzes the image data provided by the user using computer vision technology. The input is the visual information uploaded by the user, and the output is identified product category and style information. The device inputs this visual data into an image recognition model and determines the user's design preferences by extracting colors and design patterns.

[0130] Step 4: The server searches the product database based on the analyzed preferences, needs, environmental context, and image analysis results, and generates a product recommendation list. The input is an aggregation of the information processed in Steps 1-3. The output is a product list optimized for each individual user. Using a generation AI model, highly recommended products are selected from the list.

[0131] Step 5: The user receives a list of product recommendations through an interactive interface on their device. The user can view product details, make selections, and ask questions using the provided interface. This allows the system to assess the user's purchase intent and guide them through the purchase process.

[0132] Step 6: The server generates prompts using a generative AI model based on user interaction, asking questions and providing guidance to the user. The input is the user's action history and product information, and the output is prompts to assist in the dialogue.

[0133] Step 7: After a user makes a purchase, the server collects and analyzes feedback to improve the accuracy of future recommendations. The input is the user's opinions and ratings, and the output is the updated preference model and fine-tuning of the recommendation algorithm. This information is stored in a database and used to improve future product recommendations.

[0134] 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.

[0135] This invention provides an e-commerce system that recognizes the user's emotions and makes product suggestions based on those emotions. This system integrates an emotion engine to provide users with a more personalized purchasing experience.

[0136] The server retrieves user profile information from the database and analyzes user preferences and needs. Using this information, the server incorporates it into recommendation algorithms, building the foundation for generating personalized product recommendation lists for each user. Furthermore, the server integrates real-time environmental data received from sensor devices to deepen its understanding of the user's environment.

[0137] The key feature of this invention is that the emotion engine recognizes emotions from information entered by the user through the terminal and from interactions using an interactive interface. The server evaluates emotions using voice, text, and facial expression analysis, and utilizes this emotion data for product recommendations. This makes it possible to recommend products that are appropriate to the user's current emotional state.

[0138] As a concrete example, consider a scenario where a user is looking for a dress for a party held on the weekend. The server analyzes the user's sentiment using an interactive interface, along with the user's search history. Based on this analysis, the server identifies that the user is looking for a dress of a specific color and design, and recommends several products.

[0139] After the purchase process is complete, the server collects feedback from the user. This feedback includes evaluations based on product usability and emotions. The server stores this in a database to further refine the user preference model and improve the accuracy of future recommendation processes.

[0140] Thus, by using an emotion engine, the present invention provides product recommendations that are sensitive to the user's emotions, thereby offering a more satisfying purchasing experience.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The user accesses the e-commerce site using their device and logs in. The user enters the specifications of the desired product and uploads photos or images as needed.

[0144] Step 2:

[0145] The server receives data entered by the user and retrieves the user's profile information and past purchase history from the database. This allows the server to identify the user's preferences and past behavioral patterns.

[0146] Step 3:

[0147] The server receives real-time environmental information from the terminal. This information includes the user's current location, time of day, and device usage. Based on this, the server understands the user's current context.

[0148] Step 4:

[0149] If a user has uploaded image data, the server uses computer vision technology to analyze the image and identify product categories and attributes, such as party dresses or event accessories.

[0150] Step 5:

[0151] The server activates the emotion engine and recognizes emotions from text and voice input by the user through the interactive interface. For facial expression recognition, it analyzes video footage captured via the camera.

[0152] Step 6:

[0153] The server integrates emotion data obtained by the emotion engine, profile information, real-time environmental information, and image analysis results to generate a recommendation list for suggesting the most suitable products to the user.

[0154] Step 7:

[0155] The server presents the generated recommendation list to the user and uses an interactive interface to explain the features and appeal of each product. The user then uses this information to review product details and compare them.

[0156] Step 8:

[0157] Users can ask further questions about products they are interested in, and the server provides corresponding answers. This process supports their purchasing decisions.

[0158] Step 9:

[0159] After a user purchases a product, the server records the purchase information and related sentiment data, and sends a confirmation email. It also sends a message encouraging post-purchase feedback.

[0160] Step 10:

[0161] Users submit feedback via their devices after using a product. The server analyzes this feedback and stores it in a database to update the preference model and improve the accuracy of future recommendations.

[0162] (Example 2)

[0163] 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 will be referred to as the "terminal."

[0164] In e-commerce, providing users with more appropriate and personalized product recommendations requires accurately recognizing information based on their emotions and current circumstances, and recommending products accordingly. However, conventional systems have struggled to fully recognize users' emotions and meet their true needs. This challenge needs to be addressed.

[0165] 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.

[0166] In this invention, the server includes means for acquiring user attribute information stored in a data set and analyzing the user's preferences and requests; means for acquiring real-time environmental information from multiple sensors and understanding the user's situation; and means for analyzing various data (voice, text, facial expressions) provided by the user and identifying emotions. This enables highly accurate product recommendations based on the user's emotions and environment.

[0167] A "data set" is a collection of information that stores user attribute information, preferences, purchase history, sensor data, and feedback information.

[0168] A "sensor" is a device used to acquire user environmental information, physiological data, and behavior in real time. This includes cameras, microphones, and temperature and humidity sensors.

[0169] "Attribute information" refers to basic data about the user, including name, age, gender, address, past purchase history, and preferences.

[0170] "Preference" refers to the characteristics and tendencies that users like, and includes preferences for the design, color, or brand of a particular product.

[0171] "Requirements" refer to the functions, characteristics, and conditions that users expect from a product or service.

[0172] "Real-time environmental information" refers to information about the environment, such as the user's current location, weather conditions, and ambient noise, which is acquired in real time by sensors.

[0173] "Situation" refers to the physical and emotional conditions in which the user finds themselves, based on real-time environmental information.

[0174] "Diverse data" refers to various forms of information that can be obtained from users, including voice, text data, and data related to facial expressions and gestures.

[0175] "Identifying emotions" is the process of using diverse data obtained from users to identify their emotional state (joy, sadness, excitement, etc.).

[0176] A "product group" is a collection of commercial products from various categories that the system can access, and it serves as the basis for generating product lists that can be recommended to users.

[0177] A "product recommendation list" is a list containing information about multiple products, generated based on the user's preferences, needs, circumstances, and emotions, and is presented to the user.

[0178] This invention describes a form of an e-commerce system for providing product recommendations based on the user's emotional state. The system mainly consists of a server and a user terminal. A specific embodiment is described below.

[0179] The server first retrieves user attribute information from the data set and analyzes this information. This analysis utilizes specific software platforms, including, for example, database management systems and analytical software. This process reveals the user's preferences and requirements.

[0180] Next, the user's device uses sensors and cameras to collect real-time environmental information and voice, text, and facial expression data provided by the user. The device sends this data to a server. The server then uses a generative AI model to perform advanced data processing for emotion identification. In this process, natural language processing technology is used to analyze the sentiment of the text, and voice analysis technology is used to infer emotions from the tone of voice.

[0181] After the emotion is identified, the server integrates the user's attribute information, immediate environmental information, and the identified emotion to search for products and generate a highly accurate list of product recommendations. This list includes products that, for example, fit the user's current emotional state. For instance, if the user wants to relax, comfort-focused items will be recommended.

[0182] Furthermore, when providing product recommendations, the server provides an interactive interface to the user's terminal. This interface presents the information necessary for the user to gain a deeper understanding of the product and solidify their purchase decision.

[0183] After purchase, the server collects user feedback and stores it in a data set. This feedback is analyzed to improve the accuracy of future recommendations.

[0184] A concrete example of a prompt message would be: "The user is looking for party clothes; use the sentiment engine to analyze their preferences for product color and design."

[0185] This system allows users to receive personalized product recommendations tailored to their emotions, resulting in a more satisfying shopping experience.

[0186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0187] Step 1:

[0188] The user starts up their device and logs into the application. The server receives login information (user ID, password) as input and performs user authentication. If authentication is successful, the server retrieves user attribute information (purchase history, preferences, etc.) from the data set. The retrieved information is used in subsequent analysis steps.

[0189] Step 2:

[0190] The system collects user environmental information and emotional data. Using the device's sensors and camera, it acquires real-time user environmental information (location, temperature, humidity, etc.) and voice / facial expression data. This data is treated as input transmitted to the server. Data acquisition is performed in the background, ensuring it does not interrupt user interaction.

[0191] Step 3:

[0192] The server analyzes the received environmental and emotional data. Using a generative AI model, the server analyzes voice tone and performs natural language processing to identify emotions. Furthermore, it evaluates the current user situation based on sensor information. The acquired input data is structured, emotions and environmental information are identified, and based on this, the user's emotional state is output.

[0193] Step 4:

[0194] The server recommends products based on user attribute information, identified emotions, and environmental information. A recommendation algorithm runs, selecting appropriate products from a set of products. Using this data as input, the product recommendation algorithm is executed to generate an optimal product list. The output is a list of products that match the user's emotions.

[0195] Step 5:

[0196] A list of recommended products is sent to the user's device and displayed to them through an interactive screen. The user uses the screen to view detailed product information and then decide whether to purchase or add items to their list. After receiving the product list, the purchase decision is made based on the user's interaction. The UI / UX design ensures an intuitive and user-friendly interface.

[0197] Step 6:

[0198] After purchase, users are given the opportunity to provide feedback on the product to the system. This feedback includes user ratings and comments about the product. This feedback data is sent to the server and stored in a data set. Based on the feedback, the user preference model is updated for future purchases to improve recommendation accuracy. The input feedback is used to improve the user experience.

[0199] (Application Example 2)

[0200] 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".

[0201] In e-commerce, it has been difficult to grasp users' current emotional states in real time and provide personalized product recommendations and benefits that respond to those emotions. Traditional systems based recommendations solely on user feedback and preference data, and were unable to adequately address users' temporary emotions. Furthermore, the optimization of emotion-based incentives to improve the user's purchasing experience was insufficient.

[0202] 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.

[0203] In this invention, the server includes means for acquiring individual user information stored in a data storage system and interpreting the user's preferences and needs; means for receiving real-time situational information from various detection devices and understanding the user's situation; and means for evaluating the user's emotions in real time and providing benefits and incentives corresponding to those emotions. This enables accurate product recommendations and improved purchasing experiences based on the user's emotional state.

[0204] A "data storage system" is a system that stores data related to a user's individual information, preferences, and needs, and makes it available for retrieval as needed.

[0205] A "detection device" is a sensor device that collects information about the user's situation and environment in real time and transmits it to a server.

[0206] "Visual data" refers to images and video information provided by users, which is analyzed to identify products that the user is interested in or needs.

[0207] A "two-way interface" is a user interface that allows users and systems to exchange information with each other, and is a means of presenting product information and collecting opinions.

[0208] "User sentiment" refers to the psychological or emotional state a user exhibits while interacting with the system's interface, and is evaluated in real time.

[0209] "Benefits and incentives" are discounts, coupons, and other rewards offered emotionally to increase a user's willingness to purchase.

[0210] The system implementing this invention centers around a data storage system, multiple detection devices, and a server. The server retrieves individual user information stored in the data storage system and interprets preferences and needs through analysis. This enables the system to provide optimal product recommendations for each user.

[0211] The real-time sentiment assessment function uses the camera and microphone equipped on the device to detect the user's emotions through image recognition and voice analysis technologies. Specific hardware used includes smartphones and tablets. The software utilizes Google Cloud's sentiment analysis API, which sends accurate sentiment data to the server.

[0212] The server combines emotional data with user preference information to provide rewards and incentives in real time. For example, if a user's emotional state, as measured in front of a vending machine, is relaxed, the server might offer a reward such as, "Buy this drink and receive a coupon for 50% off your next purchase."

[0213] Specifically, the system provides a personalized purchasing experience by instructing the AI ​​model based on a prompt message such as, "If the customer is highly satisfied with a purchased product, please suggest additional appropriate benefits." This enables detailed product recommendations and benefit offerings based on the user's emotions, resulting in a highly satisfying purchasing experience.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The terminal retrieves individual user information from the data storage system. The input is the user's account information, and the output includes their preferences and past purchase history. Based on this information, a user profile is created on the terminal to serve as the basis for future analysis.

