system

Abstract

Provide a system. [Solution] a means of recording a customer's past purchase history, favorite items, physical data, and style preferences; means for analyzing customer characteristics using said recorded data; A means for proposing optimal fashion and makeup items to the customer based on the analysis results; A system including:

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 systems for suggesting fashion and makeup items have difficulty comprehensively considering a customer's past purchasing history, preferences, and body type information, making it difficult to provide optimal suggestions for each individual customer. Furthermore, it takes a lot of time and effort for customers to find the items that best suit them. Therefore, there is a need for a system that can efficiently respond to diverse customer needs and quickly and accurately suggest fashion and makeup items. [Means for solving the problem]

[0005] The present invention provides a system that records a customer's past purchase history, favorite items, physical data, and style preferences, and uses them to analyze the customer's characteristics. It also includes a means for proposing optimal fashion and makeup items to the customer based on the analysis results. By providing a means for inputting new data, the system obtains the customer's latest information and uses a machine learning model to predict their style, thereby making optimal suggestions for each individual customer. These means allow customers to easily find the items that best suit them, significantly saving time and effort.

[0006] "Purchase history" refers to a record of products and services that a customer has purchased in the past.

[0007] "Favorite items" are products or services that a customer particularly likes and often maintains as a specific list.

[0008] "Physical Data" refers to information related to a customer's body shape, size, and fit, such as height, weight, and waist size.

[0009] "Style preferences" refers to information that indicates a customer's preferred fashion and makeup style, including preferences for color, design, and trends.

[0010] "Means of recording" refers to the functions and methods by which the system stores various customer data and makes it available for later use.

[0011] "Means of analysis" refers to the methods and algorithms that the system uses to process recorded data and derive customer characteristics and trends.

[0012] "Means of suggestion" refers to the methods and system functions for showing customers the most suitable fashion and makeup items based on the analysis results.

[0013] "Means for inputting new data" refers to the interface or method by which a customer can add information to the system, such as updated physical data or preferences.

[0014] A "machine learning model" refers to a mathematical model or algorithm that learns from past data and makes predictions and classifications. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0037] System configuration

[0038] Recording customer data

[0039] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[0040] Customer data analysis

[0041] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[0042] Style prediction with machine learning

[0043] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[0044] Proposal of the best fashion items

[0045] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[0046] Entering New Data

[0047] Users can input their latest physical data, preferences, and other information. The new data is added to the system and used for the next analysis and prediction.

[0048] Program processing

[0049] Data loading and preprocessing

[0050] The server reads the customer's past purchase data, preferences, and body type information from a CSV file, etc. This data includes the customer's body type, favorite colors, past purchases, etc.

[0051] The server uses LabelEncoder to convert textual information into numbers, converting the data into a format that is easy for machine learning models to use. This preprocessing step ensures that the data is properly prepared.

[0052] Training the model

[0053] The server extracts input data (e.g., body type information, favorite colors, past purchases) and target data (customer style) from the data and trains a machine learning model, which generates a model that predicts style based on the customer's data.

[0054] Entering and Processing New Data

[0055] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[0056] The server takes this new data and feeds it into a machine learning model to make predictions.

[0057] Presentation of results

[0058] The server uses a machine learning model to convert the predicted style into a format that humans can understand and suggests the most suitable fashion items to the user.

[0059] The terminal displays the recommendation results received from the server to the user, allowing the user to easily find the item that best suits them.

[0060] Specific examples

[0061] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the device displays the results to the user.

[0062] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The server reads data from the customer_data.csv file, which contains customer purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using the Python pandas library.

[0066] Step 2:

[0067] The server uses LabelEncoder to convert the customer's style information into a numerical value, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for the machine learning model to process.

[0068] Step 3:

[0069] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y). Specifically, it executes X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[0070] Step 4:

[0071] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[0072] Step 5:

[0073] The user inputs new data (body type, favorite colors, past purchases, etc.) This data is collected through the terminal and sent to the server.

[0074] Step 6:

[0075] The terminal converts the new customer data you enter into a DataFrame format. Specifically, it creates the data as follows:

[0076] python

[0077] new_customer_data = pd.DataFrame({

[0078] 'customer_id': [1],

[0079] 'body_type': ['slim'],

[0080] 'fav_colors': ['blue'],

[0081] 'past_purchases': ['T-shirt']

[0082] })

[0083] Step 7:

[0084] The server receives new customer data and passes it to a pre-trained machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases']] and executes model.predict(customer_X) to get the prediction style.

[0085] Step 8:

[0086] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[0087] Step 9:

[0088] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[0089] python

[0090] print(recommendations)

[0091] Step 10:

[0092] The terminal displays the recommended styles received from the server to the user, allowing the user to check the fashion items that best suit them.

[0093] The above are the specific processing steps in this system.

[0094] Example 1

[0095] 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."

[0096] Conventional systems for suggesting fashion and makeup items have been unable to fully reflect the individual characteristics and preferences of customers, resulting in low customer satisfaction. Furthermore, data entry is cumbersome, making them impractical. To address these issues, a system is needed that can efficiently analyze diverse customer information and quickly suggest the best items for each individual customer.

[0097] 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.

[0098] In this invention, the server includes: means for recording a customer's past purchase history, favorite items, physical data, and style preferences; means for analyzing the customer's characteristics using the recorded data; means for training a machine learning model using the analysis results to predict the customer's style; means for suggesting optimal fashion and makeup items to the customer based on the prediction results of the machine learning model; means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer; and means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer.

[0099] "Customer's past purchase history" refers to a record of products and services previously purchased by a customer, including, for example, the date and time of purchase, the name, quantity, and price of the purchased items.

[0100] "Favorite Items" is a list of products or services that a customer particularly likes, including items that the customer purchases frequently and items of special interest.

[0101] "Physical Data" refers to data about a customer's body shape and physical characteristics, including, for example, height, weight, body fat percentage, and waist circumference.

[0102] "Style preferences" refers to data about a customer's preferred fashion and makeup styles, including their preferred clothing colors and designs, and favorite brands.

[0103] "Means of Recording" refers to the method or system for storing customer data, including, for example, means for storing data in the form of a database or a CSV file.

[0104] "Means for analyzing characteristics" refers to methods or systems for extracting and analyzing customer characteristics based on recorded data, including, for example, data analysis software and algorithms.

[0105] A "machine learning model" is an algorithm or program that can learn from data and make predictions or classifications. Examples include models such as random forests and neural networks.

[0106] "Training means" refers to a method or system for effectively training a machine learning model, including, for example, means for splitting a dataset and tuning model parameters.

[0107] "Means for suggesting" refers to methods or systems that present suitable products or services to customers based on analysis and prediction results. Examples include recommendation systems and notification functions.

[0108] "Information input methods" are the methods or interfaces that allow customers to enter new data into a system. Examples include input fields on web forms or mobile apps.

[0109] "Means for processing input information" refers to methods or systems that analyze new data acquired from customers and convert it into an appropriate format. For example, this may include data pre-processing algorithms.

[0110] The "means for displaying the recommendation results" refers to a method or system for visually displaying the recommendation results from the server to the user. For example, this includes the display screen of a web page or a mobile app.

[0111] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with each element of the server, terminal, and user.

[0112] System configuration

[0113] Recording customer data

[0114] The server records the customer's past purchase history, favorite items, physical data, and style preferences. This includes the ability to save the customer's purchase and physical data to a CSV file or database. For example, the data can be read from a CSV file using the Python pandas library.

[0115] Customer data analysis

[0116] The server analyzes customer characteristics based on the recorded data. Specifically, data analysis software and algorithms are used to extract characteristics based on the customer's body type, preferences, and past purchase history. Data frame manipulation using pandas and preprocessing techniques using sklearn are used here.

[0117] Style prediction using machine learning models

[0118] The server uses a machine learning model to predict the customer's style. This model can be a random forest or a neural network. Specifically, the server can use the random forest classifier from the sklearn library. The model is trained by splitting the dataset and adjusting parameters.

[0119] Proposal of the best fashion items

[0120] The server then uses the predictions made by the machine learning model to suggest the best fashion and makeup items for each customer, for example by retrieving items from a database that are suitable for a specific style and generating a specific product list.

[0121] Entering New Data

[0122] The device provides an interface through which users can input new data, including their current physical data and preferences. The input data is sent in real time to a server for analysis.

[0123] Program processing

[0124] The server reads the customer data, converts the text information into numbers using LabelEncoder, and standardizes them. The preprocessed data is then used to train machine learning models.

