system

Abstract

To provide a system that provides personalized proposals tailored to a user's preferences and improves user satisfaction. [Solution] A system including: a means for a user to input basic information and preferences; a means for saving the input basic information and preferences in a database; a means for analyzing past purchase history based on the saved basic information and preferences; a means for collecting the latest trend data from an external data source and saving it in a database; a means for combining the user's basic information, past purchase history, and trend data to generate a suggestion list; a means for sending the generated suggestion list to the user's terminal; a means for collecting and analyzing user feedback on the suggested items; and a means for updating a machine learning model to improve the next suggestion list based on the feedback.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional fashion and cosmetics recommendation systems do not adequately consider users' preferences or past purchase history, and lack the ability to effectively utilize the latest trend data. As a result, the recommendations provided to users do not meet their individual needs, resulting in low user satisfaction. Furthermore, even if users provide feedback on recommended items, this feedback is not reflected in the next recommendation, making it difficult to improve the accuracy of the system. This poses a challenge, particularly for younger users, as it is difficult to alleviate anxiety about fashion and cosmetics choices. [Means for solving the problem]

[0005] The present invention provides a means for a user to input basic information and preferences and store them in a database. It also provides a means for analyzing past purchase history based on the stored information and collecting the latest trend data from external data sources and storing it in a database. It also includes a means for combining the user's basic information, past purchase history, and trend data to generate an optimal suggestion list and sending it to the user's device. When the user provides feedback on suggested items, it also includes a means for collecting and analyzing the feedback and updating a machine learning model to improve the next suggestion list. In this way, a system is provided that provides personalized suggestions tailored to the user's preferences and increases user satisfaction.

[0006] "User" refers to an individual who uses the system and receives fashion and cosmetic suggestions.

[0007] "Basic information" refers to information that can identify an individual, such as the user's height, weight, age, gender, and personal color.

[0008] "Preferences" refers to information such as favorite colors, styles, and items of interest that are selected and input by the user.

[0009] A "database" is a system for storing basic information and preferences of users, past purchase history, collected trend data, and the like.

[0010] "Past purchase history" refers to historical data on fashion items and cosmetics purchased by a user through the system.

[0011] "Analysis" refers to the process of analyzing collected data to identify user preferences and trends.

[0012] "Trend data" refers to information such as the latest fashion items, seasonal trends, and new products from popular brands.

[0013] "External Data Source" means an external information source used by the System to collect Trend Data.

[0014] A "suggestion list" is a recommended list of fashion items and cosmetics generated based on a user's basic information, preferences, past purchase history, and trend data.

[0015] A "terminal" is an electronic device, such as a computer or smartphone, that a user uses to operate the system and check suggestions.

[0016] "Feedback" refers to the act of a user providing an evaluation or opinion such as "good," "bad," or "favorite" about a proposed item.

[0017] A "machine learning model" is an algorithm used to better optimize future suggestions based on user feedback and past data. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention relates to a system that makes personalized fashion and cosmetic suggestions to users, and specific embodiments thereof will be described below.

[0040] User Data Collection and Storage

[0041] 1. When a user registers or logs in to the system, they first enter their email address and password.

[0042] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0043] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[0044] 4. The server stores these preferences in a database.

[0045] Analyzing user data

[0046] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0047] 6. The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends.

[0048] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0049] Personalized suggestion generation

[0050] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history.

[0051] 9. The server sends the proposal list to the user's device.

[0052] View suggestions and gather feedback

[0053] 10. The device displays the sent proposal list to the user. The proposal list is appropriately designed so that it is displayed in a format that is easy for the user to view.

[0054] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite."

[0055] 12. The device collects user feedback and sends it to the server.

[0056] 13. The server stores the received feedback in a database and analyzes it.

[0057] 14. The server updates the machine learning model based on the feedback to improve the next list of suggestions.

[0058] Specific examples

[0059] Example 1: 20-year-old female user A

[0060] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[0061] 2. User A prefers a casual style and selects that he likes blue and white.

[0062] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[0063] 4. The server combines these to generate a proposal list and sends it to User A's device.

[0064] 5. The device displays the suggestion list, and User A gives feedback on the floral print shirt as a "favorite."

[0065] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[0066] Example 2: For 25-year-old male user B

[0067] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[0068] 2. User B selects that he prefers a formal style and prefers black and gray.

[0069] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[0070] 4. The server combines these to generate a proposal list and sends it to User B's device.

[0071] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it.

[0072] 6. The server receives the feedback and purchase data and updates the machine learning model to improve the next list of suggestions.

[0073] This allows highly accurate proposals that meet the individual needs of the user to be provided, thereby improving user satisfaction.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] A user registers or logs in to the system. The user enters their email address and password for authentication.

[0077] Step 2:

[0078] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0079] Step 3:

[0080] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[0081] Step 4:

[0082] The server stores the selected preference information in a database.

[0083] Step 5:

[0084] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0085] Step 6:

[0086] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[0087] Step 7:

[0088] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0089] Step 8:

[0090] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[0091] Step 9:

[0092] The server transmits the generated proposal list to the user's terminal.

[0093] Step 10:

[0094] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[0095] Step 11:

[0096] The user gives feedback on the suggested items, such as "good," "bad," or "favorite." Feedback is input from the device.

[0097] Step 12:

[0098] The device collects user feedback and sends it to the server, where it is stored in a database.

[0099] Step 13:

[0100] The server analyzes the received feedback and updates the machine learning model based on the feedback data.

[0101] Step 14:

[0102] The server uses the updated machine learning model to further improve the next list of suggestions.

[0103] Step 15:

[0104] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[0105] Example 1

[0106] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0107] A system that efficiently provides users with personalized fashion and cosmetic recommendations is required to accurately grasp user preferences and trends and quickly incorporate the latest trend data. However, conventional systems have been unable to provide recommendations that fully reflect user preferences, resulting in low user satisfaction. Furthermore, it has been difficult to effectively utilize feedback information and incorporate it into subsequent recommendations, which has led to delays in system improvements.

[0108] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0109] In this invention, the server includes an interface means for the user to input basic information and preferences, a means for saving the input basic information and preferences in a database, and a means for analyzing past purchase history based on the saved basic information and preferences, thereby enabling highly accurate suggestions that meet the individual needs of the user.

[0110] "Interface means" refers to a display device or input device that allows a user to input basic information and preferences.

[0111] "Database" refers to an information storage system for storing user basic information, preferences, purchase history, feedback information, trend data, and the like.

[0112] "Analysis means" refers to a processing device or software that uses stored data to analyze a user's purchase history, preferences, trend data, etc.

[0113] "External data source" refers to an information provider, such as an API or web service, that can be used to obtain the latest trend data from outside the system.

[0114] "Suggestion list" refers to a recommended list of fashion and cosmetic items that is generated based on the analysis results and provided to the user.

[0115] "Terminal" refers to a device, such as a smartphone or PC, on which a user receives and displays the suggestion list and enters feedback.

[0116] "Feedback" refers to information that a user inputs about a proposed item, such as their evaluation or opinion.

[0117] "Machine learning model" refers to an algorithm or numerical model that uses user data and feedback to improve the accuracy of suggestions across the system.

[0118] The present invention is a system for providing personalized fashion and cosmetic suggestions to users. Specific embodiments are described below.

[0119] User Data Collection

[0120] When a user registers or logs in to the system, they first enter their email address and password. They then enter basic information such as their height, weight, age, gender, and personal color. This is done using an input interface in a web browser or mobile app, and is developed based on the Django framework.

[0121] The entered information is collected by the server and stored in a PostgreSQL database. The user then enters their preferred colors, styles, items of interest, etc., and this information is also stored in the database.

[0122] Analyzing user data

[0123] The server retrieves the user's past purchase history from the database and processes the data using Python's Pandas library. The server then analyzes the user's past purchase history using machine learning algorithms, specifically clustering and collaborative filtering using the Scikit-Learn library.

[0124] Next, the server collects the latest trend data from external data sources. This is done using APIs from fashion and cosmetics websites, such as Style API and Fashion Cloud API. The collected trend data is then stored in a database.

[0125] Personalized suggestion generation

[0126] The server uses machine learning models to generate a personalized recommendation list based on the user's basic information, preferences, and past purchase history. This recommendation list includes fashion items and cosmetics that are best suited to the user. The generated recommendation list is sent to the user's device in JSON format via the HTTP protocol.

[0127] View suggestions and gather feedback

[0128] The user's device displays the submitted list of suggestions in an easy-to-read format. The front-end is developed using React and Vue.js. The user can then enter feedback on the suggested items, such as "good," "bad," or "favorite."

[0129] Feedback is collected on the device and sent to the server via XMLHttpRequest or Fetch API. The server stores the received feedback in a database and retrains the machine learning model using Scikit-Learn or TENSORFLOW®. This process improves the list of suggestions for the next iteration.

[0130] Specific examples

[0131] For User A

[0132] 1. User A logs in to the system and enters basic information such as height 160 cm, weight 50 kg, and personal color "spring."

[0133] 2. User A prefers casual style and selects that he likes blue and white.

[0134] 3. The server analyzes past purchase history (e.g., blue denim, white T-shirt) and collects "floral print shirt" and "light blue denim" as the latest trend data.

[0135] 4. The server combines these to generate a proposal list and sends it to User A's device.

[0136] 5. The device displays the suggestion list, and User A gives feedback that the floral print shirt is his favorite.

[0137] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[0138] Specific examples of prompts are as follows:

[0139] "I'm a 20-year-old woman, 160cm tall and weigh 50kg. I like casual style and I like blue and white. Please suggest some of the latest trendy items."

[0140] In this way, the system can provide highly accurate suggestions that meet the individual needs of the user, improving user satisfaction.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1:

[0143] When a user registers or logs in to the system, they enter their email address and password. The entered email address and password are sent to the server through the input fields of the form. The server receives them and performs authentication processing. Input: Email address and password. Output: Authentication result (success or failure). If authentication is successful, the user will be taken to the next screen where they will be asked to enter basic information.

[0144] Step 2:

[0145] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and saves it in a database. Input: Basic user information. Output: Basic user information saved in the database. The data is processed using the Django framework and saved in a PostgreSQL database.

[0146] Step 3:

[0147] The user selects and inputs preferences such as favorite colors, styles, and items of interest. This data is sent to the server through the interface. Input: Favorite colors, styles, and items. Output: Sent preference information. The server receives this and stores it in a database.

[0148] Step 4:

[0149] The server retrieves past purchase history from the database. A user's purchase history includes details such as the category, color, and brand of the purchased items. Input: User ID. Output: Past purchase history data. The server retrieves the purchase history data and organizes it using Python's Pandas library.

[0150] Step 5:

[0151] The server uses a machine learning algorithm based on the Scikit-Learn library to analyze past purchase history. The analysis results are used to identify user preferences and trends. Input: Past purchase history data. Output: User preferences and trends. Analysis is performed using clustering and collaborative filtering techniques.

[0152] Step 6:

[0153] The server collects the latest trend data from external data sources. This uses a RESTful API to obtain the latest trend information on fashion and cosmetics. Input: API endpoint of external data source. Output: Latest trend data. For example, data can be collected using Style API or Fashion Cloud API and stored in a database.

[0154] Step 7:

[0155] The server generates an individualized recommendation list based on the user's basic information, preferences, and past purchase history. The recommendation list reflects the analysis results and the latest trend data. Input: User's basic information, preferences, past purchase history, trend data. Output: Suggestion list. A Scikit-Learn model is used to suggest the most suitable fashion items and cosmetics.

[0156] Step 8:

[0157] The server sends the generated proposal list to the user's device in JSON format. Input: Proposal list. Output: Sent proposal list. Data is sent securely using the HTTP / HTTPS protocol.

[0158] Step 9:

[0159] The device displays the suggestion list to the user in an easy-to-read format. The suggestion list is rendered using the React or Vue.js framework. Input: Suggestion list. Output: Displayed suggestion list. The user reviews the suggestion list and selects an item.

[0160] Step 10:

[0161] The user gives feedback on the suggested items, such as "good", "bad", or "favorite". Input: Feedback information. Output: Submitted feedback information. The user enters feedback using a form or buttons.

[0162] Step 11:

[0163] The device collects user feedback and sends it to the server via XMLHttpRequest or Fetch API. Input: Feedback information. Output: Feedback information sent to the server.

[0164] Step 12:

[0165] The server stores the received feedback information in a database and analyzes the data using Scikit-Learn and TensorFlow. Input: Feedback information. Output: Analysis results. The model is retrained and improved based on the feedback information.

[0166] Step 13:

[0167] The server uses the retrained machine learning model to improve the next list of suggestions. By periodically updating the model, the accuracy of suggestions to users increases. Input: Feedback data. Output: Improved list of suggestions. The update process is scheduled using Cron or Celery.

[0168] (Application example 1)

[0169] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0170] Today's consumers are increasingly seeking personalized fashion and cosmetic recommendations. However, conventional systems struggle to reflect user preferences and trends in real time, resulting in insufficient consumer satisfaction. Furthermore, there are few ways to visually confirm suggested items in real time, limiting the shopping experience. Therefore, it is necessary to improve the user experience by providing a personalized recommendation system that can overlay items onto the user's field of view.

[0171] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0172] In this invention, the server

[0173] a means for users to input basic information and preferences;

[0174] means for storing the entered basic information and preferences in a database;

[0175] means for analyzing past purchases based on stored basic information and preferences;

[0176] A means of collecting and storing up-to-date trend data from external data sources in a database;

[0177] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[0178] means for transmitting the generated proposal list to a user terminal;

[0179] means for collecting and analyzing user feedback on the proposed items;

[0180] means for updating a machine learning model to improve the next list of suggestions based on the feedback;

[0181] means for overlaying personalized suggestions onto the user's field of view;

[0182] a means for displaying recommended items in real time based on user preferences and trend data;

[0183] means for updating the recommended items based on user ratings;

[0184] Includes:

[0185] This allows for highly accurate personalized suggestions to be made based on user preferences and trends, and visual confirmation and feedback.

[0186] "User" refers to a consumer who accesses the system and enters basic information and preferences.

[0187] "Basic information" is data relating to personal attributes such as height, weight, age, sex, and personal color entered by the user.

[0188] "Preferences" refers to data on the user's tastes and preferences, such as colors and styles selected by the user, and items of interest.

[0189] A "database" is a collection of electronic data that stores basic user information, preferences, past purchase history, trend data, etc., and stores it in a format that can be used by the system.

[0190] "Past purchase history" refers to information such as category, color, brand, etc., relating to items previously purchased by the user.

[0191] "External data sources" refers to the source of the latest trend data that the system obtains from external fashion sites and APIs.

[0192] "Trend data" is information about current fashion and cosmetic trends.

[0193] The "suggestion list" is a list of recommended items for a user, generated by combining the user's basic information, past purchase history, and trend data.

[0194] "User device" refers to the user's electronic device (smartphone, tablet, PC, etc.) used to collect and send suggestion lists and feedback.

[0195] "Feedback" is data of evaluations and opinions given by users regarding proposed items.

[0196] "Machine Learning Model" means the algorithm and model used to analyze data and optimize personalized recommendations.

[0197] "Overlaying in the field of view" means overlaying suggested items directly in the user's field of view using smart glasses or the like.

[0198] "Displaying recommended items in real time" means instantly displaying recommended items that are appropriate for the moment when the user uses the system.

[0199] "Updating recommended items based on ratings" means adjusting and improving the algorithm for generating the next list of suggestions based on feedback from users.

[0200] The present invention provides a system for providing personalized fashion and cosmetic recommendations to users, specifically, a system for displaying recommended items in real time using smart glasses. Specific embodiments for implementing the present invention are described below.

[0201] System Program

[0202] The system consists of a program with the following main functions:

[0203] 1. The user enters basic information and preferences.

[0204] 2. Store your basic information and preferences in our database.

[0205] 3. Analyze past purchase history based on the stored information.

[0206] 4. Collect the latest trend data from external data sources and store it in the database.

[0207] 5. Generate a list of suggestions by combining basic user information, past purchase history, and trend data.

[0208] 6. The proposal list is sent to the user's device.

[0209] 7. Collect and analyze user feedback on the proposed items.

[0210] 8. Update the machine learning model to improve the next list of suggestions based on feedback.

[0211] 9. Overlay personalized suggestions into the user's field of view.

[0212] 10. Update recommended items in real time based on user ratings.

[0213] Processing Details

[0214] The server stores the user's basic information and preferences in a database, including height, weight, age, gender, personal color, favorite colors and styles, and favorite items. The server also collects the latest trend information from external data sources and stores it in the database. Using this data, a machine learning algorithm analyzes the user's past purchase history and generates a personalized recommendation list based on the user's preferences and the latest trends.

[0215] The user's device, such as smart glasses, receives this list of suggestions and displays it as an overlay in the user's field of view. The user's ratings and feedback on the suggested items are sent to the server via the device, and the server uses this feedback to update the machine learning model and make the next suggestions more accurate.

[0216] The hardware used includes smart glasses (e.g., Google® Glass®, Apple Glass). These devices are used to overlay suggested items onto the user's field of vision. The server and device programs are implemented using Python, machine learning algorithms, and RESTful APIs.

[0217] Examples and prompts

[0218] As an example, consider how a 20-year-old female user A uses the system.

[0219] 1. User A logs in to the system and enters his height of 160 cm, weight of 50 kg, and personal color of "spring."

[0220] 2. You choose to have a casual style and prefer blue and white.

[0221] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt) and collects the latest spring trend data (e.g., floral print shirt, light blue denim).

[0222] 4. The server combines these to generate a proposal list and sends it to the smart glasses.

[0223] 5. The smart glasses overlay the suggestion list onto User A's field of view, and User A gives feedback that the floral print shirt is a "favorite."

[0224] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[0225] An example of a prompt is:

[0226] User ID: user_12345

[0227] Basic information: Height 160cm, weight 50kg, personal color "Spring"

[0228] Purchase history: Blue jeans, white T-shirt

[0229] Preferences: Blue and white, casual style

[0230] Trend data: Spring trends include floral print shirts and light blue denim

[0231] Feedback: Floral print shirt is my favorite

[0232] As described above, the present invention provides a system that can make personalized fashion and cosmetic suggestions to users in real time.

[0233] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0234] Step 1:

[0235] The user enters basic information and preferences. After logging in, the user enters their height, weight, age, gender, personal color, favorite colors and styles, and items of interest through the smart glasses. The entered information is sent to the server.

[0236] input:

[0237] Height, weight, age, gender, personal color

[0238] Favorite colors, styles, and items

[0239] output:

[0240] The input data is sent to the server and stored in a database.

[0241] Step 2:

[0242] The server stores the received user's basic information and preferences in a database.

[0243] input:

[0244] Basic information and preferences submitted by you

[0245] output:

[0246] User information stored in a database

[0247] Step 3:

[0248] The server analyzes past purchase history based on the stored information. The server retrieves the user's past purchase history stored in the database and analyzes it using a machine learning algorithm.

[0249] input:

[0250] User's past purchase history retrieved from the database

[0251] output:

[0252] Analysis results showing user preferences and trends

[0253] Step 4:

[0254] Collect the latest trend data from external data sources and store it in the database. The server uses an external API to get the latest trend information and store it in the database.

[0255] input:

[0256] Trend data obtained from external APIs

[0257] output:

[0258] Trend data stored in a database

[0259] Step 5:

[0260] The server generates a list of recommendations by combining basic user information, past purchase history, and trend data. The server then uses a machine learning algorithm to generate the optimal list of recommendations based on the acquired data.