[0217] Step 2:

[0218] Multiple detection devices acquire real-time information about the user's situation. The input consists of data from cameras and microphones, and the output is a dataset representing the user's current state. The server uses this dataset to understand the user's context and prepares for sentiment analysis in the next step.

[0219] Step 3:

[0220] The server analyzes the visual and audio data sent from the terminal. The input is the image and audio data obtained in the previous step, and the output is the user's emotional state. By using an emotion analysis API to specifically identify this emotional state, the server understands the user's psychological state.

[0221] Step 4:

[0222] The server combines the analyzed emotion data and profile information and sends a prompt to the generating AI model. An example of a prompt is, "Please suggest the best reward for this emotional state." The output is information on rewards and product recommendations generated by the AI.

[0223] Step 5:

[0224] The server sends the generated reward information to the user's device and notifies the user via a two-way interface. The input is the reward information, and the output is a reward presentation screen that the user can visually confirm. In this step, the user views the details of the offered rewards and products and makes a final purchase decision.

[0225] Step 6:

[0226] Users review the details of the offered benefits and products and send feedback to the server via their device. The input is the user's feedback, and the output is post-purchase evaluation information. This information is then stored again in the data storage system to help improve future recommendation processes.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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".

[0243] This invention provides a method for recommending the most suitable products to users in an e-commerce system and improving the purchasing experience. Specific embodiments for carrying out this invention are described below.

[0244] The server retrieves user profile information stored in the database and analyzes user preferences and needs. This analysis includes sentiment and intent derived from the user's past search history and reviews, using natural language processing techniques. Furthermore, the server receives real-time environmental information from multiple sensor devices. This allows the server to understand the user's current context and incorporate this into the recommendation algorithm.

[0245] Furthermore, the terminal uploads image data provided by the user to the server. This data is analyzed using computer vision technology to help identify product categories and styles. In this way, by comprehensively considering the user's preferences, needs, real-time environmental information, and image data analysis results, the server selects the most suitable products and generates a recommendation list.

[0246] This recommendation list is presented to the user through an interactive, conversational interface. Through this interface, users can obtain detailed information about products and ask additional questions. The server confirms the user's purchasing intent through interaction and provides concierge-like support as needed.

[0247] After purchase, the server collects feedback from the user and stores it in a database. This feedback is analyzed using big data technology and used to improve the accuracy of recommendations for future purchases.

[0248] As a concrete example, let's assume a user is looking for a new smartphone. In this case, the server can recommend products suitable for the user's current location and communication environment in real time, while also considering the user's past purchase history and brand preferences. Furthermore, it can use images taken by the user to identify smartphones with the design and color they desire. This allows users to find products that meet their needs more accurately and quickly.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The user accesses the e-commerce site using their device and logs in. The user enters or selects their profile information and desired product criteria. This information is processed together with the user's past purchase history and preference data.

[0252] Step 2:

[0253] The server retrieves user profile information and historical data from the database. This allows it to analyze user preferences and purchasing patterns and identify potential needs.

[0254] Step 3:

[0255] The server receives real-time environmental information from the user via the terminal. This includes location information, device usage, and time of day. Based on this information, the server understands the user's current status.

[0256] Step 4:

[0257] Users upload reference images of products and event photos to the server using their devices. The server uses computer vision technology to analyze these images and identify product categories and styles.

[0258] Step 5:

[0259] The server integrates user preferences, needs, context, and image analysis results, and queries the relevant product database. Based on this data, the server generates a list of products best suited to the user.

[0260] Step 6:

[0261] The server presents the user with a generated list of product recommendations. Through an interactive interface, the server provides detailed explanations of the product's features and appeal, offering information to increase the user's desire to purchase.

[0262] Step 7:

[0263] Users can view product details and compare options through the interface. Users can also ask the server further questions as needed to receive assistance in their purchasing decision.

[0264] Step 8:

[0265] When a user purchases a product, the server records the purchase information and sends a confirmation email. The server then sends a message to the user to collect post-purchase feedback.

[0266] Step 9:

[0267] After using the product, users enter feedback and send it to the server via their device. The server analyzes this feedback and stores it in a database.

[0268] Step 10:

[0269] The server uses the collected feedback and purchase data to update its preference model and improve the accuracy of product suggestions in the next recommendation process.

[0270] (Example 1)

[0271] 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."

[0272] Traditional e-commerce systems could only suggest products based on users' purchase history and basic preferences, making it difficult to provide accurate recommendations that considered users' real-time situations and detailed tastes. Furthermore, it was difficult for users to quickly find products that met their needs, resulting in a less-than-satisfactory shopping experience. Additionally, effective use of user feedback to improve the accuracy of future recommendations was insufficient.

[0273] 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.

[0274] In this invention, the server includes means for acquiring user identification information stored in a data set and analyzing the user's preferences and needs; means for receiving real-time situational information from multiple detection devices and understanding the user's situation; and means for analyzing visual data provided by the user and identifying the product category the user is seeking. This enables product suggestions that comprehensively consider diverse user information, making it possible to provide a more personalized purchasing experience.

[0275] A "data set" refers to a collection of information that is systematically stored and can be searched or retrieved later.

[0276] "User" refers to an individual or legal entity that uses the system, and the subject whose preferences and behavioral data are managed as a profile.

[0277] "Identification information" refers to data used to identify a user, and includes information that is associated with an individual's preferences and past behavioral history.

[0278] "Preference" refers to the individual user's tastes and preferences for products and services, and the factors that influence their decision-making.

[0279] "Necessity" refers to the demands and conditions that users have for a product or service, and is a need based on their intention to purchase.

[0280] A "detection device" refers to a device such as a sensor that senses the user's surroundings and actions in real time and collects that information.

[0281] "Situational information" refers to real-time background information such as the user's current location, surrounding environmental conditions, and behavioral state.

[0282] "Visual data" refers to photographs and image information provided by users, and includes information about the visual characteristics of a product.

[0283] "Product classification" refers to the criteria for categorizing products based on their types and properties.

[0284] "Product aggregate" refers to the collection of all product information managed within the system, including data used for product recommendations to users.

[0285] "Product recommendation list" refers to a list of products selected based on the preferences and needs of the user, and refers to the proposal documents for promoting purchases.

[0286] "Interactive display means" refers to the form of an interface that allows the user to interactively view and operate product information.

[0287] "Evaluation information" refers to feedback and reviews given by the user on products and services, including information that contributes to improving the accuracy of future recommendations.

[0288] This invention provides a method for proposing optimal products to users and improving the purchasing experience in an e-commerce system.

[0289] First, the server obtains the user's identification information stored in the data aggregate. A database management system is used for this process. Next, the server utilizes natural language processing technology using Python to analyze the user's preferences and needs. This makes it possible to extract emotions and intentions obtained from past reviews and search histories.

[0290] Furthermore, the server receives real-time situation information from multiple detection devices. This information includes environmental conditions and communication status at the current location where the user is. Real-time data streaming technology such as Apache Kafka is utilized to ensure immediacy.

[0291] The terminal uploads visual data captured by the user, such as photos taken with a smartphone, to the server. The server uses computer vision technologies such as OpenCV to analyze the images and identify product categories. This makes it possible to understand the user's preferred designs and colors.

[0292] The server integrates all this information and generates a list of optimal product recommendations by running a machine learning model using TensorFlow. This list is presented to the user through an interactive display using JavaScript and React. The user can use this interface to view product information and ask questions.

[0293] Furthermore, after a user makes a purchase, the server collects user feedback and stores it in a data set. This feedback data is analyzed using Hadoop and Spark and used to improve the accuracy of future recommendation processes.

[0294] As a concrete example, consider a user looking for a new laptop. The server can consider the user's past purchase history and usage patterns to recommend a product suitable for the network conditions in the user's location. Furthermore, based on images of the laptop the user has taken, it can identify the user's preferred design and color. In this way, the user can quickly find a product that meets their needs.

[0295] An example of a prompt statement to be used as input to a generative AI model is: "Please provide an algorithm for recommending products on an e-commerce platform that utilizes user history and real-time data."

[0296] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0297] Step 1:

[0298] The server retrieves user identification information from the data set. This information includes the user's past purchase history, search history, and review history. Based on the user ID as input, it executes SQL queries to extract relevant information. The output is a dataset for identifying the user's preferences and needs. The server uses this information to analyze the user's preferences and purchase motivations.

[0299] Step 2:

[0300] The server receives real-time contextual information from multiple detection devices. This includes the user's current location, communication status, and weather information. Real-time data obtained through the API serves as supplementary information to understand the user's context. The input contextual data is collected by the server, and the context model is updated as output.

[0301] Step 3:

[0302] Users use their devices to capture visual data of products they are interested in and upload it to the server. For example, they might take a picture of a laptop design with their smartphone. The server receives the input image data and analyzes it using the OpenCV library. The output includes product classification and style information, which the server uses to understand the user's visual preferences.

[0303] Step 4:

[0304] The server integrates the analyzed user preferences, needs, context, and product categories, and generates a list of optimal product suggestions using a machine learning model based on TensorFlow. The input dataset consists of the information obtained in the previous steps. The list of product suggestions generated as a result of the model's calculations is output and used to increase the user's purchasing intent.

[0305] Step 5:

[0306] The user browses the list of product recommendations through an interactive display means using JavaScript and React on the terminal. In this interface, it is possible to check the detailed information of products and ask questions. The server receives the user's input and provides additional information in real time.

[0307] Step 6:

[0308] After the user purchases a product, the user provides evaluation information regarding the transaction to the server. The input of the evaluation information is uploaded to the server as comments and evaluation scores. The server stores this data in a data aggregate and performs analysis using Hadoop and Spark. Through this analysis, output data for improving the accuracy of the next recommendation is generated.

[0309] (Application Example 1)

[0310] 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".

[0311] In the conventional e-commerce system, product recommendations are often made based on the user's past purchase history and general preferences, and real-time context and style analysis from images are not fully utilized. For this reason, there is a problem that it is difficult for users to quickly and accurately find products suitable for their current needs and the surrounding environment. Furthermore, it is also a problem that an advanced recommendation system using prompts utilizing a generative AI model has not been realized.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0313] In this invention, the server includes means for acquiring profile information stored in a database and analyzing preferences and needs, means for receiving real-time environmental information from multiple sensor devices and understanding the user's context, and means for analyzing image data provided by the user and identifying the required product categories. This enables product recommendations tailored to the user's real-time situation, providing a highly accurate purchasing experience. Furthermore, prompt sentence generation using a generative AI model enhances decision support and realizes optimal product recommendations.

[0314] "Profile information" refers to information stored in a database that includes individual settings such as the user's preferences, needs, and past purchase history.

[0315] A "sensor device" is a device that detects information about the surrounding environment in real time and transmits it to a server.

[0316] "Context" refers to the state that reflects the user's current situation and environmental conditions.

[0317] "Image data" refers to a file format that contains visual information provided by the user.

[0318] A "product category" refers to a group or type used to classify products.

[0319] "Computer vision technology" is a system of technologies used to analyze digital images and videos and extract specific information.

[0320] A "generative AI model" is a computer program that uses artificial intelligence to automatically generate new data and information.

[0321] A "prompt statement" is a sentence that describes the instructions or requests given to a generated AI model when performing a specific task.

[0322] An "interactive interface" is a user interface or platform that allows users to interact with a system in real time.

[0323] "Feedback" refers to information collected from users regarding their reactions and evaluations of the system.

[0324] The system implementing this invention has a configuration in which a server, a terminal, and a user each have their own respective roles.

[0325] The server first retrieves user profile information from the database. This profile information includes the user's preferences, needs, and past purchase history. Based on this information, it analyzes the preferences and needs that the profile brings about. Furthermore, it receives real-time environmental information from multiple sensor devices to understand the user's current context. This enables product recommendations that are tailored to the user's dynamic situation.