[0125] Next, when the user inputs new data using the device, the data is sent to the server. The server preprocesses this new data and inputs it into the machine learning model to make predictions. Finally, the server generates item suggestions based on the prediction results and sends them to the device. The device then displays the suggestions to the user, providing them with the most suitable fashion items.

[0126] Specific examples

[0127] For example, if a user enters information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and processes it using LabelEncoder and StandardScaler. Next, a machine learning model is used to predict "casual style," and based on the results, suggestions such as "blue T-shirts" and "denim jackets" are made. These suggestions are then displayed on the device, allowing the user to easily find the items that best suit them.

[0128] Prompt Sentence Examples

[0129] Body type: Slim

[0130] Favorite color: Blue

[0131] Previous purchase: T-shirt

[0132] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1:

[0135] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or a database. Specifically, it uses the pandas library to read the data with the pandas.read_csv() method, which results in the customer data in a data frame format.

[0136] Input: CSV file containing customer data

[0137] Output: Customer data in dataframe format

[0138] Step 2:

[0139] The server performs preprocessing on the loaded data, which includes converting categorical data to numeric values ​​using LabelEncoder, and then normalizing the data using StandardScaler.

[0140] Input: Customer data in dataframe format

[0141] Output: Customer data converted to numbers and normalized

[0142] Step 3:

[0143] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the data into a training set and a test set and trains the model using a random forest classifier. This step uses train_test_split and RandomForestClassifier.

[0144] Input: Customer data converted to numbers and normalized

[0145] Output: A trained machine learning model

[0146] Step 4:

[0147] The terminal provides an interface through which the user can input new data, such as body type information, favorite colors, past purchases, etc. This allows the user's latest data to be collected.

[0148] Input: User's new body type, favorite colors, past purchases

[0149] Output: The user's new data

[0150] Step 5:

[0151] The device sends new data entered by the user to the server using an HTTP request. The server receives this data and performs preprocessing. Again, it uses LabelEncoder and StandardScaler to convert the new data into a format suitable for the machine learning model.

[0152] Input: User's new data

[0153] Output: Preprocessed new user data

[0154] Step 6:

[0155] The server inputs the preprocessed new user data into the machine learning model and makes predictions. Specifically, it uses the new data to predict style and selects the most suitable fashion items based on that prediction.

[0156] Input: Preprocessed new user data

[0157] Output: Predicted style and suggested fashion items based on it

[0158] Step 7:

[0159] The server converts the prediction results into a human-understandable format and suggests the most suitable fashion and makeup items for the user, for example, "For a casual style, a blue T-shirt and denim jacket."

[0160] Input: predicted style

[0161] Output: Human-understandable fashion and makeup item suggestions

[0162] Step 8:

[0163] The device displays the proposed results received from the server to the user. Specifically, the proposed items are displayed in list format on a web page or mobile app screen so that the user can easily check them.

[0164] Input: Fashion and makeup suggestions

[0165] Output: The suggestions displayed to the user

[0166] As described above, the entire system functions in concert based on the specific operations performed at each processing step and their inputs and outputs. This series of processes allows users to efficiently find the fashion and makeup items that are best suited to them.

[0167] (Application example 1)

[0168] 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."

[0169] In recent years, there has been a demand for personalized recommendations of fashion and makeup items for customers with diverse needs. However, conventional systems have had difficulty in making recommendations that fully reflect the characteristics of each customer, making it difficult to recommend appropriate items. Furthermore, the difficulty of making recommendations in real time has limited the improvement of customer experience in physical stores.

[0170] 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.

[0171] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for analyzing the customer's characteristics using the recorded data, means for proposing optimal fashion and makeup items to the customer based on the analysis results, means for providing an interface through which the customer can input new data, means for predicting and proposing a style in real time based on the input data, and means for displaying the predicted style to the customer using a smartphone. This makes it possible to reflect the customer's individual characteristics in real time and propose optimal fashion and makeup items.

[0172] "Customer's past purchase history" refers to data on products and services that a customer has purchased in the past.

[0173] "Favorite items" refers to data on products and services that customers particularly like to purchase or use.

[0174] "Physical data" refers to information about a customer's physical characteristics, such as height, weight, and body type.

[0175] "Style preferences" refers to information about the trends and tastes of fashion and makeup that a customer particularly likes.

[0176] "Customer characteristics" are individual characteristics of a customer extracted based on the customer's purchasing history, favorite items, physical data, and style preferences.

[0177] A "machine learning model" is an algorithm that learns patterns in data and makes predictions or classifications based on new data.

[0178] A "smartphone" is a type of mobile phone, a device that has multi-functional computing capabilities and is capable of running a variety of applications.

[0179] An "interface" is the means by which a user inputs data into or receives information from a system.

[0180] "Real time" refers to a time period in which data is input and processed immediately, and the results are immediately available.

[0181] "Prediction" is the use of machine learning models to estimate future outcomes or trends based on given data.

[0182] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0183] System configuration

[0184] Recording customer data

[0185] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[0186] Customer data analysis

[0187] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[0188] Style prediction with machine learning

[0189] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[0190] Proposal of the best fashion items

[0191] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[0192] Entering New Data

[0193] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[0194] Real-time predictions and suggestions

[0195] The server receives this new data, feeds it into machine learning models, and makes real-time predictions, which are then displayed to the user via their smartphone, where they can view suggested styles and products.

[0196] Specific examples

[0197] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the smartphone device displays the results to the user.

[0198] Prompt Sentence Examples

[0199] Enter the new user data in the following format:

[0200] Build: Slim

[0201] Favorite color: Blue

[0202] Previously purchased item: T-shirt

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or database.

[0206] Input: CSV file or database

[0207] Output: A list of customer data

[0208] The server uses database access and file I / O operations to retrieve customer history and preference data and store it in list format.

[0209] Step 2:

[0210] The server preprocesses the data and converts it into a format that can be used by the machine learning model, for example, converting text information about a customer's favorite colors and styles into numbers.

[0211] Input: List of customer data

[0212] Output: Preprocessed data frame

[0213] The server uses LabelEncoder to convert the character data into numerical data, making it easier for the machine learning model to process.

[0214] Step 3:

[0215] The server uses the preprocessed data to train a machine learning model, such as a random forest classifier.

[0216] Input: preprocessed data frame, style labels

[0217] Output: A trained machine learning model

[0218] The server separates the features and target variables and applies machine learning algorithms to train the model.

[0219] Step 4:

[0220] The terminal provides an interface for the user to enter new data, such as body measurements, favorite colors, and past purchase history.

[0221] Input: New data for the user

[0222] Output: A JSON object of the user-entered data

[0223] The user enters information according to the provided format, and the terminal converts it into JSON format and sends it to the server.

[0224] Step 5:

[0225] The server receives new data entered by the user, pre-processes it, and then feeds it into a trained machine learning model.

[0226] Input: A JSON object of new data entered by the user.

[0227] Output: Predicted style labels

[0228] The server preprocesses the new data and runs style predictions against the machine learning model.

[0229] Step 6:

[0230] The server suggests optimal fashion and makeup items to the user based on the predicted style.

[0231] Input: Predicted style labels

[0232] Output: A list of the best fashion and makeup items

[0233] The server selects suggested items based on the style prediction results and generates a list of them.

[0234] Step 7:

[0235] The terminal displays the suggested fashion and makeup items to the user.

[0236] Enter: a list of the best fashion and makeup items.

[0237] Output: Recommended items displayed to the user

[0238] The terminal displays the item list received from the server on a user interface, allowing the user to view these suggestions.

[0239] Each of the above steps makes it possible to reflect the individual characteristics of each customer in real time and suggest the most suitable fashion and makeup items.

[0240] 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.

[0241] The present invention provides a system that combines a customer's past purchase history, favorite items, physical data, style preferences, and an emotion engine that recognizes the user's emotions to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with the server, terminal, and user elements.

[0242] System configuration

[0243] Recording customer and sentiment data

[0244] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This record is saved in a CSV file or database.

[0245] Customer and sentiment data analysis

[0246] The server uses the recorded customer data and emotional data to analyze the characteristics of each customer, including extracting characteristics based on the customer's body type information, preferences, past purchase history, and emotional data.

[0247] Emotion recognition by emotion engine

[0248] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The recognized emotion data is sent to the server.

[0249] Style prediction with machine learning

[0250] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier) ​​that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[0251] Proposal of the best fashion items

[0252] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[0253] Entering new data and emotion data

[0254] Users can input new information, such as their latest physical data, preferences, and emotional data. The new data is added to the system and used for the next analysis and prediction.