[0261] input:

[0262] User Basic Information

[0263] Past purchase history

[0264] Trend Data

[0265] output:

[0266] Suggestion List

[0267] Step 6:

[0268] Sending the proposal list to the user's terminal: The server sends the generated proposal list to the user's terminal, such as smart glasses.

[0269] input:

[0270] Suggestion List

[0271] output:

[0272] The proposal list sent to the user's device

[0273] Step 7:

[0274] The server collects and analyzes user feedback on the proposed items. Users input their ratings and opinions on the proposed items through the smart glasses. The server collects this feedback and stores it in a database.

[0275] input:

[0276] User Feedback

[0277] output:

[0278] Feedback stored in the database

[0279] Step 8:

[0280] Update the machine learning model to improve the next list of suggestions based on the feedback. The server analyzes the collected feedback and uses it to improve the machine learning model.

[0281] input:

[0282] Feedback stored in the database

[0283] output:

[0284] Improved machine learning models

[0285] Step 9:

[0286] Overlaying personalized suggestions onto the user's field of view: The smart glasses overlay items from the suggestion list onto the user's field of view.

[0287] input:

[0288] Suggestion List

[0289] output:

[0290] Overlaid suggested items

[0291] Step 10:

[0292] Update recommended items in real time based on user ratings: The smart glasses instantly adjust and update suggested items based on user feedback.

[0293] input:

[0294] User Feedback

[0295] output:

[0296] Updated Suggested Items

[0297] This allows users to receive personalized fashion and cosmetic suggestions in real time.

[0298] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0299] The present invention relates to a system that proposes personalized fashion and cosmetic products to a user, and further includes an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[0300] User Data Collection and Storage

[0301] 1. When a user registers or logs in to the system, they first enter their email address and password for authentication.

[0302] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0303] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[0304] 4. The server stores these preferences in a database.

[0305] Analyzing user data

[0306] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0307] 6. The server uses machine learning algorithms to analyze past purchase history and analyze user preferences and trends, and stores the results of this analysis in a database.

[0308] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0309] Personalized suggestion generation

[0310] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history. The generated list is stored in a database.

[0311] 9. The server sends the generated proposal list to the user's device.

[0312] Displaying suggestions, collecting feedback, and emotion recognition

[0313] 10. The device displays the sent proposal list to the user. The displayed proposal list is presented in a format that is easy for the user to view.

[0314] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[0315] 12. The device collects the user's feedback and emotion data and sends it to the server, where it is stored in a database.

[0316] 13. The server analyzes the received feedback and sentiment data. It updates the machine learning model based on the feedback data.

[0317] 14. The server uses the emotional data as information to further tailor the next suggestion list to the user's preferences.

[0318] Specific examples

[0319] Example 1: 20-year-old female user A

[0320] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[0321] 2. User A prefers a casual style and selects that he likes blue and white.

[0322] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[0323] 4. The server combines these to generate a proposal list and sends it to User A's device.

[0324] 5. The device displays the list of suggestions, and User A provides feedback on the floral print shirt as a "favorite," and the emotion engine also collects User A's facial expression data.

[0325] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[0326] Example 2: For 25-year-old male user B

[0327] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[0328] 2. User B selects that he prefers a formal style and prefers black and gray.

[0329] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[0330] 4. The server combines these to generate a proposal list and sends it to User B's device.

[0331] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it. The emotion engine also simultaneously collects User B's emotion data.

[0332] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[0333] This allows the system to provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. In addition, by utilizing emotion data, more detailed responses are possible, further improving the accuracy of suggestions made by the system as a whole.

[0334] The processing flow will be explained below.

[0335] Step 1:

[0336] A user registers or logs in to the system. The user enters their email address and password for authentication.

[0337] Step 2:

[0338] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0339] Step 3:

[0340] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[0341] Step 4:

[0342] The server stores the selected preference information in a database.

[0343] Step 5:

[0344] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0345] Step 6:

[0346] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[0347] Step 7:

[0348] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0349] Step 8:

[0350] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[0351] Step 9:

[0352] The server transmits the generated proposal list to the user's terminal.

[0353] Step 10:

[0354] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[0355] Step 11:

[0356] Users provide feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[0357] Step 12:

[0358] The terminal collects the user's feedback and emotion data and sends it to the server, which stores the feedback and emotion data in a database.

[0359] Step 13:

[0360] The server analyzes the received feedback and sentiment data and updates the machine learning model based on the feedback data.

[0361] Step 14:

[0362] The server uses the emotional data as information to further match the next suggestion list to the user's preferences.

[0363] Step 15:

[0364] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[0365] Example 2

[0366] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0367] Conventional online shopping systems have a problem in that recommendations to users are not personalized, making it difficult to provide items that match the individual preferences of each user. In addition, feedback data is limited to simple evaluations such as "good" or "bad," making it difficult to improve the accuracy of recommendations that reflect the user's true feelings and preferences.

[0368] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting and analyzing user feedback on proposed items; means for acquiring feedback and emotion data on the proposed items; and means for updating a machine learning model to improve the next proposal list based on the feedback and emotion data. This makes it possible to make personalized proposals based on the user's basic information, preferences, past purchase history, and latest trend data, and to provide highly accurate proposals that reflect the user's true emotions and preferences.

[0369] 1. "User" refers to an individual who uses the System and enters basic information and preferences.

[0370] 2. "Basic information" refers to basic data about the user, such as height, weight, age, gender, and personal color.

[0371] 3. "Preferences" refers to information such as the user's preferred colors, styles, and items of interest.

[0372] 4. "Database" refers to data storage within the system for safely and efficiently storing users' basic information, preferences, past purchase history, trend data, feedback, and sentiment data.

[0373] 5. "Purchase history" refers to detailed information such as category, color, and brand of products purchased by a user in the past.

[0374] 6. "External data source" refers to a source of information for obtaining data from outside the system, such as online fashion sites or trend information services.

[0375] 7. "Latest Trend Data" refers to data showing the latest fashions and trends in fashion and cosmetics.

[0376] 8. "Suggestion List" refers to a personalized list of items generated by combining a user's basic information, preferences, past purchase history, and trend data.

[0377] 9. "Terminal" refers to the electronic device, such as a computer, smartphone, or tablet, that a User uses to access the System and view the Proposal List.

[0378] 10. "Feedback" refers to the evaluations and opinions of users regarding proposed items, such as "good," "bad," or "favorite."

[0379] 11. "Emotional Data" means data that indicates a user's emotional state, collected based on the user's facial expressions and behavior.

[0380] 12. “Machine Learning Model” means an algorithmic model used to optimize recommendations based on user preferences, feedback, and sentiment data.

[0381] 13. "System" refers to a collection of computer programs and hardware that includes a set of processes for collecting and analyzing user data, generating a list of suggestions, and collecting and analyzing feedback.

[0382] This invention is a system that provides personalized fashion and cosmetic recommendations to users, and combines it with an emotion engine that recognizes the user's emotions. The system analyzes the user's input information and generates optimal recommendations.

[0383] System configuration

[0384] The system consists of the following main components:

[0385] 1. User terminal: refers to the device (e.g., computer, smartphone, tablet) through which a user enters information and receives a list of suggestions.

[0386] 2. Server: The central system that performs the main processing such as data collection, analysis, storage, and generating suggestion lists.

[0387] 3. Database: Storage within the system that stores users' basic information, preferences, past purchase history, trend data, feedback and sentiment data.

[0388] 4. Emotion engine: Software for collecting and analyzing emotional data from the user's facial expressions and voice (e.g., OpenCV, Emotion API).

[0389] Main software and hardware used

[0390] Machine learning algorithms: Machine learning libraries such as Scikit-learn and TensorFlow are used to analyze user preferences and purchase history.

[0391] External interface: Uses the API of fashion sites to collect the latest trend data.

[0392] Database management system: Uses a relational database such as MySQL (registered trademark) or PostgreSQL.

[0393] Sentiment analysis tools: OpenCV, Emotion API

[0394] Detailed System Operation

[0395] 1. User Registration and Authentication

[0396] When a user registers or logs in to the system, they enter their email address and password. The server authenticates this and, if successful, issues a token and returns it to the user.

[0397] 2. Enter your basic information and preferences

[0398] Users input basic information such as height, weight, age, gender, and personal color. They also select their preferred colors, styles, and items of interest. The server acquires this information and stores it in a database.

[0399] 3. User Data Analysis

[0400] The server retrieves the user's past purchase history from the database, analyzes it using Scikit-learn and TensorFlow, and analyzes the user's preferences and trends. It also collects the latest trend data through an external interface and stores it in the database.

[0401] 4. Generate and send a proposal list

[0402] The server combines the user's basic information, preferences, past purchase history, and trend data to generate the optimal recommendation list, which is then stored in a database in JSON format and sent to the user's device.

[0403] 5. View the list of suggestions and gather feedback

[0404] The user terminal displays the list of suggestions, and the user gives feedback such as "good," "bad," or "favorite." In addition, an emotion engine is used to collect emotional data from the user's facial expressions and voice.

[0405] 6. Analysis of Feedback and Emotion Data

[0406] The server collects and analyzes user feedback and sentiment data to update the machine learning model to improve the next list of suggestions.

[0407] Specific examples

[0408] Example 1: 20-year-old female user A

[0409] User A logs into the system and enters basic information (e.g., height 160 cm, weight 50 kg, personal color "spring"). He selects his preferred style (e.g., casual, blue and white colors). The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt), collects the latest trend data (e.g., "floral print shirt" and "light blue denim"), and generates a suggestion list. This suggestion list is sent to User A's device. User A provides feedback on the suggested items, saying "favorite," and the emotion engine collects facial expression data. The server analyzes this and improves the next suggestion list.

[0410] Prompt Sentence Examples

[0411] "What latest fashion items would you suggest to a 20-year-old woman who likes blue and white for her spring casual style?"

[0412] In this way, this system can provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. Furthermore, by utilizing emotion data, even more detailed responses are possible, further improving the accuracy of suggestions.

[0413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0414] System program processing flow

[0415] Step 1:

[0416] A user registers or logs in to the system. Specifically, the user enters their email address and password, and this data is sent to the server. The server receives this and performs authentication. If authentication is successful, the server generates an authentication token and returns it to the user. The input is an email address and password, and the output is an authentication token.

[0417] Step 2:

[0418] The user enters basic information (height, weight, age, gender, personal color, etc.) and preferences (color, style, items of interest, etc.). The entered data is sent to the server. The server receives this data and stores it in a database. The input is the user's basic information and preferences, and the output is the results stored in the database.

[0419] Step 3:

[0420] The server retrieves the user's past purchase history from the database. Specifically, it uses an SQL query to extract the user's purchase history data. This purchase history data is used for data analysis. The input is the purchase history retrieved from the database, and the output is the past purchase history data used for analysis.

[0421] Step 4:

[0422] The server uses a machine learning algorithm (e.g., Scikit-learn) to analyze the user's past purchase history and identify trends and preferences. The input is past purchase history data, and the output is the analysis results of the user's preferences. Specifically, the server performs a series of analytical processes, including feature extraction, data preprocessing, and model training.

[0423] Step 5:

[0424] The server collects the latest trend data from an external data source (e.g., a fashion site's API). It requests the trend data through the API and stores the acquired data in a database. The input is the latest trend data acquired from outside, and the output is the trend data stored in the database.

[0425] Step 6:

[0426] The server generates a list of suggestions by combining the user's basic information, preferences, past purchase history, and the latest trend data. Specifically, it uses an algorithm to integrate information from each data source and select the most suitable items. The input is the user's basic information, preferences, purchase history, and trend data, and the output is the generated list of suggestions (e.g., in JSON format).

[0427] Step 7:

[0428] The server sends the generated proposal list to the user's device. Specifically, it uses a REST API to send the proposal list to the user's device. The input is the generated proposal list, and the output is the receipt of the proposal list on the user's device.

[0429] Step 8:

[0430] The terminal displays the suggestion list to the user in an easy-to-view format, including item images, descriptions, prices, etc. The input is the received suggestion list, and the output is the suggestions displayed on the user terminal.

[0431] Step 9:

[0432] The user inputs feedback on the proposed item. Specifically, the user rates the item as "good," "bad," or "favorite," and inputs the feedback data. The input is the user's feedback information, and the output is sending the feedback data to the server.

[0433] Step 10:

[0434] The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. The input is the user's facial expressions and voice data, and the output is the collected emotional data. Specific operations involve the use of image and voice analysis algorithms.

[0435] Step 11:

[0436] The terminal transmits the user's feedback and emotion data to the server. Specifically, the data is converted into an appropriate format and sent to the server. The input is the feedback and emotion data, and the output is data transmission to the server.

[0437] Step 12:

[0438] The server analyzes the received feedback and emotion data. The input is the sent feedback and emotion data, and the output is the analysis results. Specifically, it performs data analysis based on the feedback and emotion data and updates the machine learning model.

[0439] Step 13:

[0440] The server generates information based on the analysis results to improve the next suggestion list. The input is the analysis results, and the output is an improved suggestion list. Specifically, the server applies the retrained machine learning model to make suggestions that better match the user's preferences.

[0441] The above is the flow of processing in the system program and the specific operations of each step.

[0442] (Application example 2)

[0443] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0444] Modern consumers demand personalized product recommendations based on their preferences and trends, but existing systems do not adequately meet these demands. Furthermore, existing systems are unable to accurately capture users' emotions, resulting in inaccurate recommendations. Therefore, there is a need for a system that can collect users' individual emotions and feedback in real time and provide more accurate personalized recommendations.

[0445] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting the latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting feedback and emotion data from the user about the proposed items; means for analyzing the collected feedback and emotion data and updating a machine learning model to improve the next proposal list; and means including an emotion recognition engine for visually displaying the proposal list and collecting emotion data from the user in real time. This enables highly accurate proposals that meet the individual needs of the user and improves user satisfaction.

[0446] "Means for users to input basic information and preferences" refers to an interface that allows users to input information such as height, weight, age, gender, personal color, and preferred styles and colors.

[0447] "Means for storing in a database" refers to software and hardware for securely storing the entered basic information and preferences in a database.

[0448] "Means for analyzing past purchase history" refers to algorithms and software used to analyze the categories, colors, brands, etc. of items a user has previously purchased to identify the user's preferences and tendencies.

[0449] "Means for collecting the latest trend data from external data sources and storing it in a database" refers to software and hardware for collecting the latest trend information from external fashion sites and APIs and storing it in a database.

[0450] "Means for generating a suggestion list" refers to algorithms and software for generating a list that suggests suitable fashion items and cosmetics to a user based on the user's basic information, past purchase history, and the latest trend data.

[0451] "Means for transmitting the generated proposal list to the user's terminal" refers to software and communication means for transmitting the generated proposal list to the user's smartphone, smart glasses, head-mounted display, etc.

[0452] "Means for collecting feedback and emotional data" refers to the interface and software for capturing user feedback on the proposed item and emotional data collected using the emotion recognition engine.

[0453] "Means for analyzing collected feedback and sentiment data" refers to algorithms and software for analyzing collected feedback and sentiment data to improve the accuracy of the next list of suggestions.

[0454] "Means for updating machine learning models" refers to machine learning algorithms and software for continuously improving the algorithms for generating the recommendation list based on feedback and sentiment data.

[0455] An "emotion recognition engine" refers to software and hardware for collecting and analyzing emotional data from a user's facial expressions and voice in real time.

[0456] The present invention is a system that provides personalized fashion and cosmetic recommendations to users, and improves the accuracy of recommendations based on the user's emotional data by incorporating an emotion recognition engine. Specific embodiments of the present invention are described in detail below.

[0457] User Data Collection and Storage

[0458] This system provides an interface for users to input their basic information and preferences on devices such as smartphones, smart glasses, and head-mounted displays. Users enter information such as height, weight, age, gender, personal color, and preferred styles and colors, and this information is stored in a database. Database management uses common database solutions (e.g., MySQL, PostgreSQL).

[0459] Data analysis

[0460] The server analyzes past purchase history based on the stored user basic information and preference data. It uses machine learning algorithms (e.g., Logistic Regression, Random Forest) to retrieve past purchase data from the database and analyze the user's preferences and purchasing trends. It also collects the latest fashion trend information from external data sources via API and stores this information in the database.

[0461] Personalized suggestion generation

[0462] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. This recommendation list uses an algorithm to select the most suitable items and list them in an order that suits the user. The generated recommendation list is then saved back in the database. The recommendation list is then sent to the user's device and displayed visually.

[0463] Displaying suggestions, collecting feedback, and emotion recognition

[0464] The device displays the suggested items to the user, who then inputs feedback such as "good," "bad," or "favorite." At the same time, an emotion recognition engine (e.g., EmotionRecognitionEngine) is used to collect real-time emotional data from the user's facial expressions and voice. This feedback and emotional data is sent from the device to a server and stored in a database.

[0465] Analyzing Data and Updating Models

[0466] The server analyzes the collected feedback and sentiment data and updates the machine learning model for generating the next recommendation list. The collected data is an important factor in improving the accuracy of the recommendation list generation algorithm.

[0467] Specific examples

[0468] For example, a 30-year-old female user logs in and registers data such as her height of 165 cm, weight of 55 kg, personal color of "winter," and preferred style of "elegant." The server will suggest a "black slim-fit dress" and a "silver necklace" based on her past purchase history and the latest trends. The user will then provide feedback that they are "favorites," and the emotion engine will recognize their facial expression of satisfaction.

[0469] Prompt Sentence Examples

[0470] text

[0471] User data: Height 165cm, Weight 55kg, Personal color "Winter", Favorite style "Elegant"

[0472] Previous purchase history: Black slim-fit dress, silver necklace

[0473] The latest trend: elegant pieces in black and silver

[0474] Feedback: Favorite

[0475] Emotion data: Satisfied facial expression

[0476] This allows for highly accurate proposals that meet the individual needs of users, thereby improving user satisfaction.

[0477] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0478] Step 1:

[0479] The server provides an interface for users to input their basic information and preferences on their devices. The information entered by users, such as height, weight, age, gender, personal color, and preferred style and color, is stored in a database via the device. The input data is encrypted to ensure security.

[0480] Step 2:

[0481] The server retrieves the basic information and preference data stored in the database, pulls the user's past purchase history from the database, and performs an analysis. Machine learning algorithms (e.g., Logistic Regression, Random Forest) are used to identify the user's preferences and purchasing trends. The results of this analysis are stored in the database as new data points and are later used to generate recommendations.

[0482] Step 3:

[0483] The server collects the latest fashion trend information through APIs of external data sources. The collected information is stored in a database and pre-processed to ensure accuracy and consistency, including filtering unnecessary data and normalizing the data.

[0484] Step 4:

[0485] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. It uses machine learning algorithms to analyze and select the items that best suit the user. This recommendation list is stored in a database and later sent to the device.

[0486] Step 5:

[0487] The generated suggestion list is sent to the user's device, which then displays the suggested items to the user in a visually appealing and easily understandable format, with optimized UI / UX design.

[0488] Step 6:

[0489] The user provides feedback on the suggested items, such as "good," "bad," or "favorite." The device analyzes the user's facial expressions and voice in real time using an emotion recognition engine (e.g., EmotionRecognitionEngine) to collect emotional data. The collected feedback and emotional data are sent from the device to a server and stored in a database.

[0490] Step 7:

[0491] The server analyzes the collected feedback and sentiment data and updates the machine learning model with new learning data to improve the accuracy of the next recommendation list. Model updates include retraining and tuning hyperparameters.

[0492] Step 8:

[0493] The server uses the updated machine learning model to generate the next list of suggestions, which can be more tailored to the user's individual needs.