[0326] The terminal receives image data provided by the user and analyzes it using computer vision technology. This allows the terminal to identify the user's design preferences and style, and determine the necessary product categories. Based on the analysis results, the server searches the product database and generates a personalized product recommendation list.

[0327] The user receives this recommendation list through an interactive interface. This interface allows the user to view detailed product information and make additional requests. The server uses this interaction to assess the user's purchasing intent and supports decision-making by generating prompts using a generative AI model.

[0328] Furthermore, after a purchase, user feedback is collected and analyzed by the server. This analysis is used to improve the accuracy of future recommendations. The feedback analysis updates the preference model, enabling more appropriate product suggestions.

[0329] For example, if a user is looking for furniture for their living room, they would take a picture of the room using their device and upload it. From this image, the server would identify the style of the room and recommend furniture with a suitable design. An example of a prompt message would be, "Based on the user's image style analysis, please recommend the most suitable interior products."

[0330] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0331] Step 1: The server retrieves user profile information from the database. The user ID is used as input, and the output is profile information associated with that ID. This information includes preferences, needs, and past purchase history. Based on the retrieved data, natural language processing techniques are used to analyze preferences and needs.

[0332] Step 2: The server receives real-time environmental information from multiple sensor devices. The input is information from the sensor devices. The output is detailed contextual information about the environment in which the user is located. This allows the server to understand the user's dynamic situation and recommend products that are appropriate for their current activities and location.

[0333] Step 3: The device analyzes the image data provided by the user using computer vision technology. The input is the visual information uploaded by the user, and the output is identified product category and style information. The device inputs this visual data into an image recognition model and determines the user's design preferences by extracting colors and design patterns.

[0334] Step 4: The server searches the product database based on the analyzed preferences, needs, environmental context, and image analysis results, and generates a product recommendation list. The input is an aggregation of the information processed in Steps 1-3. The output is a product list optimized for each individual user. Using a generation AI model, highly recommended products are selected from the list.

[0335] Step 5: The user receives a list of product recommendations through an interactive interface on their device. The user can view product details, make selections, and ask questions using the provided interface. This allows the system to assess the user's purchase intent and guide them through the purchase process.

[0336] Step 6: The server generates prompts using a generative AI model based on user interaction, asking questions and providing guidance to the user. The input is the user's action history and product information, and the output is prompts to assist in the dialogue.

[0337] Step 7: After a user makes a purchase, the server collects and analyzes feedback to improve the accuracy of future recommendations. The input is the user's opinions and ratings, and the output is the updated preference model and fine-tuning of the recommendation algorithm. This information is stored in a database and used to improve future product recommendations.

[0338] 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.

[0339] This invention provides an e-commerce system that recognizes the user's emotions and makes product suggestions based on those emotions. This system integrates an emotion engine to provide users with a more personalized purchasing experience.

[0340] The server retrieves user profile information from the database and analyzes user preferences and needs. Using this information, the server incorporates it into recommendation algorithms, building the foundation for generating personalized product recommendation lists for each user. Furthermore, the server integrates real-time environmental data received from sensor devices to deepen its understanding of the user's environment.

[0341] The key feature of this invention is that the emotion engine recognizes emotions from information entered by the user through the terminal and from interactions using an interactive interface. The server evaluates emotions using voice, text, and facial expression analysis, and utilizes this emotion data for product recommendations. This makes it possible to recommend products that are appropriate to the user's current emotional state.

[0342] As a concrete example, consider a scenario where a user is looking for a dress for a party held on the weekend. The server analyzes the user's sentiment using an interactive interface, along with the user's search history. Based on this analysis, the server identifies that the user is looking for a dress of a specific color and design, and recommends several products.

[0343] After the purchase process is complete, the server collects feedback from the user. This feedback includes evaluations based on product usability and emotions. The server stores this in a database to further refine the user preference model and improve the accuracy of future recommendation processes.

[0344] Thus, by using an emotion engine, the present invention provides product recommendations that are sensitive to the user's emotions, thereby offering a more satisfying purchasing experience.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] The user accesses the e-commerce site using their device and logs in. The user enters the specifications of the desired product and uploads photos or images as needed.

[0348] Step 2:

[0349] The server receives data entered by the user and retrieves the user's profile information and past purchase history from the database. This allows the server to identify the user's preferences and past behavioral patterns.

[0350] Step 3:

[0351] The server receives real-time environmental information from the terminal. This information includes the user's current location, time of day, and device usage. Based on this, the server understands the user's current context.

[0352] Step 4:

[0353] If a user has uploaded image data, the server uses computer vision technology to analyze the image and identify product categories and attributes, such as party dresses or event accessories.

[0354] Step 5:

[0355] The server activates the emotion engine and recognizes emotions from text and voice input by the user through the interactive interface. For facial expression recognition, it analyzes video footage captured via the camera.

[0356] Step 6:

[0357] The server integrates emotion data obtained by the emotion engine, profile information, real-time environmental information, and image analysis results to generate a recommendation list for suggesting the most suitable products to the user.

[0358] Step 7:

[0359] The server presents the generated recommendation list to the user and uses an interactive interface to explain the features and appeal of each product. The user then uses this information to review product details and compare them.

[0360] Step 8:

[0361] Users can ask further questions about products they are interested in, and the server provides corresponding answers. This process supports their purchasing decisions.

[0362] Step 9:

[0363] After a user purchases a product, the server records the purchase information and related sentiment data, and sends a confirmation email. It also sends a message encouraging post-purchase feedback.

[0364] Step 10:

[0365] Users submit feedback via their devices after using a product. The server analyzes this feedback and stores it in a database to update the preference model and improve the accuracy of future recommendations.

[0366] (Example 2)

[0367] 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".

[0368] In e-commerce, providing users with more appropriate and personalized product recommendations requires accurately recognizing information based on their emotions and current circumstances, and recommending products accordingly. However, conventional systems have struggled to fully recognize users' emotions and meet their true needs. This challenge needs to be addressed.

[0369] 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.

[0370] In this invention, the server includes means for acquiring user attribute information stored in a data set and analyzing the user's preferences and requests; means for acquiring real-time environmental information from multiple sensors and understanding the user's situation; and means for analyzing various data (voice, text, facial expressions) provided by the user and identifying emotions. This enables highly accurate product recommendations based on the user's emotions and environment.

[0371] A "data set" is a collection of information that stores user attribute information, preferences, purchase history, sensor data, and feedback information.

[0372] A "sensor" is a device used to acquire user environmental information, physiological data, and behavior in real time. This includes cameras, microphones, and temperature and humidity sensors.

[0373] "Attribute information" refers to basic data about the user, including name, age, gender, address, past purchase history, and preferences.

[0374] "Preference" refers to the characteristics and tendencies that users like, and includes preferences for the design, color, or brand of a particular product.

[0375] "Requirements" refer to the functions, characteristics, and conditions that users expect from a product or service.

[0376] "Real-time environmental information" refers to information about the environment, such as the user's current location, weather conditions, and ambient noise, which is acquired in real time by sensors.

[0377] "Situation" refers to the physical and emotional conditions in which the user finds themselves, based on real-time environmental information.

[0378] "Diverse data" refers to various forms of information that can be obtained from users, including voice, text data, and data related to facial expressions and gestures.

[0379] "Identifying emotions" is the process of using diverse data obtained from users to identify their emotional state (joy, sadness, excitement, etc.).

[0380] A "product group" is a collection of commercial products from various categories that the system can access, and it serves as the basis for generating product lists that can be recommended to users.

[0381] A "product recommendation list" is a list containing information about multiple products, generated based on the user's preferences, needs, circumstances, and emotions, and is presented to the user.

[0382] This invention describes a form of an e-commerce system for providing product recommendations based on the user's emotional state. The system mainly consists of a server and a user terminal. A specific embodiment is described below.

[0383] The server first retrieves user attribute information from the data set and analyzes this information. This analysis utilizes specific software platforms, including, for example, database management systems and analytical software. This process reveals the user's preferences and requirements.

[0384] Next, the user's device uses sensors and cameras to collect real-time environmental information and voice, text, and facial expression data provided by the user. The device sends this data to a server. The server then uses a generative AI model to perform advanced data processing for emotion identification. In this process, natural language processing technology is used to analyze the sentiment of the text, and voice analysis technology is used to infer emotions from the tone of voice.

[0385] After the emotion is identified, the server integrates the user's attribute information, immediate environmental information, and the identified emotion to search for products and generate a highly accurate list of product recommendations. This list includes products that, for example, fit the user's current emotional state. For instance, if the user wants to relax, comfort-focused items will be recommended.

[0386] Furthermore, when providing product recommendations, the server provides an interactive interface to the user's terminal. This interface presents the information necessary for the user to gain a deeper understanding of the product and solidify their purchase decision.

[0387] After purchase, the server collects user feedback and stores it in a data set. This feedback is analyzed to improve the accuracy of future recommendations.

[0388] A concrete example of a prompt message would be: "The user is looking for party clothes; use the sentiment engine to analyze their preferences for product color and design."

[0389] This system allows users to receive personalized product recommendations tailored to their emotions, resulting in a more satisfying shopping experience.

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The user starts up their device and logs into the application. The server receives login information (user ID, password) as input and performs user authentication. If authentication is successful, the server retrieves user attribute information (purchase history, preferences, etc.) from the data set. The retrieved information is used in subsequent analysis steps.

[0393] Step 2:

[0394] The system collects user environmental information and emotional data. Using the device's sensors and camera, it acquires real-time user environmental information (location, temperature, humidity, etc.) and voice / facial expression data. This data is treated as input transmitted to the server. Data acquisition is performed in the background, ensuring it does not interrupt user interaction.

[0395] Step 3:

[0396] The server analyzes the received environmental and emotional data. Using a generative AI model, the server analyzes voice tone and performs natural language processing to identify emotions. Furthermore, it evaluates the current user situation based on sensor information. The acquired input data is structured, emotions and environmental information are identified, and based on this, the user's emotional state is output.

[0397] Step 4:

[0398] The server recommends products based on user attribute information, identified emotions, and environmental information. A recommendation algorithm runs, selecting appropriate products from a set of products. Using this data as input, the product recommendation algorithm is executed to generate an optimal product list. The output is a list of products that match the user's emotions.

[0399] Step 5:

[0400] A list of recommended products is sent to the user's device and displayed to them through an interactive screen. The user uses the screen to view detailed product information and then decide whether to purchase or add items to their list. After receiving the product list, the purchase decision is made based on the user's interaction. The UI / UX design ensures an intuitive and user-friendly interface.

[0401] Step 6:

[0402] After purchase, users are given the opportunity to provide feedback on the product to the system. This feedback includes user ratings and comments about the product. This feedback data is sent to the server and stored in a data set. Based on the feedback, the user preference model is updated for future purchases to improve recommendation accuracy. The input feedback is used to improve the user experience.

[0403] (Application Example 2)

[0404] 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."

[0405] In e-commerce, it has been difficult to grasp users' current emotional states in real time and provide personalized product recommendations and benefits that respond to those emotions. Traditional systems based recommendations solely on user feedback and preference data, and were unable to adequately address users' temporary emotions. Furthermore, the optimization of emotion-based incentives to improve the user's purchasing experience was insufficient.

[0406] 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.

[0407] In this invention, the server includes means for acquiring individual user information stored in a data storage system and interpreting the user's preferences and needs; means for receiving real-time situational information from various detection devices and understanding the user's situation; and means for evaluating the user's emotions in real time and providing benefits and incentives corresponding to those emotions. This enables accurate product recommendations and improved purchasing experiences based on the user's emotional state.

[0408] A "data storage system" is a system that stores data related to a user's individual information, preferences, and needs, and makes it available for retrieval as needed.

[0409] A "detection device" is a sensor device that collects information about the user's situation and environment in real time and transmits it to a server.

[0410] "Visual data" refers to images and video information provided by users, which is analyzed to identify products that the user is interested in or needs.

[0411] A "two-way interface" is a user interface that allows users and systems to exchange information with each other, and is a means of presenting product information and collecting opinions.