[0255] Program processing

[0256] Data loading and preprocessing

[0257] The server reads the customer's past purchase data, preferences, body type information, and emotional data from CSV files, etc. This data includes the customer's body type information, favorite colors, past purchases, emotional state, etc.

[0258] Training a machine learning model

[0259] The server extracts input data (e.g., body type information, favorite colors, past purchases, emotional data) and target data (customer style) from the data, and trains a machine learning model to generate a style prediction model based on the customer data.

[0260] Entering new data and emotion data

[0261] The terminal provides an interface where the user can input new data (body type, favorite color, past purchases, emotional data, etc.) The input data is sent to the server.

[0262] Emotion recognition and data processing

[0263] The terminal receives the user's new data and uses the emotion engine to obtain emotion data, which is then sent to the server.

[0264] Proposal Generation

[0265] The server receives new customer data and sentiment data, inputs it into a machine learning model, and generates predictions, which are optimized to take the sentiment data into account.

[0266] The server uses LabelEncoder to reconvert the predicted numeric style into its original format (string) and provides it as a suggested result.

[0267] Specific examples

[0268] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model.

[0269] Additionally, when the emotion engine detects the user's emotion of joy, the server has the function of suggesting items with brighter colors and fun designs, allowing users to easily find fashion items that best suit them and match their current emotions.

[0270] As described above, the present invention provides a system that can quickly and accurately respond to the diverse needs and emotional states of customers and suggest optimal fashion and makeup items.

[0271] The processing flow will be explained below.

[0272] Step 1:

[0273] The server reads data from the customer_data.csv file, which contains the customer's past purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using Python's pandas library.

[0274] Step 2:

[0275] The server uses LabelEncoder to convert the customer's style information into a number, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for machine learning models to use.

[0276] Step 3:

[0277] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y), specifically, X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[0278] Step 4:

[0279] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[0280] Step 5:

[0281] Users input emotional data (e.g., facial expressions and tone of voice) along with new data (body type, favorite colors, past purchases, etc.), which is collected via the device and sent to the server.

[0282] Step 6:

[0283] The terminal converts the new customer data and emotion data into DataFrame format. Specifically, it creates the data as follows:

[0284] python

[0285] new_customer_data = pd.DataFrame({

[0286] 'customer_id': [1],

[0287] 'body_type': ['slim'],

[0288] 'fav_colors': ['blue'],

[0289] 'past_purchases': ['T-shirt'],

[0290] 'emotion': ['happy']

[0291] })

[0292] Step 7:

[0293] The server receives new customer data and passes it to the machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases', 'emotion']] and executes model.predict(customer_X) to get the prediction style.

[0294] Step 8:

[0295] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[0296] Step 9:

[0297] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[0298] python

[0299] print(recommendations)

[0300] Step 10:

[0301] The device displays the recommended styles received from the server to the user, allowing the user to see which fashion items are best suited to them. For example, if the server detects the emotion of joy, it will suggest items with bright colors and fun designs.

[0302] The above are the specific processing steps in this system.

[0303] Example 2

[0304] 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."

[0305] While conventional fashion recommendation systems take into account a customer's past purchasing history and style preferences, they are unable to make recommendations that take into account the customer's emotional state. This makes it difficult to make optimal recommendations that match the customer's current emotions. Furthermore, new data cannot be input in real time, making it impossible to always make predictions based on the latest customer data.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0307] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for recording emotional data using an emotion engine that recognizes user emotions, means for analyzing customer characteristics using the recorded data, means for predicting the customer's style using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and the emotional data, thereby enabling optimal suggestions that take into account the customer's emotional state and new data in real time.

[0308] "Customer's past purchasing history" refers to a record of the products and services that a customer has purchased in the past.

[0309] "Favorite Items" is a list of products and services that a customer particularly likes.

[0310] "Physical data" refers to information about a customer's physical characteristics and measurements, such as height, weight, and body type.

[0311] "Style preferences" refers to information about the customer's preferred fashion and design characteristics, such as color, material, and design pattern.

[0312] An "emotion engine" is software or hardware for recognizing and analyzing a user's emotions.

[0313] "Emotion data" is data on the user's emotional state as recognized by the emotion engine.

[0314] A "machine learning model" is an algorithm or model that learns from data and makes predictions or classifications.

[0315] "Style prediction" refers to predicting the best fashion and makeup items based on customer data.

[0316] "Preprocessing" is the process of preparing raw data in a form suitable for analysis and learning.

[0317] "Real-time" refers to processing and analysis occurring close to the moment the data is generated.

[0318] The "suggestion results" are a list of fashion and makeup items that the system recommends to the customer.

[0319] The present invention is a system that collects a customer's past purchase history, favorite items, physical data, style preferences, and emotional data, and uses machine learning models to suggest optimal fashion and makeup items for each customer. This system operates in cooperation with the elements of a server, terminals, and users.

[0320] Recording customer and sentiment data

[0321] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This data is saved in a CSV file or database. Programming languages ​​such as Python and R are used as the software to implement the system.

[0322] Customer and sentiment data analysis

[0323] The server uses the recorded customer data and emotional data to analyze each customer's characteristics. This analysis includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. The data analysis uses the pandas and numpy libraries.

[0324] Emotion recognition by emotion engine

[0325] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and tone of voice. The recognized emotion data is sent to the server. Tools such as OpenCV and OpenSmile are used for emotion recognition.

[0326] Style prediction with machine learning

[0327] The server predicts a customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style. Libraries such as Scikit-learn and TENSORFLOW (registered trademark) are used.

[0328] Proposal of the best fashion items

[0329] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[0330] Entering new data and emotion data

[0331] Users can input new information such as their latest physical data, preferences, emotional data, etc. The new data will be added to the system and used for the next analysis and prediction.

[0332] Specific examples

[0333] For example, if a user inputs new information such as "slim body type," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with bright colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[0334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0335] Step 1:

[0336] The server reads the customer's purchase history, favorite items, physical data, and style preferences from a CSV file. The input data is in CSV format, and the server converts it into a data frame using the pandas library and performs data preprocessing. Specifically, it complements missing data and corrects outliers.

[0337] Input: CSV file (purchase history, favorites, body data, style preferences)

[0338] Output: Preprocessed data frame

[0339] Step 2:

[0340] The server receives the user's emotional data sent from the device. The device analyzes the user's facial expressions and tone of voice in real time and generates emotional data using an emotion engine. The server stores this data and uses it for later analysis.

[0341] Input: Emotion data

[0342] Output: Stored emotion data

[0343] Step 3:

[0344] The server analyzes user characteristics based on the preprocessed customer data and emotion data. Here, characteristics are extracted based on the customer's body shape information, purchase history, preferences, and emotion data. The system is implemented using the pandas and numpy libraries.

[0345] Input: Preprocessed data frame, emotion data

[0346] Output: Analysis results (customer characteristics)

[0347] Step 4:

[0348] The server uses the analysis results to train a machine learning model, a random forest classifier implemented using the Scikit-learn library, which generates a model to predict the optimal style based on the customer's physical data, purchase history, and emotional data.

[0349] Input: Analysis results (customer characteristics)

[0350] Output: A trained machine learning model

[0351] Step 5:

[0352] The user can input new data through the terminal. The terminal provides an interface for inputting the user's new physical data, preferences, and emotional state. The input data is transmitted to the server in real time via AJAX.

[0353] Input: New user data (physical data, preferences, emotional state)

[0354] Output: New data sent to the server

[0355] Step 6:

[0356] The server receives new user data and stored emotion data, inputs them into the machine learning model, and performs style prediction. The prediction results are converted back to their original string form using LabelEncoder. Then, the suggestion results are optimized taking the emotion data into account.

[0357] Input: New user data, emotion data

[0358] Output: Optimized proposal results

[0359] Step 7:

[0360] The server then sends the optimized recommendations to the user's device, where the user can view the suggested fashion and makeup items. This allows users to easily find the fashion items that best suit them.

[0361] Input: Optimized proposal results

[0362] Output: The proposed results presented to the user

[0363] Examples of specific prompts include "slim figure," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy." Based on this information, the system can make suggestions that are appropriate for the user.

[0364] (Application example 2)

[0365] 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."

[0366] Conventional fashion and makeup product recommendation systems are based solely on a customer's purchasing history and style preferences, and do not take into account the customer's emotional state when selecting items. As a result, customer satisfaction is reduced and optimal product recommendations cannot be made. It is also difficult to respond quickly and accurately to individual customer needs.