[0494] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0495] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0496] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0497] [Second embodiment]

[0498] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0499] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0500] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0501] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0502] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0504] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0505] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0506] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0507] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0508] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0509] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0510] The present invention relates to a system that makes personalized fashion and cosmetic suggestions to users, and specific embodiments thereof will be described below.

[0511] User Data Collection and Storage

[0512] 1. When a user registers or logs in to the system, they first enter their email address and password.

[0513] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0514] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[0515] 4. The server stores these preferences in a database.

[0516] Analyzing user data

[0517] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0518] 6. The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends.

[0519] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0520] Personalized suggestion generation

[0521] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history.

[0522] 9. The server sends the proposal list to the user's device.

[0523] View suggestions and gather feedback

[0524] 10. The device displays the sent proposal list to the user. The proposal list is appropriately designed so that it is displayed in a format that is easy for the user to view.

[0525] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite."

[0526] 12. The device collects user feedback and sends it to the server.

[0527] 13. The server stores the received feedback in a database and analyzes it.

[0528] 14. The server updates the machine learning model based on the feedback to improve the next list of suggestions.

[0529] Specific examples

[0530] Example 1: 20-year-old female user A

[0531] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[0532] 2. User A prefers a casual style and selects that he likes blue and white.

[0533] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[0534] 4. The server combines these to generate a proposal list and sends it to User A's device.

[0535] 5. The device displays the suggestion list, and User A gives feedback on the floral print shirt as a "favorite."

[0536] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[0537] Example 2: For 25-year-old male user B

[0538] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[0539] 2. User B selects that he prefers a formal style and prefers black and gray.

[0540] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[0541] 4. The server combines these to generate a proposal list and sends it to User B's device.

[0542] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it.

[0543] 6. The server receives the feedback and purchase data and updates the machine learning model to improve the next list of suggestions.

[0544] This allows highly accurate proposals that meet the individual needs of the user to be provided, thereby improving user satisfaction.

[0545] The processing flow will be explained below.

[0546] Step 1:

[0547] A user registers or logs in to the system. The user enters their email address and password for authentication.

[0548] Step 2:

[0549] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0550] Step 3:

[0551] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[0552] Step 4:

[0553] The server stores the selected preference information in a database.

[0554] Step 5:

[0555] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0556] Step 6:

[0557] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[0558] Step 7:

[0559] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0560] Step 8:

[0561] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[0562] Step 9:

[0563] The server transmits the generated proposal list to the user's terminal.

[0564] Step 10:

[0565] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[0566] Step 11:

[0567] The user gives feedback on the suggested items, such as "good," "bad," or "favorite." Feedback is input from the device.

[0568] Step 12:

[0569] The device collects user feedback and sends it to the server, where it is stored in a database.

[0570] Step 13:

[0571] The server analyzes the received feedback and updates the machine learning model based on the feedback data.

[0572] Step 14:

[0573] The server uses the updated machine learning model to further improve the next list of suggestions.

[0574] Step 15:

[0575] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[0576] Example 1

[0577] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0578] A system that efficiently provides users with personalized fashion and cosmetic recommendations is required to accurately grasp user preferences and trends and quickly incorporate the latest trend data. However, conventional systems have been unable to provide recommendations that fully reflect user preferences, resulting in low user satisfaction. Furthermore, it has been difficult to effectively utilize feedback information and incorporate it into subsequent recommendations, which has led to delays in system improvements.

[0579] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0580] In this invention, the server includes an interface means for the user to input basic information and preferences, a means for saving the input basic information and preferences in a database, and a means for analyzing past purchase history based on the saved basic information and preferences, thereby enabling highly accurate suggestions that meet the individual needs of the user.

[0581] "Interface means" refers to a display device or input device that allows a user to input basic information and preferences.

[0582] "Database" refers to an information storage system for storing user basic information, preferences, purchase history, feedback information, trend data, and the like.

[0583] "Analysis means" refers to a processing device or software that uses stored data to analyze a user's purchase history, preferences, trend data, etc.

[0584] "External data source" refers to an information provider, such as an API or web service, that can be used to obtain the latest trend data from outside the system.

[0585] "Suggestion list" refers to a recommended list of fashion and cosmetic items that is generated based on the analysis results and provided to the user.

[0586] "Terminal" refers to a device, such as a smartphone or PC, on which a user receives and displays the suggestion list and enters feedback.

[0587] "Feedback" refers to information that a user inputs about a proposed item, such as their evaluation or opinion.

[0588] "Machine learning model" refers to an algorithm or numerical model that uses user data and feedback to improve the accuracy of suggestions across the system.

[0589] The present invention is a system for providing personalized fashion and cosmetic suggestions to users. Specific embodiments are described below.

[0590] User Data Collection

[0591] When a user registers or logs in to the system, they first enter their email address and password. They then enter basic information such as their height, weight, age, gender, and personal color. This is done using an input interface in a web browser or mobile app, and is developed based on the Django framework.

[0592] The entered information is collected by the server and stored in a PostgreSQL database. The user then enters their preferred colors, styles, items of interest, etc., and this information is also stored in the database.

[0593] Analyzing user data

[0594] The server retrieves the user's past purchase history from the database and processes the data using Python's Pandas library. The server then analyzes the user's past purchase history using machine learning algorithms, specifically clustering and collaborative filtering using the Scikit-Learn library.

[0595] Next, the server collects the latest trend data from external data sources. This is done using APIs from fashion and cosmetics websites, such as Style API and Fashion Cloud API. The collected trend data is then stored in a database.

[0596] Personalized suggestion generation

[0597] The server uses machine learning models to generate a personalized recommendation list based on the user's basic information, preferences, and past purchase history. This recommendation list includes fashion items and cosmetics that are best suited to the user. The generated recommendation list is sent to the user's device in JSON format via the HTTP protocol.

[0598] View suggestions and gather feedback

[0599] The user's device displays the submitted list of suggestions in an easy-to-read format. The front-end is developed using React and Vue.js. The user can then enter feedback on the suggested items, such as "good," "bad," or "favorite."

[0600] Feedback is collected on the device and sent to the server via XMLHttpRequest or the Fetch API. The server stores the received feedback in a database and retrains the machine learning model using Scikit-Learn or TensorFlow. This process improves the list of suggestions for the next iteration.

[0601] Specific examples

[0602] For User A

[0603] 1. User A logs in to the system and enters basic information such as height 160 cm, weight 50 kg, and personal color "spring."

[0604] 2. User A prefers casual style and selects that he likes blue and white.

[0605] 3. The server analyzes past purchase history (e.g., blue denim, white T-shirt) and collects "floral print shirt" and "light blue denim" as the latest trend data.

[0606] 4. The server combines these to generate a proposal list and sends it to User A's device.

[0607] 5. The device displays the suggestion list, and User A gives feedback that the floral print shirt is his favorite.

[0608] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[0609] Specific examples of prompts are as follows:

[0610] "I'm a 20-year-old woman, 160cm tall and weigh 50kg. I like casual style and I like blue and white. Please suggest some of the latest trendy items."

[0611] In this way, the system can provide highly accurate suggestions that meet the individual needs of the user, improving user satisfaction.

[0612] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0613] Step 1:

[0614] When a user registers or logs in to the system, they enter their email address and password. The entered email address and password are sent to the server through the input fields of the form. The server receives them and performs authentication processing. Input: Email address and password. Output: Authentication result (success or failure). If authentication is successful, the user will be taken to the next screen where they will be asked to enter basic information.

[0615] Step 2:

[0616] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and saves it in a database. Input: Basic user information. Output: Basic user information saved in the database. The data is processed using the Django framework and saved in a PostgreSQL database.

[0617] Step 3:

[0618] The user selects and inputs preferences such as favorite colors, styles, and items of interest. This data is sent to the server through the interface. Input: Favorite colors, styles, and items. Output: Sent preference information. The server receives this and stores it in a database.

[0619] Step 4:

[0620] The server retrieves past purchase history from the database. A user's purchase history includes details such as the category, color, and brand of the purchased items. Input: User ID. Output: Past purchase history data. The server retrieves the purchase history data and organizes it using Python's Pandas library.

[0621] Step 5:

[0622] The server uses a machine learning algorithm based on the Scikit-Learn library to analyze past purchase history. The analysis results are used to identify user preferences and trends. Input: Past purchase history data. Output: User preferences and trends. Analysis is performed using clustering and collaborative filtering techniques.

[0623] Step 6:

[0624] The server collects the latest trend data from external data sources. This uses a RESTful API to obtain the latest trend information on fashion and cosmetics. Input: API endpoint of external data source. Output: Latest trend data. For example, data can be collected using Style API or Fashion Cloud API and stored in a database.

[0625] Step 7:

[0626] The server generates an individualized recommendation list based on the user's basic information, preferences, and past purchase history. The recommendation list reflects the analysis results and the latest trend data. Input: User's basic information, preferences, past purchase history, trend data. Output: Suggestion list. A Scikit-Learn model is used to suggest the most suitable fashion items and cosmetics.

[0627] Step 8:

[0628] The server sends the generated proposal list to the user's device in JSON format. Input: Proposal list. Output: Sent proposal list. Data is sent securely using the HTTP / HTTPS protocol.

[0629] Step 9:

[0630] The device displays the suggestion list to the user in an easy-to-read format. The suggestion list is rendered using the React or Vue.js framework. Input: Suggestion list. Output: Displayed suggestion list. The user reviews the suggestion list and selects an item.

[0631] Step 10:

[0632] The user gives feedback on the suggested items, such as "good", "bad", or "favorite". Input: Feedback information. Output: Submitted feedback information. The user enters feedback using a form or buttons.

[0633] Step 11:

[0634] The device collects user feedback and sends it to the server via XMLHttpRequest or Fetch API. Input: Feedback information. Output: Feedback information sent to the server.

[0635] Step 12:

[0636] The server stores the received feedback information in a database and analyzes the data using Scikit-Learn and TensorFlow. Input: Feedback information. Output: Analysis results. The model is retrained and improved based on the feedback information.

[0637] Step 13:

[0638] The server uses the retrained machine learning model to improve the next list of suggestions. By periodically updating the model, the accuracy of suggestions to users increases. Input: Feedback data. Output: Improved list of suggestions. The update process is scheduled using Cron or Celery.

[0639] (Application example 1)

[0640] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0641] Today's consumers are increasingly seeking personalized fashion and cosmetic recommendations. However, conventional systems struggle to reflect user preferences and trends in real time, resulting in insufficient consumer satisfaction. Furthermore, there are few ways to visually confirm suggested items in real time, limiting the shopping experience. Therefore, it is necessary to improve the user experience by providing a personalized recommendation system that can overlay items onto the user's field of view.

[0642] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0643] In this invention, the server

[0644] a means for users to input basic information and preferences;

[0645] means for storing the entered basic information and preferences in a database;

[0646] means for analyzing past purchases based on stored basic information and preferences;

[0647] A means of collecting and storing up-to-date trend data from external data sources in a database;

[0648] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[0649] means for transmitting the generated proposal list to a user terminal;

[0650] means for collecting and analyzing user feedback on the proposed items;

[0651] means for updating a machine learning model to improve the next list of suggestions based on the feedback;

[0652] means for overlaying personalized suggestions onto the user's field of view;

[0653] a means for displaying recommended items in real time based on user preferences and trend data;

[0654] means for updating the recommended items based on user ratings;

[0655] Includes:

[0656] This allows for highly accurate personalized suggestions to be made based on user preferences and trends, and visual confirmation and feedback.

[0657] "User" refers to a consumer who accesses the system and enters basic information and preferences.

[0658] "Basic information" is data relating to personal attributes such as height, weight, age, sex, and personal color entered by the user.

[0659] "Preferences" refers to data on the user's tastes and preferences, such as colors and styles selected by the user, and items of interest.

[0660] A "database" is a collection of electronic data that stores basic user information, preferences, past purchase history, trend data, etc., and stores it in a format that can be used by the system.

[0661] "Past purchase history" refers to information such as category, color, brand, etc., relating to items previously purchased by the user.

[0662] "External data sources" refers to the source of the latest trend data that the system obtains from external fashion sites and APIs.

[0663] "Trend data" is information about current fashion and cosmetic trends.

[0664] The "suggestion list" is a list of recommended items for a user, generated by combining the user's basic information, past purchase history, and trend data.

[0665] "User device" refers to the user's electronic device (smartphone, tablet, PC, etc.) used to collect and send suggestion lists and feedback.

[0666] "Feedback" is data of evaluations and opinions given by users regarding proposed items.

[0667] "Machine Learning Model" means the algorithm and model used to analyze data and optimize personalized recommendations.

[0668] "Overlaying in the field of view" means overlaying suggested items directly in the user's field of view using smart glasses or the like.

[0669] "Displaying recommended items in real time" means instantly displaying recommended items that are appropriate for the moment when the user uses the system.

[0670] "Updating recommended items based on ratings" means adjusting and improving the algorithm for generating the next list of suggestions based on feedback from users.

[0671] The present invention provides a system for providing personalized fashion and cosmetic recommendations to users, specifically, a system for displaying recommended items in real time using smart glasses. Specific embodiments for implementing the present invention are described below.

[0672] System Program

[0673] The system consists of a program with the following main functions:

[0674] 1. The user enters basic information and preferences.

[0675] 2. Store your basic information and preferences in our database.

[0676] 3. Analyze past purchase history based on the stored information.

[0677] 4. Collect the latest trend data from external data sources and store it in the database.

[0678] 5. Generate a list of suggestions by combining basic user information, past purchase history, and trend data.

[0679] 6. The proposal list is sent to the user's device.

[0680] 7. Collect and analyze user feedback on the proposed items.

[0681] 8. Update the machine learning model to improve the next list of suggestions based on feedback.

[0682] 9. Overlay personalized suggestions into the user's field of view.

[0683] 10. Update recommended items in real time based on user ratings.

[0684] Processing Details

[0685] The server stores the user's basic information and preferences in a database, including height, weight, age, gender, personal color, favorite colors and styles, and favorite items. The server also collects the latest trend information from external data sources and stores it in the database. Using this data, a machine learning algorithm analyzes the user's past purchase history and generates a personalized recommendation list based on the user's preferences and the latest trends.

[0686] The user's device, such as smart glasses, receives this list of suggestions and displays it as an overlay in the user's field of view. The user's ratings and feedback on the suggested items are sent to the server via the device, and the server uses this feedback to update the machine learning model and make the next suggestions more accurate.

[0687] The hardware used includes smart glasses (e.g., Google Glass, Apple Glass). These devices are used to overlay suggested items onto the user's field of view. The server and device programs are implemented using Python, machine learning algorithms, and RESTful APIs.

[0688] Examples and prompts

[0689] As an example, consider how a 20-year-old female user A uses the system.

[0690] 1. User A logs in to the system and enters his height of 160 cm, weight of 50 kg, and personal color of "spring."

[0691] 2. You choose to have a casual style and prefer blue and white.

[0692] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt) and collects the latest spring trend data (e.g., floral print shirt, light blue denim).

[0693] 4. The server combines these to generate a proposal list and sends it to the smart glasses.

[0694] 5. The smart glasses overlay the suggestion list onto User A's field of view, and User A gives feedback that the floral print shirt is a "favorite."

[0695] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[0696] An example of a prompt is:

[0697] User ID: user_12345

[0698] Basic information: Height 160cm, weight 50kg, personal color "Spring"

[0699] Purchase history: Blue jeans, white T-shirt

[0700] Preferences: Blue and white, casual style

[0701] Trend data: Spring trends include floral print shirts and light blue denim

[0702] Feedback: Floral print shirt is my favorite

[0703] As described above, the present invention provides a system that can make personalized fashion and cosmetic suggestions to users in real time.

[0704] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0705] Step 1:

[0706] The user enters basic information and preferences. After logging in, the user enters their height, weight, age, gender, personal color, favorite colors and styles, and items of interest through the smart glasses. The entered information is sent to the server.

[0707] input:

[0708] Height, weight, age, gender, personal color

[0709] Favorite colors, styles, and items

[0710] output:

[0711] The input data is sent to the server and stored in a database.

[0712] Step 2:

[0713] The server stores the received user's basic information and preferences in a database.

[0714] input:

[0715] Basic information and preferences submitted by you

[0716] output:

[0717] User information stored in a database

[0718] Step 3:

[0719] The server analyzes past purchase history based on the stored information. The server retrieves the user's past purchase history stored in the database and analyzes it using a machine learning algorithm.

[0720] input:

[0721] User's past purchase history retrieved from the database

[0722] output:

[0723] Analysis results showing user preferences and trends

[0724] Step 4:

[0725] Collect the latest trend data from external data sources and store it in the database. The server uses an external API to get the latest trend information and store it in the database.

[0726] input:

[0727] Trend data obtained from external APIs

[0728] output:

[0729] Trend data stored in a database

[0730] Step 5:

[0731] The server generates a list of recommendations by combining basic user information, past purchase history, and trend data. The server then uses a machine learning algorithm to generate the optimal list of recommendations based on the acquired data.

[0732] input:

[0733] User Basic Information

[0734] Past purchase history

[0735] Trend Data

[0736] output:

[0737] Suggestion List

[0738] Step 6:

[0739] Sending the proposal list to the user's terminal: The server sends the generated proposal list to the user's terminal, such as smart glasses.

[0740] input:

[0741] Suggestion List

[0742] output:

[0743] The proposal list sent to the user's device

[0744] Step 7:

[0745] The server collects and analyzes user feedback on the proposed items. Users input their ratings and opinions on the proposed items through the smart glasses. The server collects this feedback and stores it in a database.

[0746] input:

[0747] User Feedback

[0748] output:

[0749] Feedback stored in the database

[0750] Step 8:

[0751] Update the machine learning model to improve the next list of suggestions based on the feedback. The server analyzes the collected feedback and uses it to improve the machine learning model.

[0752] input:

[0753] Feedback stored in the database

[0754] output:

[0755] Improved machine learning models

[0756] Step 9:

[0757] Overlaying personalized suggestions onto the user's field of view: The smart glasses overlay items from the suggestion list onto the user's field of view.

[0758] input:

[0759] Suggestion List

[0760] output:

[0761] Overlaid suggested items

[0762] Step 10:

[0763] Update recommended items in real time based on user ratings: The smart glasses instantly adjust and update suggested items based on user feedback.

[0764] input:

[0765] User Feedback

[0766] output:

[0767] Updated Suggested Items

[0768] This allows users to receive personalized fashion and cosmetic suggestions in real time.

[0769] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0770] The present invention relates to a system that proposes personalized fashion and cosmetic products to a user, and further includes an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[0771] User Data Collection and Storage

[0772] 1. When a user registers or logs in to the system, they first enter their email address and password for authentication.

[0773] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0774] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[0775] 4. The server stores these preferences in a database.

[0776] Analyzing user data

[0777] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0778] 6. The server uses machine learning algorithms to analyze past purchase history and analyze user preferences and trends, and stores the results of this analysis in a database.

[0779] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0780] Personalized suggestion generation

[0781] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history. The generated list is stored in a database.

[0782] 9. The server sends the generated proposal list to the user's device.

[0783] Displaying suggestions, collecting feedback, and emotion recognition

[0784] 10. The device displays the sent proposal list to the user. The displayed proposal list is presented in a format that is easy for the user to view.

[0785] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[0786] 12. The device collects the user's feedback and emotion data and sends it to the server, where it is stored in a database.

[0787] 13. The server analyzes the received feedback and sentiment data. It updates the machine learning model based on the feedback data.

[0788] 14. The server uses the emotional data as information to further tailor the next suggestion list to the user's preferences.

[0789] Specific examples

[0790] Example 1: 20-year-old female user A

[0791] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[0792] 2. User A prefers a casual style and selects that he likes blue and white.