[0412] "User sentiment" refers to the psychological or emotional state a user exhibits while interacting with the system's interface, and is evaluated in real time.

[0413] "Benefits and incentives" are discounts, coupons, and other rewards offered emotionally to increase a user's willingness to purchase.

[0414] The system implementing this invention centers around a data storage system, multiple detection devices, and a server. The server retrieves individual user information stored in the data storage system and interprets preferences and needs through analysis. This enables the system to provide optimal product recommendations for each user.

[0415] The real-time sentiment assessment feature uses the camera and microphone equipped on the device to detect the user's emotions through image recognition and voice analysis technologies. Specific hardware used includes smartphones and tablets. The software utilizes Google Cloud's sentiment analysis API, which sends accurate sentiment data to the server.

[0416] The server combines emotional data with user preference information to provide rewards and incentives in real time. For example, if a user's emotional state, as measured in front of a vending machine, is relaxed, the server might offer a reward such as, "Buy this drink and receive a coupon for 50% off your next purchase."

[0417] Specifically, the system provides a personalized purchasing experience by instructing the AI ​​model based on a prompt message such as, "If the customer is highly satisfied with a purchased product, please suggest additional appropriate benefits." This enables detailed product recommendations and benefit offerings based on the user's emotions, resulting in a highly satisfying purchasing experience.

[0418] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0419] Step 1:

[0420] The terminal retrieves individual user information from the data storage system. The input is the user's account information, and the output includes their preferences and past purchase history. Based on this information, a user profile is created on the terminal to serve as the basis for future analysis.

[0421] Step 2:

[0422] Multiple detection devices acquire real-time information about the user's situation. The input consists of data from cameras and microphones, and the output is a dataset representing the user's current state. The server uses this dataset to understand the user's context and prepares for sentiment analysis in the next step.

[0423] Step 3:

[0424] The server analyzes the visual and audio data sent from the terminal. The input is the image and audio data obtained in the previous step, and the output is the user's emotional state. By using an emotion analysis API to specifically identify this emotional state, the server understands the user's psychological state.

[0425] Step 4:

[0426] The server combines the analyzed emotion data and profile information and sends a prompt to the generating AI model. An example of a prompt is, "Please suggest the best reward for this emotional state." The output is information on rewards and product recommendations generated by the AI.

[0427] Step 5:

[0428] The server sends the generated reward information to the user's device and notifies the user via a two-way interface. The input is the reward information, and the output is a reward presentation screen that the user can visually confirm. In this step, the user views the details of the offered rewards and products and makes a final purchase decision.

[0429] Step 6:

[0430] Users review the details of the offered benefits and products and send feedback to the server via their device. The input is the user's feedback, and the output is post-purchase evaluation information. This information is then stored again in the data storage system to help improve future recommendation processes.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] [Third Embodiment]

[0435] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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".

[0447] This invention provides a method for recommending the most suitable products to users in an e-commerce system and improving the purchasing experience. Specific embodiments for carrying out this invention are described below.

[0448] The server retrieves user profile information stored in the database and analyzes user preferences and needs. This analysis includes sentiment and intent derived from the user's past search history and reviews, using natural language processing techniques. Furthermore, the server receives real-time environmental information from multiple sensor devices. This allows the server to understand the user's current context and incorporate this into the recommendation algorithm.

[0449] Furthermore, the terminal uploads image data provided by the user to the server. This data is analyzed using computer vision technology to help identify product categories and styles. In this way, by comprehensively considering the user's preferences, needs, real-time environmental information, and image data analysis results, the server selects the most suitable products and generates a recommendation list.

[0450] This recommendation list is presented to the user through an interactive, conversational interface. Through this interface, users can obtain detailed information about products and ask additional questions. The server confirms the user's purchasing intent through interaction and provides concierge-like support as needed.

[0451] After purchase, the server collects feedback from the user and stores it in a database. This feedback is analyzed using big data technology and used to improve the accuracy of recommendations for future purchases.

[0452] As a concrete example, let's assume a user is looking for a new smartphone. In this case, the server can recommend products suitable for the user's current location and communication environment in real time, while also considering the user's past purchase history and brand preferences. Furthermore, it can use images taken by the user to identify smartphones with the design and color they desire. This allows users to find products that meet their needs more accurately and quickly.

[0453] The following describes the processing flow.

[0454] Step 1:

[0455] The user accesses the e-commerce site using their device and logs in. The user enters or selects their profile information and desired product criteria. This information is processed together with the user's past purchase history and preference data.

[0456] Step 2:

[0457] The server retrieves user profile information and historical data from the database. This allows it to analyze user preferences and purchasing patterns and identify potential needs.

[0458] Step 3:

[0459] The server receives real-time environmental information from the user via the terminal. This includes location information, device usage, and time of day. Based on this information, the server understands the user's current status.

[0460] Step 4:

[0461] Users upload reference images of products and event photos to the server using their devices. The server uses computer vision technology to analyze these images and identify product categories and styles.

[0462] Step 5:

[0463] The server integrates user preferences, needs, context, and image analysis results, and queries the relevant product database. Based on this data, the server generates a list of products best suited to the user.

[0464] Step 6:

[0465] The server presents the user with a generated list of product recommendations. Through an interactive interface, the server provides detailed explanations of the product's features and appeal, offering information to increase the user's desire to purchase.

[0466] Step 7:

[0467] Users can view product details and compare options through the interface. Users can also ask the server further questions as needed to receive assistance in their purchasing decision.

[0468] Step 8:

[0469] When a user purchases a product, the server records the purchase information and sends a confirmation email. The server then sends a message to the user to collect post-purchase feedback.

[0470] Step 9:

[0471] After using the product, users enter feedback and send it to the server via their device. The server analyzes this feedback and stores it in a database.

[0472] Step 10:

[0473] The server uses the collected feedback and purchase data to update its preference model and improve the accuracy of product suggestions in the next recommendation process.

[0474] (Example 1)

[0475] 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."

[0476] Traditional e-commerce systems could only suggest products based on users' purchase history and basic preferences, making it difficult to provide accurate recommendations that considered users' real-time situations and detailed tastes. Furthermore, it was difficult for users to quickly find products that met their needs, resulting in a less-than-satisfactory shopping experience. Additionally, effective use of user feedback to improve the accuracy of future recommendations was insufficient.

[0477] 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.

[0478] In this invention, the server includes means for acquiring user identification information stored in a data set and analyzing the user's preferences and needs; means for receiving real-time situational information from multiple detection devices and understanding the user's situation; and means for analyzing visual data provided by the user and identifying the product category the user is seeking. This enables product suggestions that comprehensively consider diverse user information, making it possible to provide a more personalized purchasing experience.

[0479] A "data set" refers to a collection of information that is systematically stored and can be searched or retrieved later.

[0480] "User" refers to an individual or legal entity that uses the system, and the subject whose preferences and behavioral data are managed as a profile.

[0481] "Identification information" refers to data used to identify a user, and includes information that is associated with an individual's preferences and past behavioral history.

[0482] "Preference" refers to the individual user's tastes and preferences for products and services, and the factors that influence their decision-making.

[0483] "Necessity" refers to the demands and conditions that users have for a product or service, and is a need based on their intention to purchase.

[0484] A "detection device" refers to a device such as a sensor that senses the user's surroundings and actions in real time and collects that information.

[0485] "Situational information" refers to real-time background information such as the user's current location, surrounding environmental conditions, and behavioral state.

[0486] "Visual data" refers to photographs and image information provided by users, and includes information about the visual characteristics of a product.

[0487] "Product classification" refers to the criteria used to categorize products based on their type and characteristics.

[0488] A "product collection" refers to the entire set of product information managed within the system, including data used to suggest products to users.

[0489] A "product suggestion list" refers to a list of products selected based on the user's preferences and needs, and is a proposal document intended to promote purchases.

[0490] "Interactive display means" refers to a form of interface that allows users to interactively view and manipulate product information.

[0491] "Evaluation information" refers to feedback and reviews that users have given to products and services, and includes information that contributes to improving the accuracy of future recommendations.

[0492] This invention provides a method for suggesting optimal products to users and improving the purchasing experience in an e-commerce system.

[0493] The server first retrieves user identification information stored in a data set. A database management system is used for this process. Next, the server utilizes natural language processing techniques using Python to analyze the user's preferences and needs. This makes it possible to extract sentiments and intentions derived from past reviews and search history.

[0494] Furthermore, the server receives real-time status information from multiple detection devices. This information includes environmental conditions and communication status at the user's current location. Real-time data streaming technologies such as Apache Kafka are used to ensure immediacy.

[0495] The terminal uploads visual data captured by the user, such as photos taken with a smartphone, to the server. The server uses computer vision technologies such as OpenCV to analyze the images and identify product categories. This makes it possible to understand the user's preferred designs and colors.

[0496] The server integrates all this information and generates a list of optimal product recommendations by running a machine learning model using TensorFlow. This list is presented to the user through an interactive display using JavaScript and React. The user can use this interface to view product information and ask questions.

[0497] Furthermore, after a user makes a purchase, the server collects user feedback and stores it in a data set. This feedback data is analyzed using Hadoop and Spark and used to improve the accuracy of future recommendation processes.

[0498] As a concrete example, consider a user looking for a new laptop. The server can consider the user's past purchase history and usage patterns to recommend a product suitable for the network conditions in the user's location. Furthermore, based on images of the laptop the user has taken, it can identify the user's preferred design and color. In this way, the user can quickly find a product that meets their needs.

[0499] An example of a prompt statement to be used as input to a generative AI model is: "Please provide an algorithm for recommending products on an e-commerce platform that utilizes user history and real-time data."

[0500] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0501] Step 1:

[0502] The server retrieves user identification information from the data set. This information includes the user's past purchase history, search history, and review history. Based on the user ID as input, it executes SQL queries to extract relevant information. The output is a dataset for identifying the user's preferences and needs. The server uses this information to analyze the user's preferences and purchase motivations.

[0503] Step 2:

[0504] The server receives real-time contextual information from multiple detection devices. This includes the user's current location, communication status, and weather information. Real-time data obtained through the API serves as supplementary information to understand the user's context. The input contextual data is collected by the server, and the context model is updated as output.

[0505] Step 3:

[0506] Users use their devices to capture visual data of products they are interested in and upload it to the server. For example, they might take a picture of a laptop design with their smartphone. The server receives the input image data and analyzes it using the OpenCV library. The output includes product classification and style information, which the server uses to understand the user's visual preferences.

[0507] Step 4:

[0508] The server integrates the analyzed user preferences, needs, context, and product categories, and generates a list of optimal product suggestions using a machine learning model based on TensorFlow. The input dataset consists of the information obtained in the previous steps. The list of product suggestions generated as a result of the model's calculations is output and used to increase the user's purchasing intent.

[0509] Step 5:

[0510] Users view a list of product suggestions via an interactive display using JavaScript and React on their device. This interface allows them to view detailed product information and ask questions. The server receives user input and provides additional information in real time.

[0511] Step 6:

[0512] Users provide transaction feedback information to the server after purchasing a product. This feedback is uploaded to the server as comments and rating scores. The server stores this data in a data set and performs analysis using Hadoop and Spark. This analysis generates output data to improve the accuracy of future recommendations.

[0513] (Application Example 1)

[0514] 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."

[0515] Traditional e-commerce systems often rely on users' past purchase history and general preferences for product recommendations, failing to fully utilize real-time contextual and image-based style analysis. This makes it difficult for users to quickly and accurately find products that suit their current needs and surrounding environment. Furthermore, the lack of advanced recommendation systems utilizing generative AI models for prompting is also a problem.

[0516] 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.

[0517] In this invention, the server includes means for acquiring profile information stored in a database and analyzing preferences and needs, means for receiving real-time environmental information from multiple sensor devices and understanding the user's context, and means for analyzing image data provided by the user and identifying the required product categories. This enables product recommendations tailored to the user's real-time situation, providing a highly accurate purchasing experience. Furthermore, prompt sentence generation using a generative AI model enhances decision support and realizes optimal product recommendations.