[0367] The identification processing by the identification 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 recording a customer's past purchase history, favorite items, body data, style preferences, and emotional state, means for analyzing the customer's characteristics using the recorded data, means for recognizing the user's emotions using an emotion recognition engine, means for predicting the customer's style based on the analysis results using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and emotional data. This makes it possible to suggest optimal products taking the customer's emotional state into consideration, thereby improving customer satisfaction.

[0368] "Purchase history" is a record of products that a customer has purchased in the past.

[0369] "Favorite Items" is a list of products or items that a customer particularly likes.

[0370] "Physical data" refers to data such as a customer's body type, size, height, and weight.

[0371] "Style preferences" is information about the fashion and makeup styles that a customer prefers.

[0372] "Emotional state" is data that indicates the user's current mood or emotion (for example, joy or sadness).

[0373] An "emotion recognition engine" is a program or system that analyzes a user's facial expressions and tone of voice to recognize their emotions.

[0374] A "machine learning model" is an algorithm that uses data to predict customer behavior and preferences.

[0375] "Optimal fashion and makeup items" are fashion and makeup products that are recommended based on the customer's characteristics and emotional state.

[0376] A "server" is a computer system for recording, analyzing, processing, and storing data.

[0377] A "smartphone application" is a software program that runs on a smartphone and has the function of suggesting fashion and makeup items to customers.

[0378] This invention is a system that records a customer's past purchase history, favorite items, physical data, style preferences, and emotional state, and then suggests the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0379] System configuration

[0380] Recording customer and sentiment data

[0381] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also uses an emotion recognition engine to recognize the user's emotional state and saves this data in a CSV file or database. Specifically, the information entered by the user using their smartphone is sent to the server, which then records it in the database.

[0382] Customer and sentiment data analysis

[0383] The server analyzes each customer's characteristics using machine learning models based on the recorded customer data and emotional data. This includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. Machine learning models such as random forest classifiers are used.

[0384] Emotion recognition by emotion engine

[0385] The device is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The emotion recognition engine uses the EmotionEngine, a hypothetical library. The recognized emotion data is sent to a server for analysis.

[0386] Style prediction with machine learning

[0387] The server predicts a customer's style using a machine learning model that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[0388] Proposal of the best fashion items

[0389] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations based on the user's emotional state.

[0390] Entering new data and emotion data

[0391] Users input new information such as their latest physical data, preferences, and emotional data via their smartphones, allowing the system to continuously use the latest data for analysis and prediction.

[0392] Specific examples

[0393] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with brighter colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[0394] Prompt Sentence Examples

[0395] An example prompt for new data from the user might look something like this:

[0396] "Enter the user's physical and preference data, as well as their current emotional state. Example: 'Slim build, favorite color is blue, past purchase: T-shirts, current emotion: joy'"

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

[0398] Step 1:

[0399] The server records the customer's past purchase history, favorite items, physical data, style preferences, and emotional state. These data are stored in a CSV file or a database. As input, it uses the data submitted by the user, and as output, it gets the customer data recorded in a CSV file or a database.

[0400] Step 2:

[0401] The server analyzes the recorded customer data and emotion data. Specifically, it uses a machine learning model (e.g., a random forest classifier) ​​to extract customer characteristics. The customer data and emotion data stored in the database are used as input, and the customer style prediction result is obtained as output.

[0402] Step 3:

[0403] The device uses an emotion recognition engine to recognize the user's emotions. When the user points their face at the smartphone camera, the emotion recognition engine analyzes their facial expressions and tone of voice. The input is the user's facial image and voice data, and the output is recognized emotion data.

[0404] Step 4:

[0405] The device sends the recognized emotion data to the server. The emotion data sent from the device is used as input, and the server receives it and stores it in a database. The updated database is obtained as output.

[0406] Step 5:

[0407] The server initiates the process of predicting the customer's style using a machine learning model. The customer data and sentiment data stored in the database are used as input. The machine learning model runs the data and produces a predicted style as output.

[0408] Step 6:

[0409] The server then recommends the most suitable fashion and makeup items to the customer based on the prediction results and emotion data. The input is style data and emotion data predicted by the machine learning model. These data are combined for data processing, and the output is a list of the most suitable items.

[0410] Step 7:

[0411] The user uses a smartphone to input new data. The input form includes items such as physical data, preferences, emotional state, etc. The new information entered by the user is used as input, and the output is the new data that is sent to the server.

[0412] Step 8:

[0413] The terminal sends new data from the user to the server. As input, it uses the data entered into the terminal and sends it to the server. As output, the server receives the new data and adds it to the database.

[0414] Step 9:

[0415] The server uses the updated data to retrain the machine learning model for the next round of predictions and suggestions. The updated customer and sentiment data are used as input. The machine learning algorithm is retrained and the output is a predictive model with improved accuracy.

[0416] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0417] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (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.

[0418] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0419] [Second embodiment]

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

[0421] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0422] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0424] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0426] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 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.

[0427] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0428] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0429] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0430] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0431] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0432] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0433] System configuration

[0434] Recording customer data

[0435] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[0436] Customer data analysis

[0437] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[0438] Style prediction with machine learning

[0439] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[0440] Proposal of the best fashion items

[0441] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[0442] Entering New Data

[0443] Users can input their latest physical data, preferences, and other information. The new data is added to the system and used for the next analysis and prediction.

[0444] Program processing

[0445] Data loading and preprocessing

[0446] The server reads the customer's past purchase data, preferences, and body type information from a CSV file, etc. This data includes the customer's body type, favorite colors, past purchases, etc.

[0447] The server uses LabelEncoder to convert textual information into numbers, converting the data into a format that is easy for machine learning models to use. This preprocessing step ensures that the data is properly prepared.

[0448] Training the model

[0449] The server extracts input data (e.g., body type information, favorite colors, past purchases) and target data (customer style) from the data and trains a machine learning model, which generates a model that predicts style based on the customer's data.

[0450] Entering and Processing New Data

[0451] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[0452] The server takes this new data and feeds it into a machine learning model to make predictions.

[0453] Presentation of results

[0454] The server uses a machine learning model to convert the predicted style into a format that humans can understand and suggests the most suitable fashion items to the user.

[0455] The terminal displays the recommendation results received from the server to the user, allowing the user to easily find the item that best suits them.

[0456] Specific examples

[0457] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the device displays the results to the user.

[0458] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[0459] The processing flow will be explained below.

[0460] Step 1:

[0461] The server reads data from the customer_data.csv file, which contains customer purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using the Python pandas library.

[0462] Step 2:

[0463] The server uses LabelEncoder to convert the customer's style information into a numerical value, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for the machine learning model to process.

[0464] Step 3:

[0465] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y). Specifically, it executes X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[0466] Step 4:

[0467] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[0468] Step 5:

[0469] The user inputs new data (body type, favorite colors, past purchases, etc.) This data is collected through the terminal and sent to the server.

[0470] Step 6:

[0471] The terminal converts the new customer data you enter into a DataFrame format. Specifically, it creates the data as follows:

[0472] python

[0473] new_customer_data = pd.DataFrame({

[0474] 'customer_id': [1],

[0475] 'body_type': ['slim'],

[0476] 'fav_colors': ['blue'],

[0477] 'past_purchases': ['T-shirt']

[0478] })

[0479] Step 7:

[0480] The server receives new customer data and passes it to a pre-trained machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases']] and executes model.predict(customer_X) to get the prediction style.

[0481] Step 8:

[0482] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[0483] Step 9:

[0484] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[0485] python

[0486] print(recommendations)

[0487] Step 10:

[0488] The terminal displays the recommended styles received from the server to the user, allowing the user to check the fashion items that best suit them.

[0489] The above are the specific processing steps in this system.

[0490] Example 1

[0491] 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."

[0492] Conventional systems for suggesting fashion and makeup items have been unable to fully reflect the individual characteristics and preferences of customers, resulting in low customer satisfaction. Furthermore, data entry is cumbersome, making them impractical. To address these issues, a system is needed that can efficiently analyze diverse customer information and quickly suggest the best items for each individual customer.

[0493] 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.

[0494] In this invention, the server includes: means for recording a customer's past purchase history, favorite items, physical data, and style preferences; means for analyzing the customer's characteristics using the recorded data; means for training a machine learning model using the analysis results to predict the customer's style; means for suggesting optimal fashion and makeup items to the customer based on the prediction results of the machine learning model; means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer; and means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer.

[0495] "Customer's past purchase history" refers to a record of products and services previously purchased by a customer, including, for example, the date and time of purchase, the name, quantity, and price of the purchased items.