[0793] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[0794] 4. The server combines these to generate a proposal list and sends it to User A's device.

[0795] 5. The device displays the list of suggestions, and User A provides feedback on the floral print shirt as a "favorite," and the emotion engine also collects User A's facial expression data.

[0796] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[0797] Example 2: For 25-year-old male user B

[0798] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[0799] 2. User B selects that he prefers a formal style and prefers black and gray.

[0800] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[0801] 4. The server combines these to generate a proposal list and sends it to User B's device.

[0802] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it. The emotion engine also simultaneously collects User B's emotion data.

[0803] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[0804] This allows the system to provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. In addition, by utilizing emotion data, more detailed responses are possible, further improving the accuracy of suggestions made by the system as a whole.

[0805] The processing flow will be explained below.

[0806] Step 1:

[0807] A user registers or logs in to the system. The user enters their email address and password for authentication.

[0808] Step 2:

[0809] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0810] Step 3:

[0811] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[0812] Step 4:

[0813] The server stores the selected preference information in a database.

[0814] Step 5:

[0815] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0816] Step 6:

[0817] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[0818] Step 7:

[0819] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0820] Step 8:

[0821] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[0822] Step 9:

[0823] The server transmits the generated proposal list to the user's terminal.

[0824] Step 10:

[0825] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[0826] Step 11:

[0827] Users provide feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[0828] Step 12:

[0829] The terminal collects the user's feedback and emotion data and sends it to the server, which stores the feedback and emotion data in a database.

[0830] Step 13:

[0831] The server analyzes the received feedback and sentiment data and updates the machine learning model based on the feedback data.

[0832] Step 14:

[0833] The server uses the emotional data as information to further match the next suggestion list to the user's preferences.

[0834] Step 15:

[0835] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[0836] Example 2

[0837] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0838] Conventional online shopping systems have a problem in that recommendations to users are not personalized, making it difficult to provide items that match the individual preferences of each user. In addition, feedback data is limited to simple evaluations such as "good" or "bad," making it difficult to improve the accuracy of recommendations that reflect the user's true feelings and preferences.

[0839] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting and analyzing user feedback on proposed items; means for acquiring feedback and emotion data on the proposed items; and means for updating a machine learning model to improve the next proposal list based on the feedback and emotion data. This makes it possible to make personalized proposals based on the user's basic information, preferences, past purchase history, and latest trend data, and to provide highly accurate proposals that reflect the user's true emotions and preferences.

[0840] 1. "User" refers to an individual who uses the System and enters basic information and preferences.

[0841] 2. "Basic information" refers to basic data about the user, such as height, weight, age, gender, and personal color.

[0842] 3. "Preferences" refers to information such as the user's preferred colors, styles, and items of interest.

[0843] 4. "Database" refers to data storage within the system for safely and efficiently storing users' basic information, preferences, past purchase history, trend data, feedback, and sentiment data.

[0844] 5. "Purchase history" refers to detailed information such as category, color, and brand of products purchased by a user in the past.

[0845] 6. "External data source" refers to a source of information for obtaining data from outside the system, such as online fashion sites or trend information services.

[0846] 7. "Latest Trend Data" refers to data showing the latest fashions and trends in fashion and cosmetics.

[0847] 8. "Suggestion List" refers to a personalized list of items generated by combining a user's basic information, preferences, past purchase history, and trend data.

[0848] 9. "Terminal" refers to the electronic device, such as a computer, smartphone, or tablet, that a User uses to access the System and view the Proposal List.

[0849] 10. "Feedback" refers to the evaluations and opinions of users regarding proposed items, such as "good," "bad," or "favorite."

[0850] 11. "Emotional Data" means data that indicates a user's emotional state, collected based on the user's facial expressions and behavior.

[0851] 12. “Machine Learning Model” means an algorithmic model used to optimize recommendations based on user preferences, feedback, and sentiment data.

[0852] 13. "System" refers to a collection of computer programs and hardware that includes a set of processes for collecting and analyzing user data, generating a list of suggestions, and collecting and analyzing feedback.

[0853] This invention is a system that provides personalized fashion and cosmetic recommendations to users, and combines it with an emotion engine that recognizes the user's emotions. The system analyzes the user's input information and generates optimal recommendations.

[0854] System configuration

[0855] The system consists of the following main components:

[0856] 1. User terminal: refers to the device (e.g., computer, smartphone, tablet) through which a user enters information and receives a list of suggestions.

[0857] 2. Server: The central system that performs the main processing such as data collection, analysis, storage, and generating suggestion lists.

[0858] 3. Database: Storage within the system that stores users' basic information, preferences, past purchase history, trend data, feedback and sentiment data.

[0859] 4. Emotion engine: Software for collecting and analyzing emotional data from the user's facial expressions and voice (e.g., OpenCV, Emotion API).

[0860] Main software and hardware used

[0861] Machine learning algorithms: Machine learning libraries such as Scikit-learn and TensorFlow are used to analyze user preferences and purchase history.

[0862] External interface: Uses the API of fashion sites to collect the latest trend data.

[0863] Database Management System: Uses a relational database such as MySQL or PostgreSQL.

[0864] Sentiment analysis tools: OpenCV, Emotion API

[0865] Detailed System Operation

[0866] 1. User Registration and Authentication

[0867] When a user registers or logs in to the system, they enter their email address and password. The server authenticates this and, if successful, issues a token and returns it to the user.

[0868] 2. Enter your basic information and preferences

[0869] Users input basic information such as height, weight, age, gender, and personal color. They also select their preferred colors, styles, and items of interest. The server acquires this information and stores it in a database.

[0870] 3. User Data Analysis

[0871] The server retrieves the user's past purchase history from the database, analyzes it using Scikit-learn and TensorFlow, and analyzes the user's preferences and trends. It also collects the latest trend data through an external interface and stores it in the database.

[0872] 4. Generate and send a proposal list

[0873] The server combines the user's basic information, preferences, past purchase history, and trend data to generate the optimal recommendation list, which is then stored in a database in JSON format and sent to the user's device.

[0874] 5. View the list of suggestions and gather feedback

[0875] The user terminal displays the list of suggestions, and the user gives feedback such as "good," "bad," or "favorite." In addition, an emotion engine is used to collect emotional data from the user's facial expressions and voice.

[0876] 6. Analysis of Feedback and Emotion Data

[0877] The server collects and analyzes user feedback and sentiment data to update the machine learning model to improve the next list of suggestions.

[0878] Specific examples

[0879] Example 1: 20-year-old female user A

[0880] User A logs into the system and enters basic information (e.g., height 160 cm, weight 50 kg, personal color "spring"). He selects his preferred style (e.g., casual, blue and white colors). The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt), collects the latest trend data (e.g., "floral print shirt" and "light blue denim"), and generates a suggestion list. This suggestion list is sent to User A's device. User A provides feedback on the suggested items, saying "favorite," and the emotion engine collects facial expression data. The server analyzes this and improves the next suggestion list.

[0881] Prompt Sentence Examples

[0882] "What latest fashion items would you suggest to a 20-year-old woman who likes blue and white for her spring casual style?"

[0883] In this way, this system can provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. Furthermore, by utilizing emotion data, even more detailed responses are possible, further improving the accuracy of suggestions.

[0884] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0885] System program processing flow

[0886] Step 1:

[0887] A user registers or logs in to the system. Specifically, the user enters their email address and password, and this data is sent to the server. The server receives this and performs authentication. If authentication is successful, the server generates an authentication token and returns it to the user. The input is an email address and password, and the output is an authentication token.

[0888] Step 2:

[0889] The user enters basic information (height, weight, age, gender, personal color, etc.) and preferences (color, style, items of interest, etc.). The entered data is sent to the server. The server receives this data and stores it in a database. The input is the user's basic information and preferences, and the output is the results stored in the database.

[0890] Step 3:

[0891] The server retrieves the user's past purchase history from the database. Specifically, it uses an SQL query to extract the user's purchase history data. This purchase history data is used for data analysis. The input is the purchase history retrieved from the database, and the output is the past purchase history data used for analysis.

[0892] Step 4:

[0893] The server uses a machine learning algorithm (e.g., Scikit-learn) to analyze the user's past purchase history and identify trends and preferences. The input is past purchase history data, and the output is the analysis results of the user's preferences. Specifically, the server performs a series of analytical processes, including feature extraction, data preprocessing, and model training.

[0894] Step 5:

[0895] The server collects the latest trend data from an external data source (e.g., a fashion site's API). It requests the trend data through the API and stores the acquired data in a database. The input is the latest trend data acquired from outside, and the output is the trend data stored in the database.

[0896] Step 6:

[0897] The server generates a list of suggestions by combining the user's basic information, preferences, past purchase history, and the latest trend data. Specifically, it uses an algorithm to integrate information from each data source and select the most suitable items. The input is the user's basic information, preferences, purchase history, and trend data, and the output is the generated list of suggestions (e.g., in JSON format).

[0898] Step 7:

[0899] The server sends the generated proposal list to the user's device. Specifically, it uses a REST API to send the proposal list to the user's device. The input is the generated proposal list, and the output is the receipt of the proposal list on the user's device.

[0900] Step 8:

[0901] The terminal displays the suggestion list to the user in an easy-to-view format, including item images, descriptions, prices, etc. The input is the received suggestion list, and the output is the suggestions displayed on the user terminal.

[0902] Step 9:

[0903] The user inputs feedback on the proposed item. Specifically, the user rates the item as "good," "bad," or "favorite," and inputs the feedback data. The input is the user's feedback information, and the output is sending the feedback data to the server.

[0904] Step 10:

[0905] The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. The input is the user's facial expressions and voice data, and the output is the collected emotional data. Specific operations involve the use of image and voice analysis algorithms.

[0906] Step 11:

[0907] The terminal transmits the user's feedback and emotion data to the server. Specifically, the data is converted into an appropriate format and sent to the server. The input is the feedback and emotion data, and the output is data transmission to the server.

[0908] Step 12:

[0909] The server analyzes the received feedback and emotion data. The input is the sent feedback and emotion data, and the output is the analysis results. Specifically, it performs data analysis based on the feedback and emotion data and updates the machine learning model.

[0910] Step 13:

[0911] The server generates information based on the analysis results to improve the next suggestion list. The input is the analysis results, and the output is an improved suggestion list. Specifically, the server applies the retrained machine learning model to make suggestions that better match the user's preferences.

[0912] The above is the flow of processing in the system program and the specific operations of each step.

[0913] (Application example 2)

[0914] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0915] Modern consumers demand personalized product recommendations based on their preferences and trends, but existing systems do not adequately meet these demands. Furthermore, existing systems are unable to accurately capture users' emotions, resulting in inaccurate recommendations. Therefore, there is a need for a system that can collect users' individual emotions and feedback in real time and provide more accurate personalized recommendations.

[0916] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting the latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting feedback and emotion data from the user about the proposed items; means for analyzing the collected feedback and emotion data and updating a machine learning model to improve the next proposal list; and means including an emotion recognition engine for visually displaying the proposal list and collecting emotion data from the user in real time. This enables highly accurate proposals that meet the individual needs of the user and improves user satisfaction.

[0917] "Means for users to input basic information and preferences" refers to an interface that allows users to input information such as height, weight, age, gender, personal color, and preferred styles and colors.

[0918] "Means for storing in a database" refers to software and hardware for securely storing the entered basic information and preferences in a database.

[0919] "Means for analyzing past purchase history" refers to algorithms and software used to analyze the categories, colors, brands, etc. of items a user has previously purchased to identify the user's preferences and tendencies.

[0920] "Means for collecting the latest trend data from external data sources and storing it in a database" refers to software and hardware for collecting the latest trend information from external fashion sites and APIs and storing it in a database.

[0921] "Means for generating a suggestion list" refers to algorithms and software for generating a list that suggests suitable fashion items and cosmetics to a user based on the user's basic information, past purchase history, and the latest trend data.

[0922] "Means for transmitting the generated proposal list to the user's terminal" refers to software and communication means for transmitting the generated proposal list to the user's smartphone, smart glasses, head-mounted display, etc.

[0923] "Means for collecting feedback and emotional data" refers to the interface and software for capturing user feedback on the proposed item and emotional data collected using the emotion recognition engine.

[0924] "Means for analyzing collected feedback and sentiment data" refers to algorithms and software for analyzing collected feedback and sentiment data to improve the accuracy of the next list of suggestions.

[0925] "Means for updating machine learning models" refers to machine learning algorithms and software for continuously improving the algorithms for generating the recommendation list based on feedback and sentiment data.

[0926] An "emotion recognition engine" refers to software and hardware for collecting and analyzing emotional data from a user's facial expressions and voice in real time.

[0927] The present invention is a system that provides personalized fashion and cosmetic recommendations to users, and improves the accuracy of recommendations based on the user's emotional data by incorporating an emotion recognition engine. Specific embodiments of the present invention are described in detail below.

[0928] User Data Collection and Storage

[0929] This system provides an interface for users to input their basic information and preferences on devices such as smartphones, smart glasses, and head-mounted displays. Users enter information such as height, weight, age, gender, personal color, and preferred styles and colors, and this information is stored in a database. Database management uses common database solutions (e.g., MySQL, PostgreSQL).

[0930] Data analysis

[0931] The server analyzes past purchase history based on the stored user basic information and preference data. It uses machine learning algorithms (e.g., Logistic Regression, Random Forest) to retrieve past purchase data from the database and analyze the user's preferences and purchasing trends. It also collects the latest fashion trend information from external data sources via API and stores this information in the database.

[0932] Personalized suggestion generation

[0933] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. This recommendation list uses an algorithm to select the most suitable items and list them in an order that suits the user. The generated recommendation list is then saved back in the database. The recommendation list is then sent to the user's device and displayed visually.

[0934] Displaying suggestions, collecting feedback, and emotion recognition

[0935] The device displays the suggested items to the user, who then inputs feedback such as "good," "bad," or "favorite." At the same time, an emotion recognition engine (e.g., EmotionRecognitionEngine) is used to collect real-time emotional data from the user's facial expressions and voice. This feedback and emotional data is sent from the device to a server and stored in a database.

[0936] Analyzing Data and Updating Models

[0937] The server analyzes the collected feedback and sentiment data and updates the machine learning model for generating the next recommendation list. The collected data is an important factor in improving the accuracy of the recommendation list generation algorithm.

[0938] Specific examples

[0939] For example, a 30-year-old female user logs in and registers data such as her height of 165 cm, weight of 55 kg, personal color of "winter," and preferred style of "elegant." The server will suggest a "black slim-fit dress" and a "silver necklace" based on her past purchase history and the latest trends. The user will then provide feedback that they are "favorites," and the emotion engine will recognize their facial expression of satisfaction.

[0940] Prompt Sentence Examples

[0941] text

[0942] User data: Height 165cm, Weight 55kg, Personal color "Winter", Favorite style "Elegant"

[0943] Previous purchase history: Black slim-fit dress, silver necklace

[0944] The latest trend: elegant pieces in black and silver

[0945] Feedback: Favorite

[0946] Emotion data: Satisfied facial expression

[0947] This allows for highly accurate proposals that meet the individual needs of users, thereby improving user satisfaction.

[0948] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0949] Step 1:

[0950] The server provides an interface for users to input their basic information and preferences on their devices. The information entered by users, such as height, weight, age, gender, personal color, and preferred style and color, is stored in a database via the device. The input data is encrypted to ensure security.

[0951] Step 2:

[0952] The server retrieves the basic information and preference data stored in the database, pulls the user's past purchase history from the database, and performs an analysis. Machine learning algorithms (e.g., Logistic Regression, Random Forest) are used to identify the user's preferences and purchasing trends. The results of this analysis are stored in the database as new data points and are later used to generate recommendations.

[0953] Step 3:

[0954] The server collects the latest fashion trend information through APIs of external data sources. The collected information is stored in a database and pre-processed to ensure accuracy and consistency, including filtering unnecessary data and normalizing the data.

[0955] Step 4:

[0956] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. It uses machine learning algorithms to analyze and select the items that best suit the user. This recommendation list is stored in a database and later sent to the device.

[0957] Step 5:

[0958] The generated suggestion list is sent to the user's device, which then displays the suggested items to the user in a visually appealing and easily understandable format, with optimized UI / UX design.

[0959] Step 6:

[0960] The user provides feedback on the suggested items, such as "good," "bad," or "favorite." The device analyzes the user's facial expressions and voice in real time using an emotion recognition engine (e.g., EmotionRecognitionEngine) to collect emotional data. The collected feedback and emotional data are sent from the device to a server and stored in a database.

[0961] Step 7:

[0962] The server analyzes the collected feedback and sentiment data and updates the machine learning model with new learning data to improve the accuracy of the next recommendation list. Model updates include retraining and tuning hyperparameters.

[0963] Step 8:

[0964] The server uses the updated machine learning model to generate the next list of suggestions, which can be more tailored to the user's individual needs.

[0965] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0966] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0967] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0968] [Third embodiment]

[0969] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0970] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0971] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0972] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0973] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0974] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0975] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0976] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0977] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0978] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0979] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0980] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0981] The present invention relates to a system that makes personalized fashion and cosmetic suggestions to users, and specific embodiments thereof will be described below.

[0982] User Data Collection and Storage

[0983] 1. When a user registers or logs in to the system, they first enter their email address and password.

[0984] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[0985] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[0986] 4. The server stores these preferences in a database.

[0987] Analyzing user data

[0988] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[0989] 6. The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends.

[0990] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[0991] Personalized suggestion generation

[0992] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history.

[0993] 9. The server sends the proposal list to the user's device.

[0994] View suggestions and gather feedback

[0995] 10. The device displays the sent proposal list to the user. The proposal list is appropriately designed so that it is displayed in a format that is easy for the user to view.

[0996] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite."

[0997] 12. The device collects user feedback and sends it to the server.

[0998] 13. The server stores the received feedback in a database and analyzes it.

[0999] 14. The server updates the machine learning model based on the feedback to improve the next list of suggestions.

[1000] Specific examples

[1001] Example 1: 20-year-old female user A

[1002] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[1003] 2. User A prefers a casual style and selects that he likes blue and white.

[1004] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[1005] 4. The server combines these to generate a proposal list and sends it to User A's device.

[1006] 5. The device displays the suggestion list, and User A gives feedback on the floral print shirt as a "favorite."

[1007] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[1008] Example 2: For 25-year-old male user B

[1009] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[1010] 2. User B selects that he prefers a formal style and prefers black and gray.

[1011] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[1012] 4. The server combines these to generate a proposal list and sends it to User B's device.

[1013] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it.

[1014] 6. The server receives the feedback and purchase data and updates the machine learning model to improve the next list of suggestions.

[1015] This allows highly accurate proposals that meet the individual needs of the user to be provided, thereby improving user satisfaction.

[1016] The processing flow will be explained below.

[1017] Step 1:

[1018] A user registers or logs in to the system. The user enters their email address and password for authentication.

[1019] Step 2:

[1020] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[1021] Step 3:

[1022] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[1023] Step 4:

[1024] The server stores the selected preference information in a database.

[1025] Step 5:

[1026] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[1027] Step 6:

[1028] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[1029] Step 7:

[1030] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[1031] Step 8:

[1032] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[1033] Step 9:

[1034] The server transmits the generated proposal list to the user's terminal.

[1035] Step 10:

[1036] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[1037] Step 11:

[1038] The user gives feedback on the suggested items, such as "good," "bad," or "favorite." Feedback is input from the device.

[1039] Step 12:

[1040] The device collects user feedback and sends it to the server, where it is stored in a database.