[0518] "Profile information" refers to information stored in a database that includes individual settings such as the user's preferences, needs, and past purchase history.

[0519] A "sensor device" is a device that detects information about the surrounding environment in real time and transmits it to a server.

[0520] "Context" refers to the state that reflects the user's current situation and environmental conditions.

[0521] "Image data" refers to a file format that contains visual information provided by the user.

[0522] A "product category" refers to a group or type used to classify products.

[0523] "Computer vision technology" is a system of technologies used to analyze digital images and videos and extract specific information.

[0524] A "generative AI model" is a computer program that uses artificial intelligence to automatically generate new data and information.

[0525] A "prompt statement" is a sentence that describes the instructions or requests given to a generated AI model when performing a specific task.

[0526] An "interactive interface" is a user interface or platform that allows users to interact with a system in real time.

[0527] "Feedback" refers to information collected from users regarding their reactions and evaluations of the system.

[0528] The system implementing this invention has a configuration in which a server, a terminal, and a user each have their own respective roles.

[0529] The server first retrieves user profile information from the database. This profile information includes the user's preferences, needs, and past purchase history. Based on this information, it analyzes the preferences and needs that the profile brings about. Furthermore, it receives real-time environmental information from multiple sensor devices to understand the user's current context. This enables product recommendations that are tailored to the user's dynamic situation.

[0530] The terminal receives image data provided by the user and analyzes it using computer vision technology. This allows the terminal to identify the user's design preferences and style, and determine the necessary product categories. Based on the analysis results, the server searches the product database and generates a personalized product recommendation list.

[0531] The user receives this recommendation list through an interactive interface. This interface allows the user to view detailed product information and make additional requests. The server uses this interaction to assess the user's purchasing intent and supports decision-making by generating prompts using a generative AI model.

[0532] Furthermore, after a purchase, user feedback is collected and analyzed by the server. This analysis is used to improve the accuracy of future recommendations. The feedback analysis updates the preference model, enabling more appropriate product suggestions.

[0533] For example, if a user is looking for furniture for their living room, they would take a picture of the room using their device and upload it. From this image, the server would identify the style of the room and recommend furniture with a suitable design. An example of a prompt message would be, "Based on the user's image style analysis, please recommend the most suitable interior products."

[0534] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0535] Step 1: The server retrieves user profile information from the database. The user ID is used as input, and the output is profile information associated with that ID. This information includes preferences, needs, and past purchase history. Based on the retrieved data, natural language processing techniques are used to analyze preferences and needs.

[0536] Step 2: The server receives real-time environmental information from multiple sensor devices. The input is information from the sensor devices. The output is detailed contextual information about the environment in which the user is located. This allows the server to understand the user's dynamic situation and recommend products that are appropriate for their current activities and location.

[0537] Step 3: The device analyzes the image data provided by the user using computer vision technology. The input is the visual information uploaded by the user, and the output is identified product category and style information. The device inputs this visual data into an image recognition model and determines the user's design preferences by extracting colors and design patterns.

[0538] Step 4: The server searches the product database based on the analyzed preferences, needs, environmental context, and image analysis results, and generates a product recommendation list. The input is an aggregation of the information processed in Steps 1-3. The output is a product list optimized for each individual user. Using a generation AI model, highly recommended products are selected from the list.

[0539] Step 5: The user receives a list of product recommendations through an interactive interface on their device. The user can view product details, make selections, and ask questions using the provided interface. This allows the system to assess the user's purchase intent and guide them through the purchase process.

[0540] Step 6: The server generates prompts using a generative AI model based on user interaction, asking questions and providing guidance to the user. The input is the user's action history and product information, and the output is prompts to assist in the dialogue.

[0541] Step 7: After a user makes a purchase, the server collects and analyzes feedback to improve the accuracy of future recommendations. The input is the user's opinions and ratings, and the output is the updated preference model and fine-tuning of the recommendation algorithm. This information is stored in a database and used to improve future product recommendations.

[0542] 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.

[0543] This invention provides an e-commerce system that recognizes the user's emotions and makes product suggestions based on those emotions. This system integrates an emotion engine to provide users with a more personalized purchasing experience.

[0544] The server retrieves user profile information from the database and analyzes user preferences and needs. Using this information, the server incorporates it into recommendation algorithms, building the foundation for generating personalized product recommendation lists for each user. Furthermore, the server integrates real-time environmental data received from sensor devices to deepen its understanding of the user's environment.

[0545] The key feature of this invention is that the emotion engine recognizes emotions from information entered by the user through the terminal and from interactions using an interactive interface. The server evaluates emotions using voice, text, and facial expression analysis, and utilizes this emotion data for product recommendations. This makes it possible to recommend products that are appropriate to the user's current emotional state.

[0546] As a concrete example, consider a scenario where a user is looking for a dress for a party held on the weekend. The server analyzes the user's sentiment using an interactive interface, along with the user's search history. Based on this analysis, the server identifies that the user is looking for a dress of a specific color and design, and recommends several products.

[0547] After the purchase process is complete, the server collects feedback from the user. This feedback includes evaluations based on product usability and emotions. The server stores this in a database to further refine the user preference model and improve the accuracy of future recommendation processes.

[0548] Thus, by using an emotion engine, the present invention provides product recommendations that are sensitive to the user's emotions, thereby offering a more satisfying purchasing experience.

[0549] The following describes the processing flow.

[0550] Step 1:

[0551] The user accesses the e-commerce site using their device and logs in. The user enters the specifications of the desired product and uploads photos or images as needed.

[0552] Step 2:

[0553] The server receives data entered by the user and retrieves the user's profile information and past purchase history from the database. This allows the server to identify the user's preferences and past behavioral patterns.

[0554] Step 3:

[0555] The server receives real-time environmental information from the terminal. This information includes the user's current location, time of day, and device usage. Based on this, the server understands the user's current context.

[0556] Step 4:

[0557] If a user has uploaded image data, the server uses computer vision technology to analyze the image and identify product categories and attributes, such as party dresses or event accessories.

[0558] Step 5:

[0559] The server activates the emotion engine and recognizes emotions from text and voice input by the user through the interactive interface. For facial expression recognition, it analyzes video footage captured via the camera.

[0560] Step 6:

[0561] The server integrates emotion data obtained by the emotion engine, profile information, real-time environmental information, and image analysis results to generate a recommendation list for suggesting the most suitable products to the user.

[0562] Step 7:

[0563] The server presents the generated recommendation list to the user and uses an interactive interface to explain the features and appeal of each product. The user then uses this information to review product details and compare them.

[0564] Step 8:

[0565] Users can ask further questions about products they are interested in, and the server provides corresponding answers. This process supports their purchasing decisions.

[0566] Step 9:

[0567] After a user purchases a product, the server records the purchase information and related sentiment data, and sends a confirmation email. It also sends a message encouraging post-purchase feedback.

[0568] Step 10:

[0569] Users submit feedback via their devices after using a product. The server analyzes this feedback and stores it in a database to update the preference model and improve the accuracy of future recommendations.

[0570] (Example 2)

[0571] 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."

[0572] In e-commerce, providing users with more appropriate and personalized product recommendations requires accurately recognizing information based on their emotions and current circumstances, and recommending products accordingly. However, conventional systems have struggled to fully recognize users' emotions and meet their true needs. This challenge needs to be addressed.

[0573] 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.

[0574] In this invention, the server includes means for acquiring user attribute information stored in a data set and analyzing the user's preferences and requests; means for acquiring real-time environmental information from multiple sensors and understanding the user's situation; and means for analyzing various data (voice, text, facial expressions) provided by the user and identifying emotions. This enables highly accurate product recommendations based on the user's emotions and environment.

[0575] A "data set" is a collection of information that stores user attribute information, preferences, purchase history, sensor data, and feedback information.

[0576] A "sensor" is a device used to acquire user environmental information, physiological data, and behavior in real time. This includes cameras, microphones, and temperature and humidity sensors.

[0577] "Attribute information" refers to basic data about the user, including name, age, gender, address, past purchase history, and preferences.

[0578] "Preference" refers to the characteristics and tendencies that users like, and includes preferences for the design, color, or brand of a particular product.

[0579] "Requirements" refer to the functions, characteristics, and conditions that users expect from a product or service.

[0580] "Real-time environmental information" refers to information about the environment, such as the user's current location, weather conditions, and ambient noise, which is acquired in real time by sensors.

[0581] "Situation" refers to the physical and emotional conditions in which the user finds themselves, based on real-time environmental information.

[0582] "Diverse data" refers to various forms of information that can be obtained from users, including voice, text data, and data related to facial expressions and gestures.

[0583] "Identifying emotions" is the process of using diverse data obtained from users to identify their emotional state (joy, sadness, excitement, etc.).

[0584] A "product group" is a collection of commercial products from various categories that the system can access, and it serves as the basis for generating product lists that can be recommended to users.

[0585] A "product recommendation list" is a list containing information about multiple products, generated based on the user's preferences, needs, circumstances, and emotions, and is presented to the user.

[0586] This invention describes a form of an e-commerce system for providing product recommendations based on the user's emotional state. The system mainly consists of a server and a user terminal. A specific embodiment is described below.

[0587] The server first retrieves user attribute information from the data set and analyzes this information. This analysis utilizes specific software platforms, including, for example, database management systems and analytical software. This process reveals the user's preferences and requirements.

[0588] Next, the user's device uses sensors and cameras to collect real-time environmental information and voice, text, and facial expression data provided by the user. The device sends this data to a server. The server then uses a generative AI model to perform advanced data processing for emotion identification. In this process, natural language processing technology is used to analyze the sentiment of the text, and voice analysis technology is used to infer emotions from the tone of voice.

[0589] After the emotion is identified, the server integrates the user's attribute information, immediate environmental information, and the identified emotion to search for products and generate a highly accurate list of product recommendations. This list includes products that, for example, fit the user's current emotional state. For instance, if the user wants to relax, comfort-focused items will be recommended.

[0590] Furthermore, when providing product recommendations, the server provides an interactive interface to the user's terminal. This interface presents the information necessary for the user to gain a deeper understanding of the product and solidify their purchase decision.

[0591] After purchase, the server collects user feedback and stores it in a data set. This feedback is analyzed to improve the accuracy of future recommendations.

[0592] A concrete example of a prompt message would be: "The user is looking for party clothes; use the sentiment engine to analyze their preferences for product color and design."

[0593] This system allows users to receive personalized product recommendations tailored to their emotions, resulting in a more satisfying shopping experience.

[0594] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0595] Step 1:

[0596] The user starts up their device and logs into the application. The server receives login information (user ID, password) as input and performs user authentication. If authentication is successful, the server retrieves user attribute information (purchase history, preferences, etc.) from the data set. The retrieved information is used in subsequent analysis steps.

[0597] Step 2:

[0598] The system collects user environmental information and emotional data. Using the device's sensors and camera, it acquires real-time user environmental information (location, temperature, humidity, etc.) and voice / facial expression data. This data is treated as input transmitted to the server. Data acquisition is performed in the background, ensuring it does not interrupt user interaction.

[0599] Step 3:

[0600] The server analyzes the received environmental and emotional data. Using a generative AI model, the server analyzes voice tone and performs natural language processing to identify emotions. Furthermore, it evaluates the current user situation based on sensor information. The acquired input data is structured, emotions and environmental information are identified, and based on this, the user's emotional state is output.

[0601] Step 4:

[0602] The server recommends products based on user attribute information, identified emotions, and environmental information. A recommendation algorithm runs, selecting appropriate products from a set of products. Using this data as input, the product recommendation algorithm is executed to generate an optimal product list. The output is a list of products that match the user's emotions.

[0603] Step 5:

[0604] A list of recommended products is sent to the user's device and displayed to them through an interactive screen. The user uses the screen to view detailed product information and then decide whether to purchase or add items to their list. After receiving the product list, the purchase decision is made based on the user's interaction. The UI / UX design ensures an intuitive and user-friendly interface.