[0496] "Favorite Items" is a list of products or services that a customer particularly likes, including items that the customer purchases frequently and items of special interest.

[0497] "Physical Data" refers to data about a customer's body shape and physical characteristics, including, for example, height, weight, body fat percentage, and waist circumference.

[0498] "Style preferences" refers to data about a customer's preferred fashion and makeup styles, including their preferred clothing colors and designs, and favorite brands.

[0499] "Means of Recording" refers to the method or system for storing customer data, including, for example, means for storing data in the form of a database or a CSV file.

[0500] "Means for analyzing characteristics" refers to methods or systems for extracting and analyzing customer characteristics based on recorded data, including, for example, data analysis software and algorithms.

[0501] A "machine learning model" is an algorithm or program that can learn from data and make predictions or classifications. Examples include models such as random forests and neural networks.

[0502] "Training means" refers to a method or system for effectively training a machine learning model, including, for example, means for splitting a dataset and tuning model parameters.

[0503] "Means for suggesting" refers to methods or systems that present suitable products or services to customers based on analysis and prediction results. Examples include recommendation systems and notification functions.

[0504] "Information input methods" are the methods or interfaces that allow customers to enter new data into a system. Examples include input fields on web forms or mobile apps.

[0505] "Means for processing input information" refers to methods or systems that analyze new data acquired from customers and convert it into an appropriate format. For example, this may include data pre-processing algorithms.

[0506] The "means for displaying the recommendation results" refers to a method or system for visually displaying the recommendation results from the server to the user. For example, this includes the display screen of a web page or a mobile app.

[0507] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with each element of the server, terminal, and user.

[0508] System configuration

[0509] Recording customer data

[0510] The server records the customer's past purchase history, favorite items, physical data, and style preferences. This includes the ability to save the customer's purchase and physical data to a CSV file or database. For example, the data can be read from a CSV file using the Python pandas library.

[0511] Customer data analysis

[0512] The server analyzes customer characteristics based on the recorded data. Specifically, data analysis software and algorithms are used to extract characteristics based on the customer's body type, preferences, and past purchase history. Data frame manipulation using pandas and preprocessing techniques using sklearn are used here.

[0513] Style prediction using machine learning models

[0514] The server uses a machine learning model to predict the customer's style. This model can be a random forest or a neural network. Specifically, the server can use the random forest classifier from the sklearn library. The model is trained by splitting the dataset and adjusting parameters.

[0515] Proposal of the best fashion items

[0516] The server then uses the predictions made by the machine learning model to suggest the best fashion and makeup items for each customer, for example by retrieving items from a database that are suitable for a specific style and generating a specific product list.

[0517] Entering New Data

[0518] The device provides an interface through which users can input new data, including their current physical data and preferences. The input data is sent in real time to a server for analysis.

[0519] Program processing

[0520] The server reads the customer data, converts the text information into numbers using LabelEncoder, and standardizes them. The preprocessed data is then used to train machine learning models.

[0521] Next, when the user inputs new data using the device, the data is sent to the server. The server preprocesses this new data and inputs it into the machine learning model to make predictions. Finally, the server generates item suggestions based on the prediction results and sends them to the device. The device then displays the suggestions to the user, providing them with the most suitable fashion items.

[0522] Specific examples

[0523] For example, if a user enters information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and processes it using LabelEncoder and StandardScaler. Next, a machine learning model is used to predict "casual style," and based on the results, suggestions such as "blue T-shirts" and "denim jackets" are made. These suggestions are then displayed on the device, allowing the user to easily find the items that best suit them.

[0524] Prompt Sentence Examples

[0525] Body type: Slim

[0526] Favorite color: Blue

[0527] Previous purchase: T-shirt

[0528] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[0529] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0530] Step 1:

[0531] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or a database. Specifically, it uses the pandas library to read the data with the pandas.read_csv() method, which results in the customer data in a data frame format.

[0532] Input: CSV file containing customer data

[0533] Output: Customer data in dataframe format

[0534] Step 2:

[0535] The server performs preprocessing on the loaded data, which includes converting categorical data to numeric values ​​using LabelEncoder, and then normalizing the data using StandardScaler.

[0536] Input: Customer data in dataframe format

[0537] Output: Customer data converted to numbers and normalized

[0538] Step 3:

[0539] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the data into a training set and a test set and trains the model using a random forest classifier. This step uses train_test_split and RandomForestClassifier.

[0540] Input: Customer data converted to numbers and normalized

[0541] Output: A trained machine learning model

[0542] Step 4:

[0543] The terminal provides an interface through which the user can input new data, such as body type information, favorite colors, past purchases, etc. This allows the user's latest data to be collected.

[0544] Input: User's new body type, favorite colors, past purchases

[0545] Output: The user's new data

[0546] Step 5:

[0547] The device sends new data entered by the user to the server using an HTTP request. The server receives this data and performs preprocessing. Again, it uses LabelEncoder and StandardScaler to convert the new data into a format suitable for the machine learning model.

[0548] Input: User's new data

[0549] Output: Preprocessed new user data

[0550] Step 6:

[0551] The server inputs the preprocessed new user data into the machine learning model and makes predictions. Specifically, it uses the new data to predict style and selects the most suitable fashion items based on that prediction.

[0552] Input: Preprocessed new user data

[0553] Output: Predicted style and suggested fashion items based on it

[0554] Step 7:

[0555] The server converts the prediction results into a human-understandable format and suggests the most suitable fashion and makeup items for the user, for example, "For a casual style, a blue T-shirt and denim jacket."

[0556] Input: predicted style

[0557] Output: Human-understandable fashion and makeup item suggestions

[0558] Step 8:

[0559] The device displays the proposed results received from the server to the user. Specifically, the proposed items are displayed in list format on a web page or mobile app screen so that the user can easily check them.

[0560] Input: Fashion and makeup suggestions

[0561] Output: The suggestions displayed to the user

[0562] As described above, the entire system functions in concert based on the specific operations performed at each processing step and their inputs and outputs. This series of processes allows users to efficiently find the fashion and makeup items that are best suited to them.

[0563] (Application example 1)

[0564] 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."

[0565] In recent years, there has been a demand for personalized recommendations of fashion and makeup items for customers with diverse needs. However, conventional systems have had difficulty in making recommendations that fully reflect the characteristics of each customer, making it difficult to recommend appropriate items. Furthermore, the difficulty of making recommendations in real time has limited the improvement of customer experience in physical stores.

[0566] 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.

[0567] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for analyzing the customer's characteristics using the recorded data, means for proposing optimal fashion and makeup items to the customer based on the analysis results, means for providing an interface through which the customer can input new data, means for predicting and proposing a style in real time based on the input data, and means for displaying the predicted style to the customer using a smartphone. This makes it possible to reflect the customer's individual characteristics in real time and propose optimal fashion and makeup items.

[0568] "Customer's past purchase history" refers to data on products and services that a customer has purchased in the past.

[0569] "Favorite items" refers to data on products and services that customers particularly like to purchase or use.

[0570] "Physical data" refers to information about a customer's physical characteristics, such as height, weight, and body type.

[0571] "Style preferences" refers to information about the trends and tastes of fashion and makeup that a customer particularly likes.

[0572] "Customer characteristics" are individual characteristics of a customer extracted based on the customer's purchasing history, favorite items, physical data, and style preferences.

[0573] A "machine learning model" is an algorithm that learns patterns in data and makes predictions or classifications based on new data.

[0574] A "smartphone" is a type of mobile phone, a device that has multi-functional computing capabilities and is capable of running a variety of applications.

[0575] An "interface" is the means by which a user inputs data into or receives information from a system.

[0576] "Real time" refers to a time period in which data is input and processed immediately, and the results are immediately available.

[0577] "Prediction" is the use of machine learning models to estimate future outcomes or trends based on given data.

[0578] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0579] System configuration

[0580] Recording customer data

[0581] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[0582] Customer data analysis

[0583] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[0584] Style prediction with machine learning

[0585] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[0586] Proposal of the best fashion items

[0587] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[0588] Entering New Data

[0589] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[0590] Real-time predictions and suggestions

[0591] The server receives this new data, feeds it into machine learning models, and makes real-time predictions, which are then displayed to the user via their smartphone, where they can view suggested styles and products.

[0592] Specific examples

[0593] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the smartphone device displays the results to the user.

[0594] Prompt Sentence Examples

[0595] Enter the new user data in the following format:

[0596] Build: Slim

[0597] Favorite color: Blue

[0598] Previously purchased item: T-shirt

[0599] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0600] Step 1:

[0601] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or database.