[1041] Step 13:

[1042] The server analyzes the received feedback and updates the machine learning model based on the feedback data.

[1043] Step 14:

[1044] The server uses the updated machine learning model to further improve the next list of suggestions.

[1045] Step 15:

[1046] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[1047] Example 1

[1048] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1049] A system that efficiently provides users with personalized fashion and cosmetic recommendations is required to accurately grasp user preferences and trends and quickly incorporate the latest trend data. However, conventional systems have been unable to provide recommendations that fully reflect user preferences, resulting in low user satisfaction. Furthermore, it has been difficult to effectively utilize feedback information and incorporate it into subsequent recommendations, which has led to delays in system improvements.

[1050] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1051] In this invention, the server includes an interface means for the user to input basic information and preferences, a means for saving the input basic information and preferences in a database, and a means for analyzing past purchase history based on the saved basic information and preferences, thereby enabling highly accurate suggestions that meet the individual needs of the user.

[1052] "Interface means" refers to a display device or input device that allows a user to input basic information and preferences.

[1053] "Database" refers to an information storage system for storing user basic information, preferences, purchase history, feedback information, trend data, and the like.

[1054] "Analysis means" refers to a processing device or software that uses stored data to analyze a user's purchase history, preferences, trend data, etc.

[1055] "External data source" refers to an information provider, such as an API or web service, that can be used to obtain the latest trend data from outside the system.

[1056] "Suggestion list" refers to a recommended list of fashion and cosmetic items that is generated based on the analysis results and provided to the user.

[1057] "Terminal" refers to a device, such as a smartphone or PC, on which a user receives and displays the suggestion list and enters feedback.

[1058] "Feedback" refers to information that a user inputs about a proposed item, such as their evaluation or opinion.

[1059] "Machine learning model" refers to an algorithm or numerical model that uses user data and feedback to improve the accuracy of suggestions across the system.

[1060] The present invention is a system for providing personalized fashion and cosmetic suggestions to users. Specific embodiments are described below.

[1061] User Data Collection

[1062] When a user registers or logs in to the system, they first enter their email address and password. They then enter basic information such as their height, weight, age, gender, and personal color. This is done using an input interface in a web browser or mobile app, and is developed based on the Django framework.

[1063] The entered information is collected by the server and stored in a PostgreSQL database. The user then enters their preferred colors, styles, items of interest, etc., and this information is also stored in the database.

[1064] Analyzing user data

[1065] The server retrieves the user's past purchase history from the database and processes the data using Python's Pandas library. The server then analyzes the user's past purchase history using machine learning algorithms, specifically clustering and collaborative filtering using the Scikit-Learn library.

[1066] Next, the server collects the latest trend data from external data sources. This is done using APIs from fashion and cosmetics websites, such as Style API and Fashion Cloud API. The collected trend data is then stored in a database.

[1067] Personalized suggestion generation

[1068] The server uses machine learning models to generate a personalized recommendation list based on the user's basic information, preferences, and past purchase history. This recommendation list includes fashion items and cosmetics that are best suited to the user. The generated recommendation list is sent to the user's device in JSON format via the HTTP protocol.

[1069] View suggestions and gather feedback

[1070] The user's device displays the submitted list of suggestions in an easy-to-read format. The front-end is developed using React and Vue.js. The user can then enter feedback on the suggested items, such as "good," "bad," or "favorite."

[1071] Feedback is collected on the device and sent to the server via XMLHttpRequest or the Fetch API. The server stores the received feedback in a database and retrains the machine learning model using Scikit-Learn or TensorFlow. This process improves the list of suggestions for the next iteration.

[1072] Specific examples

[1073] For User A

[1074] 1. User A logs in to the system and enters basic information such as height 160 cm, weight 50 kg, and personal color "spring."

[1075] 2. User A prefers casual style and selects that he likes blue and white.

[1076] 3. The server analyzes past purchase history (e.g., blue denim, white T-shirt) and collects "floral print shirt" and "light blue denim" as the latest trend data.

[1077] 4. The server combines these to generate a proposal list and sends it to User A's device.

[1078] 5. The device displays the suggestion list, and User A gives feedback that the floral print shirt is his favorite.

[1079] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[1080] Specific examples of prompts are as follows:

[1081] "I'm a 20-year-old woman, 160cm tall and weigh 50kg. I like casual style and I like blue and white. Please suggest some of the latest trendy items."

[1082] In this way, the system can provide highly accurate suggestions that meet the individual needs of the user, improving user satisfaction.

[1083] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1084] Step 1:

[1085] When a user registers or logs in to the system, they enter their email address and password. The entered email address and password are sent to the server through the input fields of the form. The server receives them and performs authentication processing. Input: Email address and password. Output: Authentication result (success or failure). If authentication is successful, the user will be taken to the next screen where they will be asked to enter basic information.

[1086] Step 2:

[1087] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and saves it in a database. Input: Basic user information. Output: Basic user information saved in the database. The data is processed using the Django framework and saved in a PostgreSQL database.

[1088] Step 3:

[1089] The user selects and inputs preferences such as favorite colors, styles, and items of interest. This data is sent to the server through the interface. Input: Favorite colors, styles, and items. Output: Sent preference information. The server receives this and stores it in a database.

[1090] Step 4:

[1091] The server retrieves past purchase history from the database. A user's purchase history includes details such as the category, color, and brand of the purchased items. Input: User ID. Output: Past purchase history data. The server retrieves the purchase history data and organizes it using Python's Pandas library.

[1092] Step 5:

[1093] The server uses a machine learning algorithm based on the Scikit-Learn library to analyze past purchase history. The analysis results are used to identify user preferences and trends. Input: Past purchase history data. Output: User preferences and trends. Analysis is performed using clustering and collaborative filtering techniques.

[1094] Step 6:

[1095] The server collects the latest trend data from external data sources. This uses a RESTful API to obtain the latest trend information on fashion and cosmetics. Input: API endpoint of external data source. Output: Latest trend data. For example, data can be collected using Style API or Fashion Cloud API and stored in a database.

[1096] Step 7:

[1097] The server generates an individualized recommendation list based on the user's basic information, preferences, and past purchase history. The recommendation list reflects the analysis results and the latest trend data. Input: User's basic information, preferences, past purchase history, trend data. Output: Suggestion list. A Scikit-Learn model is used to suggest the most suitable fashion items and cosmetics.

[1098] Step 8:

[1099] The server sends the generated proposal list to the user's device in JSON format. Input: Proposal list. Output: Sent proposal list. Data is sent securely using the HTTP / HTTPS protocol.

[1100] Step 9:

[1101] The device displays the suggestion list to the user in an easy-to-read format. The suggestion list is rendered using the React or Vue.js framework. Input: Suggestion list. Output: Displayed suggestion list. The user reviews the suggestion list and selects an item.

[1102] Step 10:

[1103] The user gives feedback on the suggested items, such as "good", "bad", or "favorite". Input: Feedback information. Output: Submitted feedback information. The user enters feedback using a form or buttons.

[1104] Step 11:

[1105] The device collects user feedback and sends it to the server via XMLHttpRequest or Fetch API. Input: Feedback information. Output: Feedback information sent to the server.

[1106] Step 12:

[1107] The server stores the received feedback information in a database and analyzes the data using Scikit-Learn and TensorFlow. Input: Feedback information. Output: Analysis results. The model is retrained and improved based on the feedback information.

[1108] Step 13:

[1109] The server uses the retrained machine learning model to improve the next list of suggestions. By periodically updating the model, the accuracy of suggestions to users increases. Input: Feedback data. Output: Improved list of suggestions. The update process is scheduled using Cron or Celery.

[1110] (Application example 1)

[1111] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1112] Today's consumers are increasingly seeking personalized fashion and cosmetic recommendations. However, conventional systems struggle to reflect user preferences and trends in real time, resulting in insufficient consumer satisfaction. Furthermore, there are few ways to visually confirm suggested items in real time, limiting the shopping experience. Therefore, it is necessary to improve the user experience by providing a personalized recommendation system that can overlay items onto the user's field of view.

[1113] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1114] In this invention, the server

[1115] a means for users to input basic information and preferences;

[1116] means for storing the entered basic information and preferences in a database;

[1117] means for analyzing past purchases based on stored basic information and preferences;

[1118] A means of collecting and storing up-to-date trend data from external data sources in a database;

[1119] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[1120] means for transmitting the generated proposal list to a user terminal;

[1121] means for collecting and analyzing user feedback on the proposed items;

[1122] means for updating a machine learning model to improve the next list of suggestions based on the feedback;

[1123] means for overlaying personalized suggestions onto the user's field of view;

[1124] a means for displaying recommended items in real time based on user preferences and trend data;

[1125] means for updating the recommended items based on user ratings;

[1126] Includes:

[1127] This allows for highly accurate personalized suggestions to be made based on user preferences and trends, and visual confirmation and feedback.

[1128] "User" refers to a consumer who accesses the system and enters basic information and preferences.

[1129] "Basic information" is data relating to personal attributes such as height, weight, age, sex, and personal color entered by the user.

[1130] "Preferences" refers to data on the user's tastes and preferences, such as colors and styles selected by the user, and items of interest.

[1131] A "database" is a collection of electronic data that stores basic user information, preferences, past purchase history, trend data, etc., and stores it in a format that can be used by the system.

[1132] "Past purchase history" refers to information such as category, color, brand, etc., relating to items previously purchased by the user.

[1133] "External data sources" refers to the source of the latest trend data that the system obtains from external fashion sites and APIs.

[1134] "Trend data" is information about current fashion and cosmetic trends.

[1135] The "suggestion list" is a list of recommended items for a user, generated by combining the user's basic information, past purchase history, and trend data.

[1136] "User device" refers to the user's electronic device (smartphone, tablet, PC, etc.) used to collect and send suggestion lists and feedback.

[1137] "Feedback" is data of evaluations and opinions given by users regarding proposed items.

[1138] "Machine Learning Model" means the algorithm and model used to analyze data and optimize personalized recommendations.

[1139] "Overlaying in the field of view" means overlaying suggested items directly in the user's field of view using smart glasses or the like.

[1140] "Displaying recommended items in real time" means instantly displaying recommended items that are appropriate for the moment when the user uses the system.

[1141] "Updating recommended items based on ratings" means adjusting and improving the algorithm for generating the next list of suggestions based on feedback from users.

[1142] The present invention provides a system for providing personalized fashion and cosmetic recommendations to users, specifically, a system for displaying recommended items in real time using smart glasses. Specific embodiments for implementing the present invention are described below.

[1143] System Program

[1144] The system consists of a program with the following main functions:

[1145] 1. The user enters basic information and preferences.

[1146] 2. Store your basic information and preferences in our database.

[1147] 3. Analyze past purchase history based on the stored information.

[1148] 4. Collect the latest trend data from external data sources and store it in the database.

[1149] 5. Generate a list of suggestions by combining basic user information, past purchase history, and trend data.

[1150] 6. The proposal list is sent to the user's device.

[1151] 7. Collect and analyze user feedback on the proposed items.

[1152] 8. Update the machine learning model to improve the next list of suggestions based on feedback.

[1153] 9. Overlay personalized suggestions into the user's field of view.

[1154] 10. Update recommended items in real time based on user ratings.

[1155] Processing Details

[1156] The server stores the user's basic information and preferences in a database, including height, weight, age, gender, personal color, favorite colors and styles, and favorite items. The server also collects the latest trend information from external data sources and stores it in the database. Using this data, a machine learning algorithm analyzes the user's past purchase history and generates a personalized recommendation list based on the user's preferences and the latest trends.

[1157] The user's device, such as smart glasses, receives this list of suggestions and displays it as an overlay in the user's field of view. The user's ratings and feedback on the suggested items are sent to the server via the device, and the server uses this feedback to update the machine learning model and make the next suggestions more accurate.

[1158] The hardware used includes smart glasses (e.g., Google Glass, Apple Glass). These devices are used to overlay suggested items onto the user's field of view. The server and device programs are implemented using Python, machine learning algorithms, and RESTful APIs.

[1159] Examples and prompts

[1160] As an example, consider how a 20-year-old female user A uses the system.

[1161] 1. User A logs in to the system and enters his height of 160 cm, weight of 50 kg, and personal color of "spring."

[1162] 2. You choose to have a casual style and prefer blue and white.

[1163] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt) and collects the latest spring trend data (e.g., floral print shirt, light blue denim).

[1164] 4. The server combines these to generate a proposal list and sends it to the smart glasses.

[1165] 5. The smart glasses overlay the suggestion list onto User A's field of view, and User A gives feedback that the floral print shirt is a "favorite."

[1166] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[1167] An example of a prompt is:

[1168] User ID: user_12345

[1169] Basic information: Height 160cm, weight 50kg, personal color "Spring"

[1170] Purchase history: Blue jeans, white T-shirt

[1171] Preferences: Blue and white, casual style

[1172] Trend data: Spring trends include floral print shirts and light blue denim

[1173] Feedback: Floral print shirt is my favorite

[1174] As described above, the present invention provides a system that can make personalized fashion and cosmetic suggestions to users in real time.

[1175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1176] Step 1:

[1177] The user enters basic information and preferences. After logging in, the user enters their height, weight, age, gender, personal color, favorite colors and styles, and items of interest through the smart glasses. The entered information is sent to the server.

[1178] input:

[1179] Height, weight, age, gender, personal color

[1180] Favorite colors, styles, and items

[1181] output:

[1182] The input data is sent to the server and stored in a database.

[1183] Step 2:

[1184] The server stores the received user's basic information and preferences in a database.

[1185] input:

[1186] Basic information and preferences submitted by you

[1187] output:

[1188] User information stored in a database

[1189] Step 3:

[1190] The server analyzes past purchase history based on the stored information. The server retrieves the user's past purchase history stored in the database and analyzes it using a machine learning algorithm.

[1191] input:

[1192] User's past purchase history retrieved from the database

[1193] output:

[1194] Analysis results showing user preferences and trends

[1195] Step 4:

[1196] Collect the latest trend data from external data sources and store it in the database. The server uses an external API to get the latest trend information and store it in the database.

[1197] input:

[1198] Trend data obtained from external APIs

[1199] output:

[1200] Trend data stored in a database

[1201] Step 5:

[1202] The server generates a list of recommendations by combining basic user information, past purchase history, and trend data. The server then uses a machine learning algorithm to generate the optimal list of recommendations based on the acquired data.

[1203] input:

[1204] User Basic Information

[1205] Past purchase history

[1206] Trend Data

[1207] output:

[1208] Suggestion List

[1209] Step 6:

[1210] Sending the proposal list to the user's terminal: The server sends the generated proposal list to the user's terminal, such as smart glasses.

[1211] input:

[1212] Suggestion List

[1213] output:

[1214] The proposal list sent to the user's device

[1215] Step 7:

[1216] The server collects and analyzes user feedback on the proposed items. Users input their ratings and opinions on the proposed items through the smart glasses. The server collects this feedback and stores it in a database.

[1217] input:

[1218] User Feedback

[1219] output:

[1220] Feedback stored in the database

[1221] Step 8:

[1222] Update the machine learning model to improve the next list of suggestions based on the feedback. The server analyzes the collected feedback and uses it to improve the machine learning model.

[1223] input:

[1224] Feedback stored in the database

[1225] output:

[1226] Improved machine learning models

[1227] Step 9:

[1228] Overlaying personalized suggestions onto the user's field of view: The smart glasses overlay items from the suggestion list onto the user's field of view.

[1229] input:

[1230] Suggestion List

[1231] output:

[1232] Overlaid suggested items

[1233] Step 10:

[1234] Update recommended items in real time based on user ratings: The smart glasses instantly adjust and update suggested items based on user feedback.

[1235] input:

[1236] User Feedback

[1237] output:

[1238] Updated Suggested Items

[1239] This allows users to receive personalized fashion and cosmetic suggestions in real time.

[1240] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1241] The present invention relates to a system that proposes personalized fashion and cosmetic products to a user, and further includes an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[1242] User Data Collection and Storage

[1243] 1. When a user registers or logs in to the system, they first enter their email address and password for authentication.

[1244] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[1245] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[1246] 4. The server stores these preferences in a database.

[1247] Analyzing user data

[1248] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[1249] 6. The server uses machine learning algorithms to analyze past purchase history and analyze user preferences and trends, and stores the results of this analysis in a database.

[1250] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[1251] Personalized suggestion generation

[1252] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history. The generated list is stored in a database.

[1253] 9. The server sends the generated proposal list to the user's device.

[1254] Displaying suggestions, collecting feedback, and emotion recognition

[1255] 10. The device displays the sent proposal list to the user. The displayed proposal list is presented in a format that is easy for the user to view.

[1256] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[1257] 12. The device collects the user's feedback and emotion data and sends it to the server, where it is stored in a database.

[1258] 13. The server analyzes the received feedback and sentiment data. It updates the machine learning model based on the feedback data.

[1259] 14. The server uses the emotional data as information to further tailor the next suggestion list to the user's preferences.

[1260] Specific examples

[1261] Example 1: 20-year-old female user A

[1262] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[1263] 2. User A prefers a casual style and selects that he likes blue and white.

[1264] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[1265] 4. The server combines these to generate a proposal list and sends it to User A's device.

[1266] 5. The device displays the list of suggestions, and User A provides feedback on the floral print shirt as a "favorite," and the emotion engine also collects User A's facial expression data.

[1267] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[1268] Example 2: For 25-year-old male user B

[1269] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[1270] 2. User B selects that he prefers a formal style and prefers black and gray.

[1271] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[1272] 4. The server combines these to generate a proposal list and sends it to User B's device.

[1273] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it. The emotion engine also simultaneously collects User B's emotion data.

[1274] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[1275] This allows the system to provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. In addition, by utilizing emotion data, more detailed responses are possible, further improving the accuracy of suggestions made by the system as a whole.

[1276] The processing flow will be explained below.

[1277] Step 1:

[1278] A user registers or logs in to the system. The user enters their email address and password for authentication.

[1279] Step 2:

[1280] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[1281] Step 3:

[1282] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[1283] Step 4:

[1284] The server stores the selected preference information in a database.

[1285] Step 5:

[1286] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[1287] Step 6:

[1288] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[1289] Step 7:

[1290] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[1291] Step 8:

[1292] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[1293] Step 9:

[1294] The server transmits the generated proposal list to the user's terminal.

[1295] Step 10:

[1296] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[1297] Step 11:

[1298] Users provide feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[1299] Step 12:

[1300] The terminal collects the user's feedback and emotion data and sends it to the server, which stores the feedback and emotion data in a database.

[1301] Step 13:

[1302] The server analyzes the received feedback and sentiment data and updates the machine learning model based on the feedback data.

[1303] Step 14:

[1304] The server uses the emotional data as information to further match the next suggestion list to the user's preferences.

[1305] Step 15:

[1306] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[1307] Example 2

[1308] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1309] Conventional online shopping systems have a problem in that recommendations to users are not personalized, making it difficult to provide items that match the individual preferences of each user. In addition, feedback data is limited to simple evaluations such as "good" or "bad," making it difficult to improve the accuracy of recommendations that reflect the user's true feelings and preferences.

[1310] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting and analyzing user feedback on proposed items; means for acquiring feedback and emotion data on the proposed items; and means for updating a machine learning model to improve the next proposal list based on the feedback and emotion data. This makes it possible to make personalized proposals based on the user's basic information, preferences, past purchase history, and latest trend data, and to provide highly accurate proposals that reflect the user's true emotions and preferences.

[1311] 1. "User" refers to an individual who uses the System and enters basic information and preferences.

[1312] 2. "Basic information" refers to basic data about the user, such as height, weight, age, gender, and personal color.