[0605] Step 6:

[0606] After purchase, users are given the opportunity to provide feedback on the product to the system. This feedback includes user ratings and comments about the product. This feedback data is sent to the server and stored in a data set. Based on the feedback, the user preference model is updated for future purchases to improve recommendation accuracy. The input feedback is used to improve the user experience.

[0607] (Application Example 2)

[0608] 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."

[0609] In e-commerce, it has been difficult to grasp users' current emotional states in real time and provide personalized product recommendations and benefits that respond to those emotions. Traditional systems based recommendations solely on user feedback and preference data, and were unable to adequately address users' temporary emotions. Furthermore, the optimization of emotion-based incentives to improve the user's purchasing experience was insufficient.

[0610] 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.

[0611] In this invention, the server includes means for acquiring individual user information stored in a data storage system and interpreting the user's preferences and needs; means for receiving real-time situational information from various detection devices and understanding the user's situation; and means for evaluating the user's emotions in real time and providing benefits and incentives corresponding to those emotions. This enables accurate product recommendations and improved purchasing experiences based on the user's emotional state.

[0612] A "data storage system" is a system that stores data related to a user's individual information, preferences, and needs, and makes it available for retrieval as needed.

[0613] A "detection device" is a sensor device that collects information about the user's situation and environment in real time and transmits it to a server.

[0614] "Visual data" refers to images and video information provided by users, which is analyzed to identify products that the user is interested in or needs.

[0615] A "two-way interface" is a user interface that allows users and systems to exchange information with each other, and is a means of presenting product information and collecting opinions.

[0616] "User sentiment" refers to the psychological or emotional state a user exhibits while interacting with the system's interface, and is evaluated in real time.

[0617] "Benefits and incentives" are discounts, coupons, and other rewards offered emotionally to increase a user's willingness to purchase.

[0618] The system implementing this invention centers around a data storage system, multiple detection devices, and a server. The server retrieves individual user information stored in the data storage system and interprets preferences and needs through analysis. This enables the system to provide optimal product recommendations for each user.

[0619] The real-time sentiment assessment feature uses the camera and microphone equipped on the device to detect the user's emotions through image recognition and voice analysis technologies. Specific hardware used includes smartphones and tablets. The software utilizes Google Cloud's sentiment analysis API, which sends accurate sentiment data to the server.

[0620] The server combines emotional data with user preference information to provide rewards and incentives in real time. For example, if a user's emotional state, as measured in front of a vending machine, is relaxed, the server might offer a reward such as, "Buy this drink and receive a coupon for 50% off your next purchase."

[0621] Specifically, the system provides a personalized purchasing experience by instructing the AI ​​model based on a prompt message such as, "If the customer is highly satisfied with a purchased product, please suggest additional appropriate benefits." This enables detailed product recommendations and benefit offerings based on the user's emotions, resulting in a highly satisfying purchasing experience.

[0622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0623] Step 1:

[0624] The terminal retrieves individual user information from the data storage system. The input is the user's account information, and the output includes their preferences and past purchase history. Based on this information, a user profile is created on the terminal to serve as the basis for future analysis.

[0625] Step 2:

[0626] Multiple detection devices acquire real-time information about the user's situation. The input consists of data from cameras and microphones, and the output is a dataset representing the user's current state. The server uses this dataset to understand the user's context and prepares for sentiment analysis in the next step.

[0627] Step 3:

[0628] The server analyzes the visual and audio data sent from the terminal. The input is the image and audio data obtained in the previous step, and the output is the user's emotional state. By using an emotion analysis API to specifically identify this emotional state, the server understands the user's psychological state.

[0629] Step 4:

[0630] The server combines the analyzed emotion data and profile information and sends a prompt to the generating AI model. An example of a prompt is, "Please suggest the best reward for this emotional state." The output is information on rewards and product recommendations generated by the AI.

[0631] Step 5:

[0632] The server sends the generated reward information to the user's device and notifies the user via a two-way interface. The input is the reward information, and the output is a reward presentation screen that the user can visually confirm. In this step, the user views the details of the offered rewards and products and makes a final purchase decision.

[0633] Step 6:

[0634] Users review the details of the offered benefits and products and send feedback to the server via their device. The input is the user's feedback, and the output is post-purchase evaluation information. This information is then stored again in the data storage system to help improve future recommendation processes.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] [Fourth Embodiment]

[0639] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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".

[0652] This invention provides a method for recommending the most suitable products to users in an e-commerce system and improving the purchasing experience. Specific embodiments for carrying out this invention are described below.

[0653] The server retrieves user profile information stored in the database and analyzes user preferences and needs. This analysis includes sentiment and intent derived from the user's past search history and reviews, using natural language processing techniques. Furthermore, the server receives real-time environmental information from multiple sensor devices. This allows the server to understand the user's current context and incorporate this into the recommendation algorithm.

[0654] Furthermore, the terminal uploads image data provided by the user to the server. This data is analyzed using computer vision technology to help identify product categories and styles. In this way, by comprehensively considering the user's preferences, needs, real-time environmental information, and image data analysis results, the server selects the most suitable products and generates a recommendation list.

[0655] This recommendation list is presented to the user through an interactive, conversational interface. Through this interface, users can obtain detailed information about products and ask additional questions. The server confirms the user's purchasing intent through interaction and provides concierge-like support as needed.

[0656] After purchase, the server collects feedback from the user and stores it in a database. This feedback is analyzed using big data technology and used to improve the accuracy of recommendations for future purchases.

[0657] As a concrete example, let's assume a user is looking for a new smartphone. In this case, the server can recommend products suitable for the user's current location and communication environment in real time, while also considering the user's past purchase history and brand preferences. Furthermore, it can use images taken by the user to identify smartphones with the design and color they desire. This allows users to find products that meet their needs more accurately and quickly.

[0658] The following describes the processing flow.

[0659] Step 1:

[0660] The user accesses the e-commerce site using their device and logs in. The user enters or selects their profile information and desired product criteria. This information is processed together with the user's past purchase history and preference data.

[0661] Step 2:

[0662] The server retrieves user profile information and historical data from the database. This allows it to analyze user preferences and purchasing patterns and identify potential needs.

[0663] Step 3:

[0664] The server receives real-time environmental information from the user via the terminal. This includes location information, device usage, and time of day. Based on this information, the server understands the user's current status.

[0665] Step 4:

[0666] Users upload reference images of products and event photos to the server using their devices. The server uses computer vision technology to analyze these images and identify product categories and styles.

[0667] Step 5:

[0668] The server integrates user preferences, needs, context, and image analysis results, and queries the relevant product database. Based on this data, the server generates a list of products best suited to the user.

[0669] Step 6:

[0670] The server presents the user with a generated list of product recommendations. Through an interactive interface, the server provides detailed explanations of the product's features and appeal, offering information to increase the user's desire to purchase.

[0671] Step 7:

[0672] Users can view product details and compare options through the interface. Users can also ask the server further questions as needed to receive assistance in their purchasing decision.

[0673] Step 8:

[0674] When a user purchases a product, the server records the purchase information and sends a confirmation email. The server then sends a message to the user to collect post-purchase feedback.

[0675] Step 9:

[0676] After using the product, users enter feedback and send it to the server via their device. The server analyzes this feedback and stores it in a database.

[0677] Step 10:

[0678] The server uses the collected feedback and purchase data to update its preference model and improve the accuracy of product suggestions in the next recommendation process.

[0679] (Example 1)

[0680] 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".

[0681] Traditional e-commerce systems could only suggest products based on users' purchase history and basic preferences, making it difficult to provide accurate recommendations that considered users' real-time situations and detailed tastes. Furthermore, it was difficult for users to quickly find products that met their needs, resulting in a less-than-satisfactory shopping experience. Additionally, effective use of user feedback to improve the accuracy of future recommendations was insufficient.

[0682] 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.

[0683] In this invention, the server includes means for acquiring user identification information stored in a data set and analyzing the user's preferences and needs; means for receiving real-time situational information from multiple detection devices and understanding the user's situation; and means for analyzing visual data provided by the user and identifying the product category the user is seeking. This enables product suggestions that comprehensively consider diverse user information, making it possible to provide a more personalized purchasing experience.

[0684] A "data set" refers to a collection of information that is systematically stored and can be searched or retrieved later.

[0685] "User" refers to an individual or legal entity that uses the system, and the subject whose preferences and behavioral data are managed as a profile.

[0686] "Identification information" refers to data used to identify a user, and includes information that is associated with an individual's preferences and past behavioral history.

[0687] "Preference" refers to the individual user's tastes and preferences for products and services, and the factors that influence their decision-making.

[0688] "Necessity" refers to the demands and conditions that users have for a product or service, and is a need based on their intention to purchase.

[0689] A "detection device" refers to a device such as a sensor that senses the user's surroundings and actions in real time and collects that information.

[0690] "Situational information" refers to real-time background information such as the user's current location, surrounding environmental conditions, and behavioral state.

[0691] "Visual data" refers to photographs and image information provided by users, and includes information about the visual characteristics of a product.

[0692] "Product classification" refers to the criteria used to categorize products based on their type and characteristics.

[0693] A "product collection" refers to the entire set of product information managed within the system, including data used to suggest products to users.

[0694] A "product suggestion list" refers to a list of products selected based on the user's preferences and needs, and is a proposal document intended to promote purchases.

[0695] "Interactive display means" refers to a form of interface that allows users to interactively view and manipulate product information.

[0696] "Evaluation information" refers to feedback and reviews that users have given to products and services, and includes information that contributes to improving the accuracy of future recommendations.

[0697] This invention provides a method for suggesting optimal products to users and improving the purchasing experience in an e-commerce system.

[0698] The server first retrieves user identification information stored in a data set. A database management system is used for this process. Next, the server utilizes natural language processing techniques using Python to analyze the user's preferences and needs. This makes it possible to extract sentiments and intentions derived from past reviews and search history.

[0699] Furthermore, the server receives real-time status information from multiple detection devices. This information includes environmental conditions and communication status at the user's current location. Real-time data streaming technologies such as Apache Kafka are used to ensure immediacy.

[0700] The terminal uploads visual data captured by the user, such as photos taken with a smartphone, to the server. The server uses computer vision technologies such as OpenCV to analyze the images and identify product categories. This makes it possible to understand the user's preferred designs and colors.

[0701] The server integrates all this information and generates a list of optimal product recommendations by running a machine learning model using TensorFlow. This list is presented to the user through an interactive display using JavaScript and React. The user can use this interface to view product information and ask questions.

[0702] Furthermore, after a user makes a purchase, the server collects user feedback and stores it in a data set. This feedback data is analyzed using Hadoop and Spark and used to improve the accuracy of future recommendation processes.

[0703] As a concrete example, consider a user looking for a new laptop. The server can consider the user's past purchase history and usage patterns to recommend a product suitable for the network conditions in the user's location. Furthermore, based on images of the laptop the user has taken, it can identify the user's preferred design and color. In this way, the user can quickly find a product that meets their needs.

[0704] An example of a prompt statement to be used as input to a generative AI model is: "Please provide an algorithm for recommending products on an e-commerce platform that utilizes user history and real-time data."

[0705] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0706] Step 1:

[0707] The server retrieves user identification information from the data set. This information includes the user's past purchase history, search history, and review history. Based on the user ID as input, it executes SQL queries to extract relevant information. The output is a dataset for identifying the user's preferences and needs. The server uses this information to analyze the user's preferences and purchase motivations.

[0708] Step 2:

[0709] The server receives real-time contextual information from multiple detection devices. This includes the user's current location, communication status, and weather information. Real-time data obtained through the API serves as supplementary information to understand the user's context. The input contextual data is collected by the server, and the context model is updated as output.

[0710] Step 3:

[0711] Users use their devices to capture visual data of products they are interested in and upload it to the server. For example, they might take a picture of a laptop design with their smartphone. The server receives the input image data and analyzes it using the OpenCV library. The output includes product classification and style information, which the server uses to understand the user's visual preferences.