[0602] Input: CSV file or database

[0603] Output: A list of customer data

[0604] The server uses database access and file I / O operations to retrieve customer history and preference data and store it in list format.

[0605] Step 2:

[0606] The server preprocesses the data and converts it into a format that can be used by the machine learning model, for example, converting text information about a customer's favorite colors and styles into numbers.

[0607] Input: List of customer data

[0608] Output: Preprocessed data frame

[0609] The server uses LabelEncoder to convert the character data into numerical data, making it easier for the machine learning model to process.

[0610] Step 3:

[0611] The server uses the preprocessed data to train a machine learning model, such as a random forest classifier.

[0612] Input: preprocessed data frame, style labels

[0613] Output: A trained machine learning model

[0614] The server separates the features and target variables and applies machine learning algorithms to train the model.

[0615] Step 4:

[0616] The terminal provides an interface for the user to enter new data, such as body measurements, favorite colors, and past purchase history.

[0617] Input: New data for the user

[0618] Output: A JSON object of the user-entered data

[0619] The user enters information according to the provided format, and the terminal converts it into JSON format and sends it to the server.

[0620] Step 5:

[0621] The server receives new data entered by the user, pre-processes it, and then feeds it into a trained machine learning model.

[0622] Input: A JSON object of new data entered by the user.

[0623] Output: Predicted style labels

[0624] The server preprocesses the new data and runs style predictions against the machine learning model.

[0625] Step 6:

[0626] The server suggests optimal fashion and makeup items to the user based on the predicted style.

[0627] Input: Predicted style labels

[0628] Output: A list of the best fashion and makeup items

[0629] The server selects suggested items based on the style prediction results and generates a list of them.

[0630] Step 7:

[0631] The terminal displays the suggested fashion and makeup items to the user.

[0632] Enter: a list of the best fashion and makeup items.

[0633] Output: Recommended items displayed to the user

[0634] The terminal displays the item list received from the server on a user interface, allowing the user to view these suggestions.

[0635] Each of the above steps makes it possible to reflect the individual characteristics of each customer in real time and suggest the most suitable fashion and makeup items.

[0636] 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.

[0637] The present invention provides a system that combines a customer's past purchase history, favorite items, physical data, style preferences, and an emotion engine that recognizes the user's emotions to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with the server, terminal, and user elements.

[0638] System configuration

[0639] Recording customer and sentiment data

[0640] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This record is saved in a CSV file or database.

[0641] Customer and sentiment data analysis

[0642] The server uses the recorded customer data and emotional data to analyze the characteristics of each customer, including extracting characteristics based on the customer's body type information, preferences, past purchase history, and emotional data.

[0643] Emotion recognition by emotion engine

[0644] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The recognized emotion data is sent to the server.

[0645] Style prediction with machine learning

[0646] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier) ​​that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[0647] Proposal of the best fashion items

[0648] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[0649] Entering new data and emotion data

[0650] Users can input new information, such as their latest physical data, preferences, and emotional data. The new data is added to the system and used for the next analysis and prediction.

[0651] Program processing

[0652] Data loading and preprocessing

[0653] The server reads the customer's past purchase data, preferences, body type information, and emotional data from CSV files, etc. This data includes the customer's body type information, favorite colors, past purchases, emotional state, etc.

[0654] Training a machine learning model

[0655] The server extracts input data (e.g., body type information, favorite colors, past purchases, emotional data) and target data (customer style) from the data, and trains a machine learning model to generate a style prediction model based on the customer data.

[0656] Entering new data and emotion data

[0657] The terminal provides an interface where the user can input new data (body type, favorite color, past purchases, emotional data, etc.) The input data is sent to the server.

[0658] Emotion recognition and data processing

[0659] The terminal receives the user's new data and uses the emotion engine to obtain emotion data, which is then sent to the server.

[0660] Proposal Generation

[0661] The server receives new customer data and sentiment data, inputs it into a machine learning model, and generates predictions, which are optimized to take the sentiment data into account.

[0662] The server uses LabelEncoder to reconvert the predicted numeric style into its original format (string) and provides it as a suggested result.

[0663] Specific examples

[0664] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model.

[0665] Additionally, when the emotion engine detects the user's emotion of joy, the server has the function of suggesting items with brighter colors and fun designs, allowing users to easily find fashion items that best suit them and match their current emotions.

[0666] As described above, the present invention provides a system that can quickly and accurately respond to the diverse needs and emotional states of customers and suggest optimal fashion and makeup items.

[0667] The processing flow will be explained below.

[0668] Step 1:

[0669] The server reads data from the customer_data.csv file, which contains the customer's past purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using Python's pandas library.

[0670] Step 2:

[0671] The server uses LabelEncoder to convert the customer's style information into a number, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for machine learning models to use.

[0672] Step 3:

[0673] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y), specifically, X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[0674] Step 4:

[0675] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[0676] Step 5:

[0677] Users input emotional data (e.g., facial expressions and tone of voice) along with new data (body type, favorite colors, past purchases, etc.), which is collected via the device and sent to the server.

[0678] Step 6:

[0679] The terminal converts the new customer data and emotion data into DataFrame format. Specifically, it creates the data as follows:

[0680] python

[0681] new_customer_data = pd.DataFrame({

[0682] 'customer_id': [1],

[0683] 'body_type': ['slim'],

[0684] 'fav_colors': ['blue'],

[0685] 'past_purchases': ['T-shirt'],

[0686] 'emotion': ['happy']

[0687] })

[0688] Step 7:

[0689] The server receives new customer data and passes it to the machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases', 'emotion']] and executes model.predict(customer_X) to get the prediction style.

[0690] Step 8:

[0691] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[0692] Step 9:

[0693] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[0694] python

[0695] print(recommendations)

[0696] Step 10:

[0697] The device displays the recommended styles received from the server to the user, allowing the user to see which fashion items are best suited to them. For example, if the server detects the emotion of joy, it will suggest items with bright colors and fun designs.

[0698] The above are the specific processing steps in this system.

[0699] Example 2

[0700] 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."

[0701] While conventional fashion recommendation systems take into account a customer's past purchasing history and style preferences, they are unable to make recommendations that take into account the customer's emotional state. This makes it difficult to make optimal recommendations that match the customer's current emotions. Furthermore, new data cannot be input in real time, making it impossible to always make predictions based on the latest customer data.

[0702] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0703] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for recording emotional data using an emotion engine that recognizes user emotions, means for analyzing customer characteristics using the recorded data, means for predicting the customer's style using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and the emotional data, thereby enabling optimal suggestions that take into account the customer's emotional state and new data in real time.

[0704] "Customer's past purchasing history" refers to a record of the products and services that a customer has purchased in the past.

[0705] "Favorite Items" is a list of products and services that a customer particularly likes.

[0706] "Physical data" refers to information about a customer's physical characteristics and measurements, such as height, weight, and body type.

[0707] "Style preferences" refers to information about the customer's preferred fashion and design characteristics, such as color, material, and design pattern.

[0708] An "emotion engine" is software or hardware for recognizing and analyzing a user's emotions.

[0709] "Emotion data" is data on the user's emotional state as recognized by the emotion engine.

[0710] A "machine learning model" is an algorithm or model that learns from data and makes predictions or classifications.

[0711] "Style prediction" refers to predicting the best fashion and makeup items based on customer data.

[0712] "Preprocessing" is the process of preparing raw data in a form suitable for analysis and learning.

[0713] "Real-time" refers to processing and analysis occurring close to the moment the data is generated.

[0714] The "suggestion results" are a list of fashion and makeup items that the system recommends to the customer.

[0715] The present invention is a system that collects a customer's past purchase history, favorite items, physical data, style preferences, and emotional data, and uses machine learning models to suggest optimal fashion and makeup items for each customer. This system operates in cooperation with the elements of a server, terminals, and users.

[0716] Recording customer and sentiment data

[0717] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This data is saved in a CSV file or database. Programming languages ​​such as Python and R are used as the software to implement the system.

[0718] Customer and sentiment data analysis

[0719] The server uses the recorded customer data and emotional data to analyze each customer's characteristics. This analysis includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. The data analysis uses the pandas and numpy libraries.

[0720] Emotion recognition by emotion engine

[0721] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and tone of voice. The recognized emotion data is sent to the server. Tools such as OpenCV and OpenSmile are used for emotion recognition.

[0722] Style prediction with machine learning

[0723] The server predicts a customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style. Libraries such as Scikit-learn and TensorFlow are used.