[1313] 3. "Preferences" refers to information such as the user's preferred colors, styles, and items of interest.

[1314] 4. "Database" refers to data storage within the system for safely and efficiently storing users' basic information, preferences, past purchase history, trend data, feedback, and sentiment data.

[1315] 5. "Purchase history" refers to detailed information such as category, color, and brand of products purchased by a user in the past.

[1316] 6. "External data source" refers to a source of information for obtaining data from outside the system, such as online fashion sites or trend information services.

[1317] 7. "Latest Trend Data" refers to data showing the latest fashions and trends in fashion and cosmetics.

[1318] 8. "Suggestion List" refers to a personalized list of items generated by combining a user's basic information, preferences, past purchase history, and trend data.

[1319] 9. "Terminal" refers to the electronic device, such as a computer, smartphone, or tablet, that a User uses to access the System and view the Proposal List.

[1320] 10. "Feedback" refers to the evaluations and opinions of users regarding proposed items, such as "good," "bad," or "favorite."

[1321] 11. "Emotional Data" means data that indicates a user's emotional state, collected based on the user's facial expressions and behavior.

[1322] 12. “Machine Learning Model” means an algorithmic model used to optimize recommendations based on user preferences, feedback, and sentiment data.

[1323] 13. "System" refers to a collection of computer programs and hardware that includes a set of processes for collecting and analyzing user data, generating a list of suggestions, and collecting and analyzing feedback.

[1324] This invention is a system that provides personalized fashion and cosmetic recommendations to users, and combines it with an emotion engine that recognizes the user's emotions. The system analyzes the user's input information and generates optimal recommendations.

[1325] System configuration

[1326] The system consists of the following main components:

[1327] 1. User terminal: refers to the device (e.g., computer, smartphone, tablet) through which a user enters information and receives a list of suggestions.

[1328] 2. Server: The central system that performs the main processing such as data collection, analysis, storage, and generating suggestion lists.

[1329] 3. Database: Storage within the system that stores users' basic information, preferences, past purchase history, trend data, feedback and sentiment data.

[1330] 4. Emotion engine: Software for collecting and analyzing emotional data from the user's facial expressions and voice (e.g., OpenCV, Emotion API).

[1331] Main software and hardware used

[1332] Machine learning algorithms: Machine learning libraries such as Scikit-learn and TensorFlow are used to analyze user preferences and purchase history.

[1333] External interface: Uses the API of fashion sites to collect the latest trend data.

[1334] Database Management System: Uses a relational database such as MySQL or PostgreSQL.

[1335] Sentiment analysis tools: OpenCV, Emotion API

[1336] Detailed System Operation

[1337] 1. User Registration and Authentication

[1338] When a user registers or logs in to the system, they enter their email address and password. The server authenticates this and, if successful, issues a token and returns it to the user.

[1339] 2. Enter your basic information and preferences

[1340] Users input basic information such as height, weight, age, gender, and personal color. They also select their preferred colors, styles, and items of interest. The server acquires this information and stores it in a database.

[1341] 3. User Data Analysis

[1342] The server retrieves the user's past purchase history from the database, analyzes it using Scikit-learn and TensorFlow, and analyzes the user's preferences and trends. It also collects the latest trend data through an external interface and stores it in the database.

[1343] 4. Generate and send a proposal list

[1344] The server combines the user's basic information, preferences, past purchase history, and trend data to generate the optimal recommendation list, which is then stored in a database in JSON format and sent to the user's device.

[1345] 5. View the list of suggestions and gather feedback

[1346] The user terminal displays the list of suggestions, and the user gives feedback such as "good," "bad," or "favorite." In addition, an emotion engine is used to collect emotional data from the user's facial expressions and voice.

[1347] 6. Analysis of Feedback and Emotion Data

[1348] The server collects and analyzes user feedback and sentiment data to update the machine learning model to improve the next list of suggestions.

[1349] Specific examples

[1350] Example 1: 20-year-old female user A

[1351] User A logs into the system and enters basic information (e.g., height 160 cm, weight 50 kg, personal color "spring"). He selects his preferred style (e.g., casual, blue and white colors). The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt), collects the latest trend data (e.g., "floral print shirt" and "light blue denim"), and generates a suggestion list. This suggestion list is sent to User A's device. User A provides feedback on the suggested items, saying "favorite," and the emotion engine collects facial expression data. The server analyzes this and improves the next suggestion list.

[1352] Prompt Sentence Examples

[1353] "What latest fashion items would you suggest to a 20-year-old woman who likes blue and white for her spring casual style?"

[1354] In this way, this system can provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. Furthermore, by utilizing emotion data, even more detailed responses are possible, further improving the accuracy of suggestions.

[1355] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1356] System program processing flow

[1357] Step 1:

[1358] A user registers or logs in to the system. Specifically, the user enters their email address and password, and this data is sent to the server. The server receives this and performs authentication. If authentication is successful, the server generates an authentication token and returns it to the user. The input is an email address and password, and the output is an authentication token.

[1359] Step 2:

[1360] The user enters basic information (height, weight, age, gender, personal color, etc.) and preferences (color, style, items of interest, etc.). The entered data is sent to the server. The server receives this data and stores it in a database. The input is the user's basic information and preferences, and the output is the results stored in the database.

[1361] Step 3:

[1362] The server retrieves the user's past purchase history from the database. Specifically, it uses an SQL query to extract the user's purchase history data. This purchase history data is used for data analysis. The input is the purchase history retrieved from the database, and the output is the past purchase history data used for analysis.

[1363] Step 4:

[1364] The server uses a machine learning algorithm (e.g., Scikit-learn) to analyze the user's past purchase history and identify trends and preferences. The input is past purchase history data, and the output is the analysis results of the user's preferences. Specifically, the server performs a series of analytical processes, including feature extraction, data preprocessing, and model training.

[1365] Step 5:

[1366] The server collects the latest trend data from an external data source (e.g., a fashion site's API). It requests the trend data through the API and stores the acquired data in a database. The input is the latest trend data acquired from outside, and the output is the trend data stored in the database.

[1367] Step 6:

[1368] The server generates a list of suggestions by combining the user's basic information, preferences, past purchase history, and the latest trend data. Specifically, it uses an algorithm to integrate information from each data source and select the most suitable items. The input is the user's basic information, preferences, purchase history, and trend data, and the output is the generated list of suggestions (e.g., in JSON format).

[1369] Step 7:

[1370] The server sends the generated proposal list to the user's device. Specifically, it uses a REST API to send the proposal list to the user's device. The input is the generated proposal list, and the output is the receipt of the proposal list on the user's device.

[1371] Step 8:

[1372] The terminal displays the suggestion list to the user in an easy-to-view format, including item images, descriptions, prices, etc. The input is the received suggestion list, and the output is the suggestions displayed on the user terminal.

[1373] Step 9:

[1374] The user inputs feedback on the proposed item. Specifically, the user rates the item as "good," "bad," or "favorite," and inputs the feedback data. The input is the user's feedback information, and the output is sending the feedback data to the server.

[1375] Step 10:

[1376] The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. The input is the user's facial expressions and voice data, and the output is the collected emotional data. Specific operations involve the use of image and voice analysis algorithms.

[1377] Step 11:

[1378] The terminal transmits the user's feedback and emotion data to the server. Specifically, the data is converted into an appropriate format and sent to the server. The input is the feedback and emotion data, and the output is data transmission to the server.

[1379] Step 12:

[1380] The server analyzes the received feedback and emotion data. The input is the sent feedback and emotion data, and the output is the analysis results. Specifically, it performs data analysis based on the feedback and emotion data and updates the machine learning model.

[1381] Step 13:

[1382] The server generates information based on the analysis results to improve the next suggestion list. The input is the analysis results, and the output is an improved suggestion list. Specifically, the server applies the retrained machine learning model to make suggestions that better match the user's preferences.

[1383] The above is the flow of processing in the system program and the specific operations of each step.

[1384] (Application example 2)

[1385] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1386] Modern consumers demand personalized product recommendations based on their preferences and trends, but existing systems do not adequately meet these demands. Furthermore, existing systems are unable to accurately capture users' emotions, resulting in inaccurate recommendations. Therefore, there is a need for a system that can collect users' individual emotions and feedback in real time and provide more accurate personalized recommendations.

[1387] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting the latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting feedback and emotion data from the user about the proposed items; means for analyzing the collected feedback and emotion data and updating a machine learning model to improve the next proposal list; and means including an emotion recognition engine for visually displaying the proposal list and collecting emotion data from the user in real time. This enables highly accurate proposals that meet the individual needs of the user and improves user satisfaction.

[1388] "Means for users to input basic information and preferences" refers to an interface that allows users to input information such as height, weight, age, gender, personal color, and preferred styles and colors.

[1389] "Means for storing in a database" refers to software and hardware for securely storing the entered basic information and preferences in a database.

[1390] "Means for analyzing past purchase history" refers to algorithms and software used to analyze the categories, colors, brands, etc. of items a user has previously purchased to identify the user's preferences and tendencies.

[1391] "Means for collecting the latest trend data from external data sources and storing it in a database" refers to software and hardware for collecting the latest trend information from external fashion sites and APIs and storing it in a database.

[1392] "Means for generating a suggestion list" refers to algorithms and software for generating a list that suggests suitable fashion items and cosmetics to a user based on the user's basic information, past purchase history, and the latest trend data.

[1393] "Means for transmitting the generated proposal list to the user's terminal" refers to software and communication means for transmitting the generated proposal list to the user's smartphone, smart glasses, head-mounted display, etc.

[1394] "Means for collecting feedback and emotional data" refers to the interface and software for capturing user feedback on the proposed item and emotional data collected using the emotion recognition engine.

[1395] "Means for analyzing collected feedback and sentiment data" refers to algorithms and software for analyzing collected feedback and sentiment data to improve the accuracy of the next list of suggestions.

[1396] "Means for updating machine learning models" refers to machine learning algorithms and software for continuously improving the algorithms for generating the recommendation list based on feedback and sentiment data.

[1397] An "emotion recognition engine" refers to software and hardware for collecting and analyzing emotional data from a user's facial expressions and voice in real time.

[1398] The present invention is a system that provides personalized fashion and cosmetic recommendations to users, and improves the accuracy of recommendations based on the user's emotional data by incorporating an emotion recognition engine. Specific embodiments of the present invention are described in detail below.

[1399] User Data Collection and Storage

[1400] This system provides an interface for users to input their basic information and preferences on devices such as smartphones, smart glasses, and head-mounted displays. Users enter information such as height, weight, age, gender, personal color, and preferred styles and colors, and this information is stored in a database. Database management uses common database solutions (e.g., MySQL, PostgreSQL).

[1401] Data analysis

[1402] The server analyzes past purchase history based on the stored user basic information and preference data. It uses machine learning algorithms (e.g., Logistic Regression, Random Forest) to retrieve past purchase data from the database and analyze the user's preferences and purchasing trends. It also collects the latest fashion trend information from external data sources via API and stores this information in the database.

[1403] Personalized suggestion generation

[1404] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. This recommendation list uses an algorithm to select the most suitable items and list them in an order that suits the user. The generated recommendation list is then saved back in the database. The recommendation list is then sent to the user's device and displayed visually.

[1405] Displaying suggestions, collecting feedback, and emotion recognition

[1406] The device displays the suggested items to the user, who then inputs feedback such as "good," "bad," or "favorite." At the same time, an emotion recognition engine (e.g., EmotionRecognitionEngine) is used to collect real-time emotional data from the user's facial expressions and voice. This feedback and emotional data is sent from the device to a server and stored in a database.

[1407] Analyzing Data and Updating Models

[1408] The server analyzes the collected feedback and sentiment data and updates the machine learning model for generating the next recommendation list. The collected data is an important factor in improving the accuracy of the recommendation list generation algorithm.

[1409] Specific examples

[1410] For example, a 30-year-old female user logs in and registers data such as her height of 165 cm, weight of 55 kg, personal color of "winter," and preferred style of "elegant." The server will suggest a "black slim-fit dress" and a "silver necklace" based on her past purchase history and the latest trends. The user will then provide feedback that they are "favorites," and the emotion engine will recognize their facial expression of satisfaction.

[1411] Prompt Sentence Examples

[1412] text

[1413] User data: Height 165cm, Weight 55kg, Personal color "Winter", Favorite style "Elegant"

[1414] Previous purchase history: Black slim-fit dress, silver necklace

[1415] The latest trend: elegant pieces in black and silver

[1416] Feedback: Favorite

[1417] Emotion data: Satisfied facial expression

[1418] This allows for highly accurate proposals that meet the individual needs of users, thereby improving user satisfaction.

[1419] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1420] Step 1:

[1421] The server provides an interface for users to input their basic information and preferences on their devices. The information entered by users, such as height, weight, age, gender, personal color, and preferred style and color, is stored in a database via the device. The input data is encrypted to ensure security.

[1422] Step 2:

[1423] The server retrieves the basic information and preference data stored in the database, pulls the user's past purchase history from the database, and performs an analysis. Machine learning algorithms (e.g., Logistic Regression, Random Forest) are used to identify the user's preferences and purchasing trends. The results of this analysis are stored in the database as new data points and are later used to generate recommendations.

[1424] Step 3:

[1425] The server collects the latest fashion trend information through APIs of external data sources. The collected information is stored in a database and pre-processed to ensure accuracy and consistency, including filtering unnecessary data and normalizing the data.

[1426] Step 4:

[1427] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. It uses machine learning algorithms to analyze and select the items that best suit the user. This recommendation list is stored in a database and later sent to the device.

[1428] Step 5:

[1429] The generated suggestion list is sent to the user's device, which then displays the suggested items to the user in a visually appealing and easily understandable format, with optimized UI / UX design.

[1430] Step 6:

[1431] The user provides feedback on the suggested items, such as "good," "bad," or "favorite." The device analyzes the user's facial expressions and voice in real time using an emotion recognition engine (e.g., EmotionRecognitionEngine) to collect emotional data. The collected feedback and emotional data are sent from the device to a server and stored in a database.

[1432] Step 7:

[1433] The server analyzes the collected feedback and sentiment data and updates the machine learning model with new learning data to improve the accuracy of the next recommendation list. Model updates include retraining and tuning hyperparameters.

[1434] Step 8:

[1435] The server uses the updated machine learning model to generate the next list of suggestions, which can be more tailored to the user's individual needs.

[1436] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1437] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1438] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1439] [Fourth embodiment]

[1440] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1441] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1442] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1443] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1444] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1446] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1447] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1448] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1449] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1450] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1451] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1452] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1453] The present invention relates to a system that makes personalized fashion and cosmetic suggestions to users, and specific embodiments thereof will be described below.

[1454] User Data Collection and Storage

[1455] 1. When a user registers or logs in to the system, they first enter their email address and password.

[1456] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[1457] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[1458] 4. The server stores these preferences in a database.

[1459] Analyzing user data

[1460] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[1461] 6. The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends.

[1462] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[1463] Personalized suggestion generation

[1464] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history.

[1465] 9. The server sends the proposal list to the user's device.

[1466] View suggestions and gather feedback

[1467] 10. The device displays the sent proposal list to the user. The proposal list is appropriately designed so that it is displayed in a format that is easy for the user to view.

[1468] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite."

[1469] 12. The device collects user feedback and sends it to the server.

[1470] 13. The server stores the received feedback in a database and analyzes it.

[1471] 14. The server updates the machine learning model based on the feedback to improve the next list of suggestions.

[1472] Specific examples

[1473] Example 1: 20-year-old female user A

[1474] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[1475] 2. User A prefers a casual style and selects that he likes blue and white.

[1476] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[1477] 4. The server combines these to generate a proposal list and sends it to User A's device.

[1478] 5. The device displays the suggestion list, and User A gives feedback on the floral print shirt as a "favorite."

[1479] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[1480] Example 2: For 25-year-old male user B

[1481] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[1482] 2. User B selects that he prefers a formal style and prefers black and gray.

[1483] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[1484] 4. The server combines these to generate a proposal list and sends it to User B's device.

[1485] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it.

[1486] 6. The server receives the feedback and purchase data and updates the machine learning model to improve the next list of suggestions.

[1487] This allows highly accurate proposals that meet the individual needs of the user to be provided, thereby improving user satisfaction.

[1488] The processing flow will be explained below.

[1489] Step 1:

[1490] A user registers or logs in to the system. The user enters their email address and password for authentication.

[1491] Step 2:

[1492] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[1493] Step 3:

[1494] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[1495] Step 4:

[1496] The server stores the selected preference information in a database.

[1497] Step 5:

[1498] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[1499] Step 6:

[1500] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[1501] Step 7:

[1502] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[1503] Step 8:

[1504] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[1505] Step 9:

[1506] The server transmits the generated proposal list to the user's terminal.

[1507] Step 10:

[1508] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[1509] Step 11:

[1510] The user gives feedback on the suggested items, such as "good," "bad," or "favorite." Feedback is input from the device.

[1511] Step 12:

[1512] The device collects user feedback and sends it to the server, where it is stored in a database.

[1513] Step 13:

[1514] The server analyzes the received feedback and updates the machine learning model based on the feedback data.

[1515] Step 14:

[1516] The server uses the updated machine learning model to further improve the next list of suggestions.

[1517] Step 15:

[1518] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[1519] Example 1

[1520] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1521] A system that efficiently provides users with personalized fashion and cosmetic recommendations is required to accurately grasp user preferences and trends and quickly incorporate the latest trend data. However, conventional systems have been unable to provide recommendations that fully reflect user preferences, resulting in low user satisfaction. Furthermore, it has been difficult to effectively utilize feedback information and incorporate it into subsequent recommendations, which has led to delays in system improvements.

[1522] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1523] In this invention, the server includes an interface means for the user to input basic information and preferences, a means for saving the input basic information and preferences in a database, and a means for analyzing past purchase history based on the saved basic information and preferences, thereby enabling highly accurate suggestions that meet the individual needs of the user.

[1524] "Interface means" refers to a display device or input device that allows a user to input basic information and preferences.

[1525] "Database" refers to an information storage system for storing user basic information, preferences, purchase history, feedback information, trend data, and the like.

[1526] "Analysis means" refers to a processing device or software that uses stored data to analyze a user's purchase history, preferences, trend data, etc.

[1527] "External data source" refers to an information provider, such as an API or web service, that can be used to obtain the latest trend data from outside the system.

[1528] "Suggestion list" refers to a recommended list of fashion and cosmetic items that is generated based on the analysis results and provided to the user.

[1529] "Terminal" refers to a device, such as a smartphone or PC, on which a user receives and displays the suggestion list and enters feedback.

[1530] "Feedback" refers to information that a user inputs about a proposed item, such as their evaluation or opinion.

[1531] "Machine learning model" refers to an algorithm or numerical model that uses user data and feedback to improve the accuracy of suggestions across the system.

[1532] The present invention is a system for providing personalized fashion and cosmetic suggestions to users. Specific embodiments are described below.

[1533] User Data Collection

[1534] When a user registers or logs in to the system, they first enter their email address and password. They then enter basic information such as their height, weight, age, gender, and personal color. This is done using an input interface in a web browser or mobile app, and is developed based on the Django framework.

[1535] The entered information is collected by the server and stored in a PostgreSQL database. The user then enters their preferred colors, styles, items of interest, etc., and this information is also stored in the database.

[1536] Analyzing user data

[1537] The server retrieves the user's past purchase history from the database and processes the data using Python's Pandas library. The server then analyzes the user's past purchase history using machine learning algorithms, specifically clustering and collaborative filtering using the Scikit-Learn library.