[0712] Step 4:

[0713] The server integrates the analyzed user preferences, needs, context, and product categories, and generates a list of optimal product suggestions using a machine learning model based on TensorFlow. The input dataset consists of the information obtained in the previous steps. The list of product suggestions generated as a result of the model's calculations is output and used to increase the user's purchasing intent.

[0714] Step 5:

[0715] Users view a list of product suggestions via an interactive display using JavaScript and React on their device. This interface allows them to view detailed product information and ask questions. The server receives user input and provides additional information in real time.

[0716] Step 6:

[0717] Users provide transaction feedback information to the server after purchasing a product. This feedback is uploaded to the server as comments and rating scores. The server stores this data in a data set and performs analysis using Hadoop and Spark. This analysis generates output data to improve the accuracy of future recommendations.

[0718] (Application Example 1)

[0719] 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".

[0720] Traditional e-commerce systems often rely on users' past purchase history and general preferences for product recommendations, failing to fully utilize real-time contextual and image-based style analysis. This makes it difficult for users to quickly and accurately find products that suit their current needs and surrounding environment. Furthermore, the lack of advanced recommendation systems utilizing generative AI models for prompting is also a problem.

[0721] 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.

[0722] In this invention, the server includes means for acquiring profile information stored in a database and analyzing preferences and needs, means for receiving real-time environmental information from multiple sensor devices and understanding the user's context, and means for analyzing image data provided by the user and identifying the required product categories. This enables product recommendations tailored to the user's real-time situation, providing a highly accurate purchasing experience. Furthermore, prompt sentence generation using a generative AI model enhances decision support and realizes optimal product recommendations.

[0723] "Profile information" refers to information stored in a database that includes individual settings such as the user's preferences, needs, and past purchase history.

[0724] A "sensor device" is a device that detects information about the surrounding environment in real time and transmits it to a server.

[0725] "Context" refers to the state that reflects the user's current situation and environmental conditions.

[0726] "Image data" refers to a file format that contains visual information provided by the user.

[0727] A "product category" refers to a group or type used to classify products.

[0728] "Computer vision technology" is a system of technologies used to analyze digital images and videos and extract specific information.

[0729] A "generative AI model" is a computer program that uses artificial intelligence to automatically generate new data and information.

[0730] A "prompt statement" is a sentence that describes the instructions or requests given to a generated AI model when performing a specific task.

[0731] An "interactive interface" is a user interface or platform that allows users to interact with a system in real time.

[0732] "Feedback" refers to information collected from users regarding their reactions and evaluations of the system.

[0733] The system implementing this invention has a configuration in which a server, a terminal, and a user each have their own respective roles.

[0734] The server first retrieves user profile information from the database. This profile information includes the user's preferences, needs, and past purchase history. Based on this information, it analyzes the preferences and needs that the profile brings about. Furthermore, it receives real-time environmental information from multiple sensor devices to understand the user's current context. This enables product recommendations that are tailored to the user's dynamic situation.

[0735] The terminal receives image data provided by the user and analyzes it using computer vision technology. This allows the terminal to identify the user's design preferences and style, and determine the necessary product categories. Based on the analysis results, the server searches the product database and generates a personalized product recommendation list.

[0736] The user receives this recommendation list through an interactive interface. This interface allows the user to view detailed product information and make additional requests. The server uses this interaction to assess the user's purchasing intent and supports decision-making by generating prompts using a generative AI model.

[0737] Furthermore, after a purchase, user feedback is collected and analyzed by the server. This analysis is used to improve the accuracy of future recommendations. The feedback analysis updates the preference model, enabling more appropriate product suggestions.

[0738] For example, if a user is looking for furniture for their living room, they would take a picture of the room using their device and upload it. From this image, the server would identify the style of the room and recommend furniture with a suitable design. An example of a prompt message would be, "Based on the user's image style analysis, please recommend the most suitable interior products."

[0739] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0740] Step 1: The server retrieves user profile information from the database. The user ID is used as input, and the output is profile information associated with that ID. This information includes preferences, needs, and past purchase history. Based on the retrieved data, natural language processing techniques are used to analyze preferences and needs.

[0741] Step 2: The server receives real-time environmental information from multiple sensor devices. The input is information from the sensor devices. The output is detailed contextual information about the environment in which the user is located. This allows the server to understand the user's dynamic situation and recommend products that are appropriate for their current activities and location.

[0742] Step 3: The device analyzes the image data provided by the user using computer vision technology. The input is the visual information uploaded by the user, and the output is identified product category and style information. The device inputs this visual data into an image recognition model and determines the user's design preferences by extracting colors and design patterns.

[0743] Step 4: The server searches the product database based on the analyzed preferences, needs, environmental context, and image analysis results, and generates a product recommendation list. The input is an aggregation of the information processed in Steps 1-3. The output is a product list optimized for each individual user. Using a generation AI model, highly recommended products are selected from the list.

[0744] Step 5: The user receives a list of product recommendations through an interactive interface on their device. The user can view product details, make selections, and ask questions using the provided interface. This allows the system to assess the user's purchase intent and guide them through the purchase process.

[0745] Step 6: The server generates prompts using a generative AI model based on user interaction, asking questions and providing guidance to the user. The input is the user's action history and product information, and the output is prompts to assist in the dialogue.

[0746] Step 7: After a user makes a purchase, the server collects and analyzes feedback to improve the accuracy of future recommendations. The input is the user's opinions and ratings, and the output is the updated preference model and fine-tuning of the recommendation algorithm. This information is stored in a database and used to improve future product recommendations.

[0747] 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.

[0748] This invention provides an e-commerce system that recognizes the user's emotions and makes product suggestions based on those emotions. This system integrates an emotion engine to provide users with a more personalized purchasing experience.

[0749] The server retrieves user profile information from the database and analyzes user preferences and needs. Using this information, the server incorporates it into recommendation algorithms, building the foundation for generating personalized product recommendation lists for each user. Furthermore, the server integrates real-time environmental data received from sensor devices to deepen its understanding of the user's environment.

[0750] The key feature of this invention is that the emotion engine recognizes emotions from information entered by the user through the terminal and from interactions using an interactive interface. The server evaluates emotions using voice, text, and facial expression analysis, and utilizes this emotion data for product recommendations. This makes it possible to recommend products that are appropriate to the user's current emotional state.

[0751] As a concrete example, consider a scenario where a user is looking for a dress for a party held on the weekend. The server analyzes the user's sentiment using an interactive interface, along with the user's search history. Based on this analysis, the server identifies that the user is looking for a dress of a specific color and design, and recommends several products.

[0752] After the purchase process is complete, the server collects feedback from the user. This feedback includes evaluations based on product usability and emotions. The server stores this in a database to further refine the user preference model and improve the accuracy of future recommendation processes.

[0753] Thus, by using an emotion engine, the present invention provides product recommendations that are sensitive to the user's emotions, thereby offering a more satisfying purchasing experience.

[0754] The following describes the processing flow.

[0755] Step 1:

[0756] The user accesses the e-commerce site using their device and logs in. The user enters the specifications of the desired product and uploads photos or images as needed.

[0757] Step 2:

[0758] The server receives data entered by the user and retrieves the user's profile information and past purchase history from the database. This allows the server to identify the user's preferences and past behavioral patterns.

[0759] Step 3:

[0760] The server receives real-time environmental information from the terminal. This information includes the user's current location, time of day, and device usage. Based on this, the server understands the user's current context.

[0761] Step 4:

[0762] If a user has uploaded image data, the server uses computer vision technology to analyze the image and identify product categories and attributes, such as party dresses or event accessories.

[0763] Step 5:

[0764] The server activates the emotion engine and recognizes emotions from text and voice input by the user through the interactive interface. For facial expression recognition, it analyzes video footage captured via the camera.

[0765] Step 6:

[0766] The server integrates emotion data obtained by the emotion engine, profile information, real-time environmental information, and image analysis results to generate a recommendation list for suggesting the most suitable products to the user.

[0767] Step 7:

[0768] The server presents the generated recommendation list to the user and uses an interactive interface to explain the features and appeal of each product. The user then uses this information to review product details and compare them.

[0769] Step 8:

[0770] Users can ask further questions about products they are interested in, and the server provides corresponding answers. This process supports their purchasing decisions.

[0771] Step 9:

[0772] After a user purchases a product, the server records the purchase information and related sentiment data, and sends a confirmation email. It also sends a message encouraging post-purchase feedback.

[0773] Step 10:

[0774] Users submit feedback via their devices after using a product. The server analyzes this feedback and stores it in a database to update the preference model and improve the accuracy of future recommendations.

[0775] (Example 2)

[0776] 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".

[0777] In e-commerce, providing users with more appropriate and personalized product recommendations requires accurately recognizing information based on their emotions and current circumstances, and recommending products accordingly. However, conventional systems have struggled to fully recognize users' emotions and meet their true needs. This challenge needs to be addressed.

[0778] 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.

[0779] In this invention, the server includes means for acquiring user attribute information stored in a data set and analyzing the user's preferences and requests; means for acquiring real-time environmental information from multiple sensors and understanding the user's situation; and means for analyzing various data (voice, text, facial expressions) provided by the user and identifying emotions. This enables highly accurate product recommendations based on the user's emotions and environment.

[0780] A "data set" is a collection of information that stores user attribute information, preferences, purchase history, sensor data, and feedback information.

[0781] A "sensor" is a device used to acquire user environmental information, physiological data, and behavior in real time. This includes cameras, microphones, and temperature and humidity sensors.

[0782] "Attribute information" refers to basic data about the user, including name, age, gender, address, past purchase history, and preferences.

[0783] "Preference" refers to the characteristics and tendencies that users like, and includes preferences for the design, color, or brand of a particular product.

[0784] "Requirements" refer to the functions, characteristics, and conditions that users expect from a product or service.

[0785] "Real-time environmental information" refers to information about the environment, such as the user's current location, weather conditions, and ambient noise, which is acquired in real time by sensors.

[0786] "Situation" refers to the physical and emotional conditions in which the user finds themselves, based on real-time environmental information.

[0787] "Diverse data" refers to various forms of information that can be obtained from users, including voice, text data, and data related to facial expressions and gestures.

[0788] "Identifying emotions" is the process of using diverse data obtained from users to identify their emotional state (joy, sadness, excitement, etc.).

[0789] A "product group" is a collection of commercial products from various categories that the system can access, and it serves as the basis for generating product lists that can be recommended to users.

[0790] A "product recommendation list" is a list containing information about multiple products, generated based on the user's preferences, needs, circumstances, and emotions, and is presented to the user.

[0791] This invention describes a form of an e-commerce system for providing product recommendations based on the user's emotional state. The system mainly consists of a server and a user terminal. A specific embodiment is described below.

[0792] The server first retrieves user attribute information from the data set and analyzes this information. This analysis utilizes specific software platforms, including, for example, database management systems and analytical software. This process reveals the user's preferences and requirements.

[0793] Next, the user's device uses sensors and cameras to collect real-time environmental information and voice, text, and facial expression data provided by the user. The device sends this data to a server. The server then uses a generative AI model to perform advanced data processing for emotion identification. In this process, natural language processing technology is used to analyze the sentiment of the text, and voice analysis technology is used to infer emotions from the tone of voice.

[0794] After the emotion is identified, the server integrates the user's attribute information, immediate environmental information, and the identified emotion to search for products and generate a highly accurate list of product recommendations. This list includes products that, for example, fit the user's current emotional state. For instance, if the user wants to relax, comfort-focused items will be recommended.

[0795] Furthermore, when providing product recommendations, the server provides an interactive interface to the user's terminal. This interface presents the information necessary for the user to gain a deeper understanding of the product and solidify their purchase decision.

[0796] After purchase, the server collects user feedback and stores it in a data set. This feedback is analyzed to improve the accuracy of future recommendations.

[0797] A concrete example of a prompt message would be: "The user is looking for party clothes; use the sentiment engine to analyze their preferences for product color and design."

[0798] This system allows users to receive personalized product recommendations tailored to their emotions, resulting in a more satisfying shopping experience.