[0724] Proposal of the best fashion items

[0725] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[0726] Entering new data and emotion data

[0727] Users can input new information such as their latest physical data, preferences, emotional data, etc. The new data will be added to the system and used for the next analysis and prediction.

[0728] Specific examples

[0729] For example, if a user inputs new information such as "slim body type," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with bright colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[0730] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0731] Step 1:

[0732] The server reads the customer's purchase history, favorite items, physical data, and style preferences from a CSV file. The input data is in CSV format, and the server converts it into a data frame using the pandas library and performs data preprocessing. Specifically, it complements missing data and corrects outliers.

[0733] Input: CSV file (purchase history, favorites, body data, style preferences)

[0734] Output: Preprocessed data frame

[0735] Step 2:

[0736] The server receives the user's emotional data sent from the device. The device analyzes the user's facial expressions and tone of voice in real time and generates emotional data using an emotion engine. The server stores this data and uses it for later analysis.

[0737] Input: Emotion data

[0738] Output: Stored emotion data

[0739] Step 3:

[0740] The server analyzes user characteristics based on the preprocessed customer data and emotion data. Here, characteristics are extracted based on the customer's body shape information, purchase history, preferences, and emotion data. The system is implemented using the pandas and numpy libraries.

[0741] Input: Preprocessed data frame, emotion data

[0742] Output: Analysis results (customer characteristics)

[0743] Step 4:

[0744] The server uses the analysis results to train a machine learning model, a random forest classifier implemented using the Scikit-learn library, which generates a model to predict the optimal style based on the customer's physical data, purchase history, and emotional data.

[0745] Input: Analysis results (customer characteristics)

[0746] Output: A trained machine learning model

[0747] Step 5:

[0748] The user can input new data through the terminal. The terminal provides an interface for inputting the user's new physical data, preferences, and emotional state. The input data is transmitted to the server in real time via AJAX.

[0749] Input: New user data (physical data, preferences, emotional state)

[0750] Output: New data sent to the server

[0751] Step 6:

[0752] The server receives new user data and stored emotion data, inputs them into the machine learning model, and performs style prediction. The prediction results are converted back to their original string form using LabelEncoder. Then, the suggestion results are optimized taking the emotion data into account.

[0753] Input: New user data, emotion data

[0754] Output: Optimized proposal results

[0755] Step 7:

[0756] The server then sends the optimized recommendations to the user's device, where the user can view the suggested fashion and makeup items. This allows users to easily find the fashion items that best suit them.

[0757] Input: Optimized proposal results

[0758] Output: The proposed results presented to the user

[0759] Examples of specific prompts include "slim figure," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy." Based on this information, the system can make suggestions that are appropriate for the user.

[0760] (Application example 2)

[0761] 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."

[0762] Conventional fashion and makeup product recommendation systems are based solely on a customer's purchasing history and style preferences, and do not take into account the customer's emotional state when selecting items. As a result, customer satisfaction is reduced and optimal product recommendations cannot be made. It is also difficult to respond quickly and accurately to individual customer needs.

[0763] The identification processing by the identification 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 recording a customer's past purchase history, favorite items, body data, style preferences, and emotional state, means for analyzing the customer's characteristics using the recorded data, means for recognizing the user's emotions using an emotion recognition engine, means for predicting the customer's style based on the analysis results using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and emotional data. This makes it possible to suggest optimal products taking the customer's emotional state into consideration, thereby improving customer satisfaction.

[0764] "Purchase history" is a record of products that a customer has purchased in the past.

[0765] "Favorite Items" is a list of products or items that a customer particularly likes.

[0766] "Physical data" refers to data such as a customer's body type, size, height, and weight.

[0767] "Style preferences" is information about the fashion and makeup styles that a customer prefers.

[0768] "Emotional state" is data that indicates the user's current mood or emotion (for example, joy or sadness).

[0769] An "emotion recognition engine" is a program or system that analyzes a user's facial expressions and tone of voice to recognize their emotions.

[0770] A "machine learning model" is an algorithm that uses data to predict customer behavior and preferences.

[0771] "Optimal fashion and makeup items" are fashion and makeup products that are recommended based on the customer's characteristics and emotional state.

[0772] A "server" is a computer system for recording, analyzing, processing, and storing data.

[0773] A "smartphone application" is a software program that runs on a smartphone and has the function of suggesting fashion and makeup items to customers.

[0774] This invention is a system that records a customer's past purchase history, favorite items, physical data, style preferences, and emotional state, and then suggests the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0775] System configuration

[0776] Recording customer and sentiment data

[0777] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also uses an emotion recognition engine to recognize the user's emotional state and saves this data in a CSV file or database. Specifically, the information entered by the user using their smartphone is sent to the server, which then records it in the database.

[0778] Customer and sentiment data analysis

[0779] The server analyzes each customer's characteristics using machine learning models based on the recorded customer data and emotional data. This includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. Machine learning models such as random forest classifiers are used.

[0780] Emotion recognition by emotion engine

[0781] The device is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The emotion recognition engine uses the EmotionEngine, a hypothetical library. The recognized emotion data is sent to a server for analysis.

[0782] Style prediction with machine learning

[0783] The server predicts a customer's style using a machine learning model that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[0784] Proposal of the best fashion items

[0785] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations based on the user's emotional state.

[0786] Entering new data and emotion data

[0787] Users input new information such as their latest physical data, preferences, and emotional data via their smartphones, allowing the system to continuously use the latest data for analysis and prediction.

[0788] Specific examples

[0789] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with brighter colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[0790] Prompt Sentence Examples

[0791] An example prompt for new data from the user might look something like this:

[0792] "Enter the user's physical and preference data, as well as their current emotional state. Example: 'Slim build, favorite color is blue, past purchase: T-shirts, current emotion: joy'"

[0793] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0794] Step 1:

[0795] The server records the customer's past purchase history, favorite items, physical data, style preferences, and emotional state. These data are stored in a CSV file or a database. As input, it uses the data submitted by the user, and as output, it gets the customer data recorded in a CSV file or a database.

[0796] Step 2:

[0797] The server analyzes the recorded customer data and emotion data. Specifically, it uses a machine learning model (e.g., a random forest classifier) ​​to extract customer characteristics. The customer data and emotion data stored in the database are used as input, and the customer style prediction result is obtained as output.

[0798] Step 3:

[0799] The device uses an emotion recognition engine to recognize the user's emotions. When the user points their face at the smartphone camera, the emotion recognition engine analyzes their facial expressions and tone of voice. The input is the user's facial image and voice data, and the output is recognized emotion data.

[0800] Step 4:

[0801] The device sends the recognized emotion data to the server. The emotion data sent from the device is used as input, and the server receives it and stores it in a database. The updated database is obtained as output.

[0802] Step 5:

[0803] The server initiates the process of predicting the customer's style using a machine learning model. The customer data and sentiment data stored in the database are used as input. The machine learning model runs the data and produces a predicted style as output.

[0804] Step 6:

[0805] The server then recommends the most suitable fashion and makeup items to the customer based on the prediction results and emotion data. The input is style data and emotion data predicted by the machine learning model. These data are combined for data processing, and the output is a list of the most suitable items.

[0806] Step 7:

[0807] The user uses a smartphone to input new data. The input form includes items such as physical data, preferences, emotional state, etc. The new information entered by the user is used as input, and the output is the new data that is sent to the server.

[0808] Step 8:

[0809] The terminal sends new data from the user to the server. As input, it uses the data entered into the terminal and sends it to the server. As output, the server receives the new data and adds it to the database.

[0810] Step 9:

[0811] The server uses the updated data to retrain the machine learning model for the next round of predictions and suggestions. The updated customer and sentiment data are used as input. The machine learning algorithm is retrained and the output is a predictive model with improved accuracy.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] [Third embodiment]

[0816] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0817] 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.

[0818] 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).

[0819] 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.

[0820] 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.

[0821] 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).

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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."

[0828] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0829] System configuration

[0830] Recording customer data

[0831] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[0832] Customer data analysis

[0833] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[0834] Style prediction with machine learning

[0835] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[0836] Proposal of the best fashion items

[0837] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[0838] Entering New Data

[0839] Users can input their latest physical data, preferences, and other information. The new data is added to the system and used for the next analysis and prediction.

[0840] Program processing

[0841] Data loading and preprocessing

[0842] The server reads the customer's past purchase data, preferences, and body type information from a CSV file, etc. This data includes the customer's body type, favorite colors, past purchases, etc.