[1538] Next, the server collects the latest trend data from external data sources. This is done using APIs from fashion and cosmetics websites, such as Style API and Fashion Cloud API. The collected trend data is then stored in a database.

[1539] Personalized suggestion generation

[1540] The server uses machine learning models to generate a personalized recommendation list based on the user's basic information, preferences, and past purchase history. This recommendation list includes fashion items and cosmetics that are best suited to the user. The generated recommendation list is sent to the user's device in JSON format via the HTTP protocol.

[1541] View suggestions and gather feedback

[1542] The user's device displays the submitted list of suggestions in an easy-to-read format. The front-end is developed using React and Vue.js. The user can then enter feedback on the suggested items, such as "good," "bad," or "favorite."

[1543] Feedback is collected on the device and sent to the server via XMLHttpRequest or the Fetch API. The server stores the received feedback in a database and retrains the machine learning model using Scikit-Learn or TensorFlow. This process improves the list of suggestions for the next iteration.

[1544] Specific examples

[1545] For User A

[1546] 1. User A logs in to the system and enters basic information such as height 160 cm, weight 50 kg, and personal color "spring."

[1547] 2. User A prefers casual style and selects that he likes blue and white.

[1548] 3. The server analyzes past purchase history (e.g., blue denim, white T-shirt) and collects "floral print shirt" and "light blue denim" as the latest trend data.

[1549] 4. The server combines these to generate a proposal list and sends it to User A's device.

[1550] 5. The device displays the suggestion list, and User A gives feedback that the floral print shirt is his favorite.

[1551] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[1552] Specific examples of prompts are as follows:

[1553] "I'm a 20-year-old woman, 160cm tall and weigh 50kg. I like casual style and I like blue and white. Please suggest some of the latest trendy items."

[1554] In this way, the system can provide highly accurate suggestions that meet the individual needs of the user, improving user satisfaction.

[1555] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1556] Step 1:

[1557] When a user registers or logs in to the system, they enter their email address and password. The entered email address and password are sent to the server through the input fields of the form. The server receives them and performs authentication processing. Input: Email address and password. Output: Authentication result (success or failure). If authentication is successful, the user will be taken to the next screen where they will be asked to enter basic information.

[1558] Step 2:

[1559] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and saves it in a database. Input: Basic user information. Output: Basic user information saved in the database. The data is processed using the Django framework and saved in a PostgreSQL database.

[1560] Step 3:

[1561] The user selects and inputs preferences such as favorite colors, styles, and items of interest. This data is sent to the server through the interface. Input: Favorite colors, styles, and items. Output: Sent preference information. The server receives this and stores it in a database.

[1562] Step 4:

[1563] The server retrieves past purchase history from the database. A user's purchase history includes details such as the category, color, and brand of the purchased items. Input: User ID. Output: Past purchase history data. The server retrieves the purchase history data and organizes it using Python's Pandas library.

[1564] Step 5:

[1565] The server uses a machine learning algorithm based on the Scikit-Learn library to analyze past purchase history. The analysis results are used to identify user preferences and trends. Input: Past purchase history data. Output: User preferences and trends. Analysis is performed using clustering and collaborative filtering techniques.

[1566] Step 6:

[1567] The server collects the latest trend data from external data sources. This uses a RESTful API to obtain the latest trend information on fashion and cosmetics. Input: API endpoint of external data source. Output: Latest trend data. For example, data can be collected using Style API or Fashion Cloud API and stored in a database.

[1568] Step 7:

[1569] The server generates an individualized recommendation list based on the user's basic information, preferences, and past purchase history. The recommendation list reflects the analysis results and the latest trend data. Input: User's basic information, preferences, past purchase history, trend data. Output: Suggestion list. A Scikit-Learn model is used to suggest the most suitable fashion items and cosmetics.

[1570] Step 8:

[1571] The server sends the generated proposal list to the user's device in JSON format. Input: Proposal list. Output: Sent proposal list. Data is sent securely using the HTTP / HTTPS protocol.

[1572] Step 9:

[1573] The device displays the suggestion list to the user in an easy-to-read format. The suggestion list is rendered using the React or Vue.js framework. Input: Suggestion list. Output: Displayed suggestion list. The user reviews the suggestion list and selects an item.

[1574] Step 10:

[1575] The user gives feedback on the suggested items, such as "good", "bad", or "favorite". Input: Feedback information. Output: Submitted feedback information. The user enters feedback using a form or buttons.

[1576] Step 11:

[1577] The device collects user feedback and sends it to the server via XMLHttpRequest or Fetch API. Input: Feedback information. Output: Feedback information sent to the server.

[1578] Step 12:

[1579] The server stores the received feedback information in a database and analyzes the data using Scikit-Learn and TensorFlow. Input: Feedback information. Output: Analysis results. The model is retrained and improved based on the feedback information.

[1580] Step 13:

[1581] The server uses the retrained machine learning model to improve the next list of suggestions. By periodically updating the model, the accuracy of suggestions to users increases. Input: Feedback data. Output: Improved list of suggestions. The update process is scheduled using Cron or Celery.

[1582] (Application example 1)

[1583] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1584] Today's consumers are increasingly seeking personalized fashion and cosmetic recommendations. However, conventional systems struggle to reflect user preferences and trends in real time, resulting in insufficient consumer satisfaction. Furthermore, there are few ways to visually confirm suggested items in real time, limiting the shopping experience. Therefore, it is necessary to improve the user experience by providing a personalized recommendation system that can overlay items onto the user's field of view.

[1585] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1586] In this invention, the server

[1587] a means for users to input basic information and preferences;

[1588] means for storing the entered basic information and preferences in a database;

[1589] means for analyzing past purchases based on stored basic information and preferences;

[1590] A means of collecting and storing up-to-date trend data from external data sources in a database;

[1591] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[1592] means for transmitting the generated proposal list to a user terminal;

[1593] means for collecting and analyzing user feedback on the proposed items;

[1594] means for updating a machine learning model to improve the next list of suggestions based on the feedback;

[1595] means for overlaying personalized suggestions onto the user's field of view;

[1596] a means for displaying recommended items in real time based on user preferences and trend data;

[1597] means for updating the recommended items based on user ratings;

[1598] Includes:

[1599] This allows for highly accurate personalized suggestions to be made based on user preferences and trends, and visual confirmation and feedback.

[1600] "User" refers to a consumer who accesses the system and enters basic information and preferences.

[1601] "Basic information" is data relating to personal attributes such as height, weight, age, sex, and personal color entered by the user.

[1602] "Preferences" refers to data on the user's tastes and preferences, such as colors and styles selected by the user, and items of interest.

[1603] A "database" is a collection of electronic data that stores basic user information, preferences, past purchase history, trend data, etc., and stores it in a format that can be used by the system.

[1604] "Past purchase history" refers to information such as category, color, brand, etc., relating to items previously purchased by the user.

[1605] "External data sources" refers to the source of the latest trend data that the system obtains from external fashion sites and APIs.

[1606] "Trend data" is information about current fashion and cosmetic trends.

[1607] The "suggestion list" is a list of recommended items for a user, generated by combining the user's basic information, past purchase history, and trend data.

[1608] "User device" refers to the user's electronic device (smartphone, tablet, PC, etc.) used to collect and send suggestion lists and feedback.

[1609] "Feedback" is data of evaluations and opinions given by users regarding proposed items.

[1610] "Machine Learning Model" means the algorithm and model used to analyze data and optimize personalized recommendations.

[1611] "Overlaying in the field of view" means overlaying suggested items directly in the user's field of view using smart glasses or the like.

[1612] "Displaying recommended items in real time" means instantly displaying recommended items that are appropriate for the moment when the user uses the system.

[1613] "Updating recommended items based on ratings" means adjusting and improving the algorithm for generating the next list of suggestions based on feedback from users.

[1614] The present invention provides a system for providing personalized fashion and cosmetic recommendations to users, specifically, a system for displaying recommended items in real time using smart glasses. Specific embodiments for implementing the present invention are described below.

[1615] System Program

[1616] The system consists of a program with the following main functions:

[1617] 1. The user enters basic information and preferences.

[1618] 2. Store your basic information and preferences in our database.

[1619] 3. Analyze past purchase history based on the stored information.

[1620] 4. Collect the latest trend data from external data sources and store it in the database.

[1621] 5. Generate a list of suggestions by combining basic user information, past purchase history, and trend data.

[1622] 6. The proposal list is sent to the user's device.

[1623] 7. Collect and analyze user feedback on the proposed items.

[1624] 8. Update the machine learning model to improve the next list of suggestions based on feedback.

[1625] 9. Overlay personalized suggestions into the user's field of view.

[1626] 10. Update recommended items in real time based on user ratings.

[1627] Processing Details

[1628] The server stores the user's basic information and preferences in a database, including height, weight, age, gender, personal color, favorite colors and styles, and favorite items. The server also collects the latest trend information from external data sources and stores it in the database. Using this data, a machine learning algorithm analyzes the user's past purchase history and generates a personalized recommendation list based on the user's preferences and the latest trends.

[1629] The user's device, such as smart glasses, receives this list of suggestions and displays it as an overlay in the user's field of view. The user's ratings and feedback on the suggested items are sent to the server via the device, and the server uses this feedback to update the machine learning model and make the next suggestions more accurate.

[1630] The hardware used includes smart glasses (e.g., Google Glass, Apple Glass). These devices are used to overlay suggested items onto the user's field of view. The server and device programs are implemented using Python, machine learning algorithms, and RESTful APIs.

[1631] Examples and prompts

[1632] As an example, consider how a 20-year-old female user A uses the system.

[1633] 1. User A logs in to the system and enters his height of 160 cm, weight of 50 kg, and personal color of "spring."

[1634] 2. You choose to have a casual style and prefer blue and white.

[1635] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt) and collects the latest spring trend data (e.g., floral print shirt, light blue denim).

[1636] 4. The server combines these to generate a proposal list and sends it to the smart glasses.

[1637] 5. The smart glasses overlay the suggestion list onto User A's field of view, and User A gives feedback that the floral print shirt is a "favorite."

[1638] 6. The server receives the feedback and updates the machine learning model to improve the next list of suggestions.

[1639] An example of a prompt is:

[1640] User ID: user_12345

[1641] Basic information: Height 160cm, weight 50kg, personal color "Spring"

[1642] Purchase history: Blue jeans, white T-shirt

[1643] Preferences: Blue and white, casual style

[1644] Trend data: Spring trends include floral print shirts and light blue denim

[1645] Feedback: Floral print shirt is my favorite

[1646] As described above, the present invention provides a system that can make personalized fashion and cosmetic suggestions to users in real time.

[1647] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1648] Step 1:

[1649] The user enters basic information and preferences. After logging in, the user enters their height, weight, age, gender, personal color, favorite colors and styles, and items of interest through the smart glasses. The entered information is sent to the server.

[1650] input:

[1651] Height, weight, age, gender, personal color

[1652] Favorite colors, styles, and items

[1653] output:

[1654] The input data is sent to the server and stored in a database.

[1655] Step 2:

[1656] The server stores the received user's basic information and preferences in a database.

[1657] input:

[1658] Basic information and preferences submitted by you

[1659] output:

[1660] User information stored in a database

[1661] Step 3:

[1662] The server analyzes past purchase history based on the stored information. The server retrieves the user's past purchase history stored in the database and analyzes it using a machine learning algorithm.

[1663] input:

[1664] User's past purchase history retrieved from the database

[1665] output:

[1666] Analysis results showing user preferences and trends

[1667] Step 4:

[1668] Collect the latest trend data from external data sources and store it in the database. The server uses an external API to get the latest trend information and store it in the database.

[1669] input:

[1670] Trend data obtained from external APIs

[1671] output:

[1672] Trend data stored in a database

[1673] Step 5:

[1674] The server generates a list of recommendations by combining basic user information, past purchase history, and trend data. The server then uses a machine learning algorithm to generate the optimal list of recommendations based on the acquired data.

[1675] input:

[1676] User Basic Information

[1677] Past purchase history

[1678] Trend Data

[1679] output:

[1680] Suggestion List

[1681] Step 6:

[1682] Sending the proposal list to the user's terminal: The server sends the generated proposal list to the user's terminal, such as smart glasses.

[1683] input:

[1684] Suggestion List

[1685] output:

[1686] The proposal list sent to the user's device

[1687] Step 7:

[1688] The server collects and analyzes user feedback on the proposed items. Users input their ratings and opinions on the proposed items through the smart glasses. The server collects this feedback and stores it in a database.

[1689] input:

[1690] User Feedback

[1691] output:

[1692] Feedback stored in the database

[1693] Step 8:

[1694] Update the machine learning model to improve the next list of suggestions based on the feedback. The server analyzes the collected feedback and uses it to improve the machine learning model.

[1695] input:

[1696] Feedback stored in the database

[1697] output:

[1698] Improved machine learning models

[1699] Step 9:

[1700] Overlaying personalized suggestions onto the user's field of view: The smart glasses overlay items from the suggestion list onto the user's field of view.

[1701] input:

[1702] Suggestion List

[1703] output:

[1704] Overlaid suggested items

[1705] Step 10:

[1706] Update recommended items in real time based on user ratings: The smart glasses instantly adjust and update suggested items based on user feedback.

[1707] input:

[1708] User Feedback

[1709] output:

[1710] Updated Suggested Items

[1711] This allows users to receive personalized fashion and cosmetic suggestions in real time.

[1712] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1713] The present invention relates to a system that proposes personalized fashion and cosmetic products to a user, and further includes an emotion engine that recognizes the user's emotions. Specific embodiments of the system are described below.

[1714] User Data Collection and Storage

[1715] 1. When a user registers or logs in to the system, they first enter their email address and password for authentication.

[1716] 2. The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[1717] 3. The user selects and enters preferences such as preferred colors, styles, and items of interest.

[1718] 4. The server stores these preferences in a database.

[1719] Analyzing user data

[1720] 5. The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[1721] 6. The server uses machine learning algorithms to analyze past purchase history and analyze user preferences and trends, and stores the results of this analysis in a database.

[1722] 7. The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[1723] Personalized suggestion generation

[1724] 8. The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history. The generated list is stored in a database.

[1725] 9. The server sends the generated proposal list to the user's device.

[1726] Displaying suggestions, collecting feedback, and emotion recognition

[1727] 10. The device displays the sent proposal list to the user. The displayed proposal list is presented in a format that is easy for the user to view.

[1728] 11. The user gives feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[1729] 12. The device collects the user's feedback and emotion data and sends it to the server, where it is stored in a database.

[1730] 13. The server analyzes the received feedback and sentiment data. It updates the machine learning model based on the feedback data.

[1731] 14. The server uses the emotional data as information to further tailor the next suggestion list to the user's preferences.

[1732] Specific examples

[1733] Example 1: 20-year-old female user A

[1734] 1. When User A logs in to the system, basic information such as height 160 cm, weight 50 kg, and personal color "spring" is entered.

[1735] 2. User A prefers a casual style and selects that he likes blue and white.

[1736] 3. The server analyzes User A's past purchase history (e.g., blue denim, white T-shirts) and collects "floral print shirts" and "light blue denim" as the latest spring trend data.

[1737] 4. The server combines these to generate a proposal list and sends it to User A's device.

[1738] 5. The device displays the list of suggestions, and User A provides feedback on the floral print shirt as a "favorite," and the emotion engine also collects User A's facial expression data.

[1739] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[1740] Example 2: For 25-year-old male user B

[1741] 1. User B logs in and enters basic information such as height 175 cm, weight 70 kg, and personal color "Autumn."

[1742] 2. User B selects that he prefers a formal style and prefers black and gray.

[1743] 3. The server analyzes User B's past purchase history (e.g., black suit, gray tie) and collects "wool jacket" and "dark gray pants" as the latest autumn trend data.

[1744] 4. The server combines these to generate a proposal list and sends it to User B's device.

[1745] 5. The device displays the list of suggestions, and User B rates the wool jacket as "good" and purchases it. The emotion engine also simultaneously collects User B's emotion data.

[1746] 6. The server receives the feedback and sentiment data and updates the machine learning model to improve the next list of suggestions.

[1747] This allows the system to provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. In addition, by utilizing emotion data, more detailed responses are possible, further improving the accuracy of suggestions made by the system as a whole.

[1748] The processing flow will be explained below.

[1749] Step 1:

[1750] A user registers or logs in to the system. The user enters their email address and password for authentication.

[1751] Step 2:

[1752] The server obtains the user's basic information (height, weight, age, gender, personal color, etc.) through an input form and stores it in a database.

[1753] Step 3:

[1754] The user selects and inputs preferences such as preferred colors, styles, and items of interest.

[1755] Step 4:

[1756] The server stores the selected preference information in a database.

[1757] Step 5:

[1758] The server retrieves the user's past purchase history (category, color, brand, etc. of purchased items) from the database.

[1759] Step 6:

[1760] The server uses machine learning algorithms to analyze past purchase history and identify user preferences and trends, and stores the results of this analysis in a database.

[1761] Step 7:

[1762] The server collects the latest trend data from external data sources (e.g., fashion site APIs) and stores it in a database.

[1763] Step 8:

[1764] The server generates a list of recommended fashion items and cosmetics based on the user's basic information, preferences, and past purchase history, and stores the list in a database.

[1765] Step 9:

[1766] The server transmits the generated proposal list to the user's terminal.

[1767] Step 10:

[1768] The terminal displays the suggestion list to the user, and the displayed suggestion list is provided in a format that is easy for the user to view.

[1769] Step 11:

[1770] Users provide feedback on the suggested items, such as "good," "bad," or "favorite." At the same time, the emotion engine monitors the user's facial expressions and behavior to collect emotional data.

[1771] Step 12:

[1772] The terminal collects the user's feedback and emotion data and sends it to the server, which stores the feedback and emotion data in a database.

[1773] Step 13:

[1774] The server analyzes the received feedback and sentiment data and updates the machine learning model based on the feedback data.

[1775] Step 14:

[1776] The server uses the emotional data as information to further match the next suggestion list to the user's preferences.

[1777] Step 15:

[1778] The accuracy of the entire system will improve so that future suggestions will be more suited to the user's preferences.

[1779] Example 2

[1780] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1781] Conventional online shopping systems have a problem in that recommendations to users are not personalized, making it difficult to provide items that match the individual preferences of each user. In addition, feedback data is limited to simple evaluations such as "good" or "bad," making it difficult to improve the accuracy of recommendations that reflect the user's true feelings and preferences.

[1782] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting and analyzing user feedback on proposed items; means for acquiring feedback and emotion data on the proposed items; and means for updating a machine learning model to improve the next proposal list based on the feedback and emotion data. This makes it possible to make personalized proposals based on the user's basic information, preferences, past purchase history, and latest trend data, and to provide highly accurate proposals that reflect the user's true emotions and preferences.

[1783] 1. "User" refers to an individual who uses the System and enters basic information and preferences.

[1784] 2. "Basic information" refers to basic data about the user, such as height, weight, age, gender, and personal color.

[1785] 3. "Preferences" refers to information such as the user's preferred colors, styles, and items of interest.

[1786] 4. "Database" refers to data storage within the system for safely and efficiently storing users' basic information, preferences, past purchase history, trend data, feedback, and sentiment data.

[1787] 5. "Purchase history" refers to detailed information such as category, color, and brand of products purchased by a user in the past.

[1788] 6. "External data source" refers to a source of information for obtaining data from outside the system, such as online fashion sites or trend information services.

[1789] 7. "Latest Trend Data" refers to data showing the latest fashions and trends in fashion and cosmetics.

[1790] 8. "Suggestion List" refers to a personalized list of items generated by combining a user's basic information, preferences, past purchase history, and trend data.