[0799] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0800] Step 1:

[0801] The user starts up their device and logs into the application. The server receives login information (user ID, password) as input and performs user authentication. If authentication is successful, the server retrieves user attribute information (purchase history, preferences, etc.) from the data set. The retrieved information is used in subsequent analysis steps.

[0802] Step 2:

[0803] The system collects user environmental information and emotional data. Using the device's sensors and camera, it acquires real-time user environmental information (location, temperature, humidity, etc.) and voice / facial expression data. This data is treated as input transmitted to the server. Data acquisition is performed in the background, ensuring it does not interrupt user interaction.

[0804] Step 3:

[0805] The server analyzes the received environmental and emotional data. Using a generative AI model, the server analyzes voice tone and performs natural language processing to identify emotions. Furthermore, it evaluates the current user situation based on sensor information. The acquired input data is structured, emotions and environmental information are identified, and based on this, the user's emotional state is output.

[0806] Step 4:

[0807] The server recommends products based on user attribute information, identified emotions, and environmental information. A recommendation algorithm runs, selecting appropriate products from a set of products. Using this data as input, the product recommendation algorithm is executed to generate an optimal product list. The output is a list of products that match the user's emotions.

[0808] Step 5:

[0809] A list of recommended products is sent to the user's device and displayed to them through an interactive screen. The user uses the screen to view detailed product information and then decide whether to purchase or add items to their list. After receiving the product list, the purchase decision is made based on the user's interaction. The UI / UX design ensures an intuitive and user-friendly interface.

[0810] Step 6:

[0811] After purchase, users are given the opportunity to provide feedback on the product to the system. This feedback includes user ratings and comments about the product. This feedback data is sent to the server and stored in a data set. Based on the feedback, the user preference model is updated for future purchases to improve recommendation accuracy. The input feedback is used to improve the user experience.

[0812] (Application Example 2)

[0813] 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".

[0814] In e-commerce, it has been difficult to grasp users' current emotional states in real time and provide personalized product recommendations and benefits that respond to those emotions. Traditional systems based recommendations solely on user feedback and preference data, and were unable to adequately address users' temporary emotions. Furthermore, the optimization of emotion-based incentives to improve the user's purchasing experience was insufficient.

[0815] 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.

[0816] In this invention, the server includes means for acquiring individual user information stored in a data storage system and interpreting the user's preferences and needs; means for receiving real-time situational information from various detection devices and understanding the user's situation; and means for evaluating the user's emotions in real time and providing benefits and incentives corresponding to those emotions. This enables accurate product recommendations and improved purchasing experiences based on the user's emotional state.

[0817] A "data storage system" is a system that stores data related to a user's individual information, preferences, and needs, and makes it available for retrieval as needed.

[0818] A "detection device" is a sensor device that collects information about the user's situation and environment in real time and transmits it to a server.

[0819] "Visual data" refers to images and video information provided by users, which is analyzed to identify products that the user is interested in or needs.

[0820] A "two-way interface" is a user interface that allows users and systems to exchange information with each other, and is a means of presenting product information and collecting opinions.

[0821] "User sentiment" refers to the psychological or emotional state a user exhibits while interacting with the system's interface, and is evaluated in real time.

[0822] "Benefits and incentives" are discounts, coupons, and other rewards offered emotionally to increase a user's willingness to purchase.

[0823] The system implementing this invention centers around a data storage system, multiple detection devices, and a server. The server retrieves individual user information stored in the data storage system and interprets preferences and needs through analysis. This enables the system to provide optimal product recommendations for each user.

[0824] The real-time sentiment assessment feature uses the camera and microphone equipped on the device to detect the user's emotions through image recognition and voice analysis technologies. Specific hardware used includes smartphones and tablets. The software utilizes Google Cloud's sentiment analysis API, which sends accurate sentiment data to the server.

[0825] The server combines emotional data with user preference information to provide rewards and incentives in real time. For example, if a user's emotional state, as measured in front of a vending machine, is relaxed, the server might offer a reward such as, "Buy this drink and receive a coupon for 50% off your next purchase."

[0826] Specifically, the system provides a personalized purchasing experience by instructing the AI ​​model based on a prompt message such as, "If the customer is highly satisfied with a purchased product, please suggest additional appropriate benefits." This enables detailed product recommendations and benefit offerings based on the user's emotions, resulting in a highly satisfying purchasing experience.

[0827] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0828] Step 1:

[0829] The terminal retrieves individual user information from the data storage system. The input is the user's account information, and the output includes their preferences and past purchase history. Based on this information, a user profile is created on the terminal to serve as the basis for future analysis.

[0830] Step 2:

[0831] Multiple detection devices acquire real-time information about the user's situation. The input consists of data from cameras and microphones, and the output is a dataset representing the user's current state. The server uses this dataset to understand the user's context and prepares for sentiment analysis in the next step.

[0832] Step 3:

[0833] The server analyzes the visual and audio data sent from the terminal. The input is the image and audio data obtained in the previous step, and the output is the user's emotional state. By using an emotion analysis API to specifically identify this emotional state, the server understands the user's psychological state.

[0834] Step 4:

[0835] The server combines the analyzed emotion data and profile information and sends a prompt to the generating AI model. An example of a prompt is, "Please suggest the best reward for this emotional state." The output is information on rewards and product recommendations generated by the AI.

[0836] Step 5:

[0837] The server sends the generated reward information to the user's device and notifies the user via a two-way interface. The input is the reward information, and the output is a reward presentation screen that the user can visually confirm. In this step, the user views the details of the offered rewards and products and makes a final purchase decision.

[0838] Step 6:

[0839] Users review the details of the offered benefits and products and send feedback to the server via their device. The input is the user's feedback, and the output is post-purchase evaluation information. This information is then stored again in the data storage system to help improve future recommendation processes.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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."

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] The following is further disclosed regarding the embodiments described above.

[0862] (Claim 1)

[0863] A means for obtaining user profile information stored in a database and analyzing the user's preferences and needs,

[0864] A means for receiving real-time environmental information from multiple sensor devices and understanding the user's context,

[0865] A means for analyzing image data provided by the user and identifying the product category required by the user,

[0866] A means for searching a product database based on the aforementioned preferences, needs, context, and product categories, and generating a product recommendation list,

[0867] A means of providing the aforementioned user with an interactive interface, explaining product information, and presenting information to promote purchase,

[0868] A means for collecting user feedback, storing it in a database, and analyzing it,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, further comprising means for identifying that the user is looking for items for a specific event based on the analyzed image data, and for comprehensively suggesting a number of relevant items.

[0872] (Claim 3)

[0873] The system according to claim 1, further comprising means for updating the preference model based on the user's purchase history and evaluation after collecting the aforementioned feedback, thereby improving the accuracy of recommendations in the next recommendation process.

[0874] "Example 1"

[0875] (Claim 1)

[0876] A means for obtaining user identification information stored in a data set and analyzing the user's preferences and needs,

[0877] A means for receiving real-time status information from multiple detection devices and understanding the user's status,

[0878] A means for analyzing the visual data provided by the user and identifying the product category requested by the user,

[0879] A means for searching for a collection of products based on the aforementioned preferences, needs, circumstances, and product classifications, and for creating a list of product suggestions.

[0880] The means of providing the user with an interactive display means, explaining product information, and displaying information to promote purchase,

[0881] A means for collecting the aforementioned user evaluation information, storing it in a data set, and analyzing it,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, further comprising means for determining that the user is looking for items for a specific event based on the analyzed visual data, and for comprehensively suggesting a number of relevant products.

[0885] (Claim 3)

[0886] The system according to claim 1, further comprising means for updating the user's preference model based on their purchase history and evaluations after collecting the evaluation information, thereby improving the accuracy of suggestions in the next suggestion process.

[0887] "Application Example 1"

[0888] (Claim 1)

[0889] A means for obtaining user profile information stored in a database and analyzing the user's preferences and needs,

[0890] A means for receiving real-time environmental information from multiple sensor devices and understanding the user's context,

[0891] A means for analyzing image data provided by the user and identifying the product category required by the user,

[0892] A means for searching a product database based on the aforementioned preferences, needs, context, and product categories, and generating a product recommendation list,

[0893] A means of providing the aforementioned user with an interactive interface, explaining product information, and presenting information to promote purchase,

[0894] A means for collecting user feedback, storing it in a database, and analyzing it,

[0895] A means of using computer vision technology to perform style discrimination based on images taken by the user and to identify the corresponding product,

[0896] A means of providing decision support to improve product recommendations by generating prompt sentences using a generative AI model,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, further comprising means for identifying that the user is looking for products for a specific event based on the analyzed image data, and for comprehensively suggesting a number of relevant items.

[0900] (Claim 3)

[0901] The system according to claim 1, further comprising means for updating the preference model based on the user's purchase history and evaluation after collecting the aforementioned feedback, thereby improving the accuracy of recommendations in the next recommendation process.

[0902] "Example 2 of combining an emotion engine"

[0903] (Claim 1)

[0904] A means for obtaining user attribute information stored in a data set and analyzing the user's preferences and requests,

[0905] A means for acquiring immediate environmental information from multiple sensors and understanding the user's situation,

[0906] The means of analyzing the diverse data (voice, text, facial expressions) provided by the aforementioned user and identifying emotions,

[0907] A means for searching for a group of products based on the aforementioned preferences, requirements, circumstances, and emotions, and for generating a list of recommended products,

[0908] A means of providing the user with an interactive operation screen, explaining product information, and presenting information to promote purchase,

[0909] A means for collecting the user's response, storing it in a data set, and analyzing it,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, further comprising means for identifying that the user is looking for items for a specific event based on the diverse data analyzed, and for comprehensively suggesting a number of relevant items.

[0913] (Claim 3)

[0914] The system according to claim 1, further comprising means for updating the preference model based on the user's purchase history and evaluation after collecting the aforementioned responses, thereby improving the recommendation accuracy in the next recommendation process.

[0915] "Application example 2 when combining with an emotional engine"

[0916] (Claim 1)

[0917] A means for obtaining individual user information stored in a data storage system and interpreting the user's preferences and needs,

[0918] A means for receiving real-time situational information from various detection devices and understanding the user's situation,

[0919] A means for analyzing the visual data provided by the user and identifying the product classification required by the user,

[0920] A means for searching product information storage based on the aforementioned preferences, needs, circumstances, and product classifications, and generating a product recommendation list,

[0921] A means of providing a two-way interface to the user, explaining product information, and presenting information to encourage purchase,

[0922] A means for collecting the aforementioned user opinions, storing them in a data storage system, and analyzing them,

[0923] A means of evaluating the emotions of the aforementioned users in real time and providing benefits and incentives corresponding to those emotions,

[0924] A system that includes this.

[0925] (Claim 2)

[0926] The system according to claim 1, further comprising means for identifying that the user is searching for items for a specific activity based on the analyzed visual data, and for comprehensively suggesting a plurality of such items.

[0927] (Claim 3)

[0928] The system according to claim 1, further comprising means for evaluating the user's emotional data and optimizing the effectiveness of the incentives provided, further comprising means for updating a preference model based on the user's purchase history and evaluations after collecting the aforementioned opinions, and for improving the accuracy of recommendations in the next recommendation process. [Explanation of symbols]

[0929] 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. A means for obtaining user profile information stored in a database and analyzing the user's preferences and needs, A means for receiving real-time environmental information from multiple sensor devices and understanding the user's context, A means for analyzing image data provided by the user and identifying the product category required by the user, A means for searching a product database based on the aforementioned preferences, needs, context, and product categories, and generating a product recommendation list, A means of providing the aforementioned user with an interactive interface, explaining product information, and presenting information to promote purchase, A means for collecting user feedback, storing it in a database, and analyzing it, A system that includes this.

2. The system according to claim 1, further comprising means for identifying that the user is looking for items for a specific event based on the analyzed image data, and for comprehensively suggesting a number of relevant items.

3. The system according to claim 1, further comprising means for updating the preference model based on the user's purchase history and evaluation after collecting the aforementioned feedback, thereby improving the recommendation accuracy in the next recommendation process.

Images