[1791] 9. "Terminal" refers to the electronic device, such as a computer, smartphone, or tablet, that a User uses to access the System and view the Proposal List.

[1792] 10. "Feedback" refers to the evaluations and opinions of users regarding proposed items, such as "good," "bad," or "favorite."

[1793] 11. "Emotional Data" means data that indicates a user's emotional state, collected based on the user's facial expressions and behavior.

[1794] 12. “Machine Learning Model” means an algorithmic model used to optimize recommendations based on user preferences, feedback, and sentiment data.

[1795] 13. "System" refers to a collection of computer programs and hardware that includes a set of processes for collecting and analyzing user data, generating a list of suggestions, and collecting and analyzing feedback.

[1796] This invention is a system that provides personalized fashion and cosmetic recommendations to users, and combines it with an emotion engine that recognizes the user's emotions. The system analyzes the user's input information and generates optimal recommendations.

[1797] System configuration

[1798] The system consists of the following main components:

[1799] 1. User terminal: refers to the device (e.g., computer, smartphone, tablet) through which a user enters information and receives a list of suggestions.

[1800] 2. Server: The central system that performs the main processing such as data collection, analysis, storage, and generating suggestion lists.

[1801] 3. Database: Storage within the system that stores users' basic information, preferences, past purchase history, trend data, feedback and sentiment data.

[1802] 4. Emotion engine: Software for collecting and analyzing emotional data from the user's facial expressions and voice (e.g., OpenCV, Emotion API).

[1803] Main software and hardware used

[1804] Machine learning algorithms: Machine learning libraries such as Scikit-learn and TensorFlow are used to analyze user preferences and purchase history.

[1805] External interface: Uses the API of fashion sites to collect the latest trend data.

[1806] Database Management System: Uses a relational database such as MySQL or PostgreSQL.

[1807] Sentiment analysis tools: OpenCV, Emotion API

[1808] Detailed System Operation

[1809] 1. User Registration and Authentication

[1810] When a user registers or logs in to the system, they enter their email address and password. The server authenticates this and, if successful, issues a token and returns it to the user.

[1811] 2. Enter your basic information and preferences

[1812] Users input basic information such as height, weight, age, gender, and personal color. They also select their preferred colors, styles, and items of interest. The server acquires this information and stores it in a database.

[1813] 3. User Data Analysis

[1814] The server retrieves the user's past purchase history from the database, analyzes it using Scikit-learn and TensorFlow, and analyzes the user's preferences and trends. It also collects the latest trend data through an external interface and stores it in the database.

[1815] 4. Generate and send a proposal list

[1816] The server combines the user's basic information, preferences, past purchase history, and trend data to generate the optimal recommendation list, which is then stored in a database in JSON format and sent to the user's device.

[1817] 5. View the list of suggestions and gather feedback

[1818] The user terminal displays the list of suggestions, and the user gives feedback such as "good," "bad," or "favorite." In addition, an emotion engine is used to collect emotional data from the user's facial expressions and voice.

[1819] 6. Analysis of Feedback and Emotion Data

[1820] The server collects and analyzes user feedback and sentiment data to update the machine learning model to improve the next list of suggestions.

[1821] Specific examples

[1822] Example 1: 20-year-old female user A

[1823] User A logs into the system and enters basic information (e.g., height 160 cm, weight 50 kg, personal color "spring"). He selects his preferred style (e.g., casual, blue and white colors). The server analyzes User A's past purchase history (e.g., blue denim, white T-shirt), collects the latest trend data (e.g., "floral print shirt" and "light blue denim"), and generates a suggestion list. This suggestion list is sent to User A's device. User A provides feedback on the suggested items, saying "favorite," and the emotion engine collects facial expression data. The server analyzes this and improves the next suggestion list.

[1824] Prompt Sentence Examples

[1825] "What latest fashion items would you suggest to a 20-year-old woman who likes blue and white for her spring casual style?"

[1826] In this way, this system can provide highly accurate suggestions that meet the individual needs of users, improving user satisfaction. Furthermore, by utilizing emotion data, even more detailed responses are possible, further improving the accuracy of suggestions.

[1827] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1828] System program processing flow

[1829] Step 1:

[1830] A user registers or logs in to the system. Specifically, the user enters their email address and password, and this data is sent to the server. The server receives this and performs authentication. If authentication is successful, the server generates an authentication token and returns it to the user. The input is an email address and password, and the output is an authentication token.

[1831] Step 2:

[1832] The user enters basic information (height, weight, age, gender, personal color, etc.) and preferences (color, style, items of interest, etc.). The entered data is sent to the server. The server receives this data and stores it in a database. The input is the user's basic information and preferences, and the output is the results stored in the database.

[1833] Step 3:

[1834] The server retrieves the user's past purchase history from the database. Specifically, it uses an SQL query to extract the user's purchase history data. This purchase history data is used for data analysis. The input is the purchase history retrieved from the database, and the output is the past purchase history data used for analysis.

[1835] Step 4:

[1836] The server uses a machine learning algorithm (e.g., Scikit-learn) to analyze the user's past purchase history and identify trends and preferences. The input is past purchase history data, and the output is the analysis results of the user's preferences. Specifically, the server performs a series of analytical processes, including feature extraction, data preprocessing, and model training.

[1837] Step 5:

[1838] The server collects the latest trend data from an external data source (e.g., a fashion site's API). It requests the trend data through the API and stores the acquired data in a database. The input is the latest trend data acquired from outside, and the output is the trend data stored in the database.

[1839] Step 6:

[1840] The server generates a list of suggestions by combining the user's basic information, preferences, past purchase history, and the latest trend data. Specifically, it uses an algorithm to integrate information from each data source and select the most suitable items. The input is the user's basic information, preferences, purchase history, and trend data, and the output is the generated list of suggestions (e.g., in JSON format).

[1841] Step 7:

[1842] The server sends the generated proposal list to the user's device. Specifically, it uses a REST API to send the proposal list to the user's device. The input is the generated proposal list, and the output is the receipt of the proposal list on the user's device.

[1843] Step 8:

[1844] The terminal displays the suggestion list to the user in an easy-to-view format, including item images, descriptions, prices, etc. The input is the received suggestion list, and the output is the suggestions displayed on the user terminal.

[1845] Step 9:

[1846] The user inputs feedback on the proposed item. Specifically, the user rates the item as "good," "bad," or "favorite," and inputs the feedback data. The input is the user's feedback information, and the output is sending the feedback data to the server.

[1847] Step 10:

[1848] The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. The input is the user's facial expressions and voice data, and the output is the collected emotional data. Specific operations involve the use of image and voice analysis algorithms.

[1849] Step 11:

[1850] The terminal transmits the user's feedback and emotion data to the server. Specifically, the data is converted into an appropriate format and sent to the server. The input is the feedback and emotion data, and the output is data transmission to the server.

[1851] Step 12:

[1852] The server analyzes the received feedback and emotion data. The input is the sent feedback and emotion data, and the output is the analysis results. Specifically, it performs data analysis based on the feedback and emotion data and updates the machine learning model.

[1853] Step 13:

[1854] The server generates information based on the analysis results to improve the next suggestion list. The input is the analysis results, and the output is an improved suggestion list. Specifically, the server applies the retrained machine learning model to make suggestions that better match the user's preferences.

[1855] The above is the flow of processing in the system program and the specific operations of each step.

[1856] (Application example 2)

[1857] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1858] Modern consumers demand personalized product recommendations based on their preferences and trends, but existing systems do not adequately meet these demands. Furthermore, existing systems are unable to accurately capture users' emotions, resulting in inaccurate recommendations. Therefore, there is a need for a system that can collect users' individual emotions and feedback in real time and provide more accurate personalized recommendations.

[1859] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information and preferences; means for saving the input basic information and preferences in a database; means for analyzing past purchase history based on the saved basic information and preferences; means for collecting the latest trend data from an external data source and saving it in a database; means for generating a proposal list by combining the user's basic information, past purchase history, and trend data; means for transmitting the generated proposal list to the user's terminal; means for collecting feedback and emotion data from the user about the proposed items; means for analyzing the collected feedback and emotion data and updating a machine learning model to improve the next proposal list; and means including an emotion recognition engine for visually displaying the proposal list and collecting emotion data from the user in real time. This enables highly accurate proposals that meet the individual needs of the user and improves user satisfaction.

[1860] "Means for users to input basic information and preferences" refers to an interface that allows users to input information such as height, weight, age, gender, personal color, and preferred styles and colors.

[1861] "Means for storing in a database" refers to software and hardware for securely storing the entered basic information and preferences in a database.

[1862] "Means for analyzing past purchase history" refers to algorithms and software used to analyze the categories, colors, brands, etc. of items a user has previously purchased to identify the user's preferences and tendencies.

[1863] "Means for collecting the latest trend data from external data sources and storing it in a database" refers to software and hardware for collecting the latest trend information from external fashion sites and APIs and storing it in a database.

[1864] "Means for generating a suggestion list" refers to algorithms and software for generating a list that suggests suitable fashion items and cosmetics to a user based on the user's basic information, past purchase history, and the latest trend data.

[1865] "Means for transmitting the generated proposal list to the user's terminal" refers to software and communication means for transmitting the generated proposal list to the user's smartphone, smart glasses, head-mounted display, etc.

[1866] "Means for collecting feedback and emotional data" refers to the interface and software for capturing user feedback on the proposed item and emotional data collected using the emotion recognition engine.

[1867] "Means for analyzing collected feedback and sentiment data" refers to algorithms and software for analyzing collected feedback and sentiment data to improve the accuracy of the next list of suggestions.

[1868] "Means for updating machine learning models" refers to machine learning algorithms and software for continuously improving the algorithms for generating the recommendation list based on feedback and sentiment data.

[1869] An "emotion recognition engine" refers to software and hardware for collecting and analyzing emotional data from a user's facial expressions and voice in real time.

[1870] The present invention is a system that provides personalized fashion and cosmetic recommendations to users, and improves the accuracy of recommendations based on the user's emotional data by incorporating an emotion recognition engine. Specific embodiments of the present invention are described in detail below.

[1871] User Data Collection and Storage

[1872] This system provides an interface for users to input their basic information and preferences on devices such as smartphones, smart glasses, and head-mounted displays. Users enter information such as height, weight, age, gender, personal color, and preferred styles and colors, and this information is stored in a database. Database management uses common database solutions (e.g., MySQL, PostgreSQL).

[1873] Data analysis

[1874] The server analyzes past purchase history based on the stored user basic information and preference data. It uses machine learning algorithms (e.g., Logistic Regression, Random Forest) to retrieve past purchase data from the database and analyze the user's preferences and purchasing trends. It also collects the latest fashion trend information from external data sources via API and stores this information in the database.

[1875] Personalized suggestion generation

[1876] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. This recommendation list uses an algorithm to select the most suitable items and list them in an order that suits the user. The generated recommendation list is then saved back in the database. The recommendation list is then sent to the user's device and displayed visually.

[1877] Displaying suggestions, collecting feedback, and emotion recognition

[1878] The device displays the suggested items to the user, who then inputs feedback such as "good," "bad," or "favorite." At the same time, an emotion recognition engine (e.g., EmotionRecognitionEngine) is used to collect real-time emotional data from the user's facial expressions and voice. This feedback and emotional data is sent from the device to a server and stored in a database.

[1879] Analyzing Data and Updating Models

[1880] The server analyzes the collected feedback and sentiment data and updates the machine learning model for generating the next recommendation list. The collected data is an important factor in improving the accuracy of the recommendation list generation algorithm.

[1881] Specific examples

[1882] For example, a 30-year-old female user logs in and registers data such as her height of 165 cm, weight of 55 kg, personal color of "winter," and preferred style of "elegant." The server will suggest a "black slim-fit dress" and a "silver necklace" based on her past purchase history and the latest trends. The user will then provide feedback that they are "favorites," and the emotion engine will recognize their facial expression of satisfaction.

[1883] Prompt Sentence Examples

[1884] text

[1885] User data: Height 165cm, Weight 55kg, Personal color "Winter", Favorite style "Elegant"

[1886] Previous purchase history: Black slim-fit dress, silver necklace

[1887] The latest trend: elegant pieces in black and silver

[1888] Feedback: Favorite

[1889] Emotion data: Satisfied facial expression

[1890] This allows for highly accurate proposals that meet the individual needs of users, thereby improving user satisfaction.

[1891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1892] Step 1:

[1893] The server provides an interface for users to input their basic information and preferences on their devices. The information entered by users, such as height, weight, age, gender, personal color, and preferred style and color, is stored in a database via the device. The input data is encrypted to ensure security.

[1894] Step 2:

[1895] The server retrieves the basic information and preference data stored in the database, pulls the user's past purchase history from the database, and performs an analysis. Machine learning algorithms (e.g., Logistic Regression, Random Forest) are used to identify the user's preferences and purchasing trends. The results of this analysis are stored in the database as new data points and are later used to generate recommendations.

[1896] Step 3:

[1897] The server collects the latest fashion trend information through APIs of external data sources. The collected information is stored in a database and pre-processed to ensure accuracy and consistency, including filtering unnecessary data and normalizing the data.

[1898] Step 4:

[1899] The server combines the user's basic information, past purchase history, and the latest trend data to generate a personalized recommendation list. It uses machine learning algorithms to analyze and select the items that best suit the user. This recommendation list is stored in a database and later sent to the device.

[1900] Step 5:

[1901] The generated suggestion list is sent to the user's device, which then displays the suggested items to the user in a visually appealing and easily understandable format, with optimized UI / UX design.

[1902] Step 6:

[1903] The user provides feedback on the suggested items, such as "good," "bad," or "favorite." The device analyzes the user's facial expressions and voice in real time using an emotion recognition engine (e.g., EmotionRecognitionEngine) to collect emotional data. The collected feedback and emotional data are sent from the device to a server and stored in a database.

[1904] Step 7:

[1905] The server analyzes the collected feedback and sentiment data and updates the machine learning model with new learning data to improve the accuracy of the next recommendation list. Model updates include retraining and tuning hyperparameters.

[1906] Step 8:

[1907] The server uses the updated machine learning model to generate the next list of suggestions, which can be more tailored to the user's individual needs.

[1908] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1909] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1910] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1911] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1912] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1913] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1914] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1915] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1916] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1917] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1918] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1919] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1920] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1921] 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.

[1922] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1923] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1924] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1925] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1926] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1927] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1928] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1929] The following is further disclosed regarding the above embodiment.

[1930] (Claim 1)

[1931] a means for users to input basic information and preferences;

[1932] means for storing the entered basic information and preferences in a database;

[1933] means for analyzing past purchases based on stored basic information and preferences;

[1934] A means of collecting and storing up-to-date trend data from external data sources in a database;

[1935] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[1936] means for transmitting the generated proposal list to a user terminal;

[1937] means for collecting and analyzing user feedback on the proposed items;

[1938] means for updating a machine learning model to improve the next list of suggestions based on the feedback;

[1939] A system including:

[1940] (Claim 2)

[1941] 10. The system of claim 1, wherein a machine learning algorithm is used to analyze a user's past purchase history.

[1942] (Claim 3)

[1943] 10. The system of claim 1, wherein the latest collected trend data is obtained from an external API.

[1944] "Example 1"

[1945] (Claim 1)

[1946] an interface means for a user to input basic information and preferences;

[1947] means for storing the entered basic information and preferences in a database;

[1948] means for analyzing past purchases based on stored basic information and preferences;

[1949] A means of collecting and storing up-to-date trend data from external data sources in a database;

[1950] a means for combining a user's basic information, purchase history, and trend data to generate a personalized list of suggestions;

[1951] means for transmitting the generated proposal list to a user terminal;

[1952] means for collecting user feedback on the proposed items, storing it in a database and analyzing it;

[1953] means for updating a machine learning model to improve the next list of suggestions based on the feedback;

[1954] A system including:

[1955] (Claim 2)

[1956] 10. The system of claim 1, wherein a machine learning algorithm is used to analyze a user's past purchase history.

[1957] (Claim 3)

[1958] 10. The system of claim 1, wherein the latest collected trend data is obtained from an external API.

[1959] "Application Example 1"

[1960] (Claim 1)

[1961] a means for users to input basic information and preferences;

[1962] means for storing the entered basic information and preferences in a database;

[1963] means for analyzing past purchases based on stored basic information and preferences;

[1964] A means of collecting and storing up-to-date trend data from external data sources in a database;

[1965] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[1966] means for transmitting the generated proposal list to a user terminal;

[1967] means for collecting and analyzing user feedback on the proposed items;

[1968] means for updating a machine learning model to improve the next list of suggestions based on the feedback;

[1969] means for overlaying personalized suggestions onto the user's field of view;

[1970] a means for displaying recommended items in real time based on user preferences and trend data;

[1971] means for updating the recommended items based on user ratings;

[1972] A system including:

[1973] (Claim 2)

[1974] 10. The system of claim 1, wherein a machine learning algorithm is used to analyze a user's past purchase history.

[1975] (Claim 3)

[1976] 10. The system of claim 1, wherein the latest collected trend data is obtained from an external API.

[1977] "Example 2: Combining Emotion Engines"

[1978] (Claim 1)

[1979] a means for users to input basic information and preferences;

[1980] means for storing the entered basic information and preferences in a database;

[1981] means for analyzing past purchases based on stored basic information and preferences;

[1982] A means of collecting and storing up-to-date trend data from external data sources in a database;

[1983] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[1984] means for transmitting the generated proposal list to a user terminal;

[1985] means for collecting and analyzing user feedback on the proposed items;

[1986] means for obtaining feedback and sentiment data for the proposed items;

[1987] means for updating a machine learning model to improve the next list of suggestions based on the feedback and sentiment data;

[1988] A system including:

[1989] (Claim 2)

[1990] 10. The system of claim 1, wherein a machine learning algorithm is used to analyze a user's past purchase history.

[1991] (Claim 3)

[1992] 10. The system of claim 1, wherein the latest collected trend data is obtained from an external interface.

[1993] "Application example 2 when combining emotion engines"

[1994] (Claim 1)

[1995] a means for users to input basic information and preferences;

[1996] means for storing the entered basic information and preferences in a database;

[1997] means for analyzing past purchases based on stored basic information and preferences;

[1998] A means of collecting and storing up-to-date trend data from external data sources in a database;

[1999] A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data;

[2000] means for transmitting the generated proposal list to a user terminal;

[2001] means for collecting user feedback and sentiment data for the proposed items;

[2002] A means of analyzing the collected feedback and sentiment data and updating the machine learning model to improve the next list of suggestions; and

[2003] means for visually displaying the suggestion list and including an emotion recognition engine for collecting emotion data from the user in real time;

[2004] A system including:

[2005] (Claim 2)

[2006] 10. The system of claim 1, wherein the system uses machine learning algorithms to analyze a user's past purchase history and sentiment data.

[2007] (Claim 3)

[2008] 10. The system of claim 1, wherein the latest collected trend data is obtained from an external data source. [Explanation of symbols]

[2009] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for users to input basic information and preferences; means for storing the entered basic information and preferences in a database; means for analyzing past purchases based on stored basic information and preferences; A means of collecting and storing up-to-date trend data from external data sources in a database; A means for generating a recommendation list by combining basic information of the user, past purchase history, and trend data; means for transmitting the generated proposal list to a user terminal; means for collecting and analyzing user feedback on the proposed items; means for updating a machine learning model to improve the next list of suggestions based on the feedback; A system including:

2. The system of claim 1 , wherein the system uses a machine learning algorithm to analyze a user's past purchasing history.

3. The system of claim 1 , wherein the latest collected trend data is obtained from an external API.

Images