[0843] The server uses LabelEncoder to convert textual information into numbers, converting the data into a format that is easy for machine learning models to use. This preprocessing step ensures that the data is properly prepared.

[0844] Training the model

[0845] The server extracts input data (e.g., body type information, favorite colors, past purchases) and target data (customer style) from the data and trains a machine learning model, which generates a model that predicts style based on the customer's data.

[0846] Entering and Processing New Data

[0847] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[0848] The server takes this new data and feeds it into a machine learning model to make predictions.

[0849] Presentation of results

[0850] The server uses a machine learning model to convert the predicted style into a format that humans can understand and suggests the most suitable fashion items to the user.

[0851] The terminal displays the recommendation results received from the server to the user, allowing the user to easily find the item that best suits them.

[0852] Specific examples

[0853] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the device displays the results to the user.

[0854] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[0855] The processing flow will be explained below.

[0856] Step 1:

[0857] The server reads data from the customer_data.csv file, which contains customer purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using the Python pandas library.

[0858] Step 2:

[0859] The server uses LabelEncoder to convert the customer's style information into a numerical value, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for the machine learning model to process.

[0860] Step 3:

[0861] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y). Specifically, it executes X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[0862] Step 4:

[0863] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[0864] Step 5:

[0865] The user inputs new data (body type, favorite colors, past purchases, etc.) This data is collected through the terminal and sent to the server.

[0866] Step 6:

[0867] The terminal converts the new customer data you enter into a DataFrame format. Specifically, it creates the data as follows:

[0868] python

[0869] new_customer_data = pd.DataFrame({

[0870] 'customer_id': [1],

[0871] 'body_type': ['slim'],

[0872] 'fav_colors': ['blue'],

[0873] 'past_purchases': ['T-shirt']

[0874] })

[0875] Step 7:

[0876] The server receives new customer data and passes it to a pre-trained machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases']] and executes model.predict(customer_X) to get the prediction style.

[0877] Step 8:

[0878] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[0879] Step 9:

[0880] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[0881] python

[0882] print(recommendations)

[0883] Step 10:

[0884] The terminal displays the recommended styles received from the server to the user, allowing the user to check the fashion items that best suit them.

[0885] The above are the specific processing steps in this system.

[0886] Example 1

[0887] 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."

[0888] Conventional systems for suggesting fashion and makeup items have been unable to fully reflect the individual characteristics and preferences of customers, resulting in low customer satisfaction. Furthermore, data entry is cumbersome, making them impractical. To address these issues, a system is needed that can efficiently analyze diverse customer information and quickly suggest the best items for each individual customer.

[0889] 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.

[0890] In this invention, the server includes: means for recording a customer's past purchase history, favorite items, physical data, and style preferences; means for analyzing the customer's characteristics using the recorded data; means for training a machine learning model using the analysis results to predict the customer's style; means for suggesting optimal fashion and makeup items to the customer based on the prediction results of the machine learning model; means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer; and means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer.

[0891] "Customer's past purchase history" refers to a record of products and services previously purchased by a customer, including, for example, the date and time of purchase, the name, quantity, and price of the purchased items.

[0892] "Favorite Items" is a list of products or services that a customer particularly likes, including items that the customer purchases frequently and items of special interest.

[0893] "Physical Data" refers to data about a customer's body shape and physical characteristics, including, for example, height, weight, body fat percentage, and waist circumference.

[0894] "Style preferences" refers to data about a customer's preferred fashion and makeup styles, including their preferred clothing colors and designs, and favorite brands.

[0895] "Means of Recording" refers to the method or system for storing customer data, including, for example, means for storing data in the form of a database or a CSV file.

[0896] "Means for analyzing characteristics" refers to methods or systems for extracting and analyzing customer characteristics based on recorded data, including, for example, data analysis software and algorithms.

[0897] A "machine learning model" is an algorithm or program that can learn from data and make predictions or classifications. Examples include models such as random forests and neural networks.

[0898] "Training means" refers to a method or system for effectively training a machine learning model, including, for example, means for splitting a dataset and tuning model parameters.

[0899] "Means for suggesting" refers to methods or systems that present suitable products or services to customers based on analysis and prediction results. Examples include recommendation systems and notification functions.

[0900] "Information input methods" are the methods or interfaces that allow customers to enter new data into a system. Examples include input fields on web forms or mobile apps.

[0901] "Means for processing input information" refers to methods or systems that analyze new data acquired from customers and convert it into an appropriate format. For example, this may include data pre-processing algorithms.

[0902] The "means for displaying the recommendation results" refers to a method or system for visually displaying the recommendation results from the server to the user. For example, this includes the display screen of a web page or a mobile app.

[0903] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with each element of the server, terminal, and user.

[0904] System configuration

[0905] Recording customer data

[0906] The server records the customer's past purchase history, favorite items, physical data, and style preferences. This includes the ability to save the customer's purchase and physical data to a CSV file or database. For example, the data can be read from a CSV file using the Python pandas library.

[0907] Customer data analysis

[0908] The server analyzes customer characteristics based on the recorded data. Specifically, data analysis software and algorithms are used to extract characteristics based on the customer's body type, preferences, and past purchase history. Data frame manipulation using pandas and preprocessing techniques using sklearn are used here.

[0909] Style prediction using machine learning models

[0910] The server uses a machine learning model to predict the customer's style. This model can be a random forest or a neural network. Specifically, the server can use the random forest classifier from the sklearn library. The model is trained by splitting the dataset and adjusting parameters.

[0911] Proposal of the best fashion items

[0912] The server then uses the predictions made by the machine learning model to suggest the best fashion and makeup items for each customer, for example by retrieving items from a database that are suitable for a specific style and generating a specific product list.

[0913] Entering New Data

[0914] The device provides an interface through which users can input new data, including their current physical data and preferences. The input data is sent in real time to a server for analysis.

[0915] Program processing

[0916] The server reads the customer data, converts the text information into numbers using LabelEncoder, and standardizes them. The preprocessed data is then used to train machine learning models.

[0917] Next, when the user inputs new data using the device, the data is sent to the server. The server preprocesses this new data and inputs it into the machine learning model to make predictions. Finally, the server generates item suggestions based on the prediction results and sends them to the device. The device then displays the suggestions to the user, providing them with the most suitable fashion items.

[0918] Specific examples

[0919] For example, if a user enters information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and processes it using LabelEncoder and StandardScaler. Next, a machine learning model is used to predict "casual style," and based on the results, suggestions such as "blue T-shirts" and "denim jackets" are made. These suggestions are then displayed on the device, allowing the user to easily find the items that best suit them.

[0920] Prompt Sentence Examples

[0921] Body type: Slim

[0922] Favorite color: Blue

[0923] Previous purchase: T-shirt

[0924] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[0925] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0926] Step 1:

[0927] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or a database. Specifically, it uses the pandas library to read the data with the pandas.read_csv() method, which results in the customer data in a data frame format.

[0928] Input: CSV file containing customer data

[0929] Output: Customer data in dataframe format

[0930] Step 2:

[0931] The server performs preprocessing on the loaded data, which includes converting categorical data to numeric values ​​using LabelEncoder, and then normalizing the data using StandardScaler.

[0932] Input: Customer data in dataframe format

[0933] Output: Customer data converted to numbers and normalized

[0934] Step 3:

[0935] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the data into a training set and a test set and trains the model using a random forest classifier. This step uses train_test_split and RandomForestClassifier.

[0936] Input: Customer data converted to numbers and normalized

[0937] Output: A trained machine learning model

[0938] Step 4:

[0939] The terminal provides an interface through which the user can input new data, such as body type information, favorite colors, past purchases, etc. This allows the user's latest data to be collected.

[0940] Input: User's new body type, favorite colors, past purchases

[0941] Output: The user's new data

[0942] Step 5:

[0943] The device sends new data entered by the user to the server using an HTTP request. The server receives this data and performs preprocessing. Again, it uses LabelEncoder and StandardScaler to convert the new data into a format suitable for the machine learning model.

[0944] Input: User's new data

[0945] Output: Preprocessed new user data

[0946] Step 6:

[0947] The server inputs the preprocessed new user data into the machine learning model and makes predictions. Specifically, it uses the new data to predict style and selects the most suitable fashion items based on that prediction.

[0948] Input: Preprocessed new user data

[0949] Output: Predicted style and suggested fashion items based on it

[0950] Step 7:

[0951] The server converts the prediction results into a human-understandable format and suggests the most suitable fashion and makeup items for the user, for example, "For a casual style, a blue T-shirt and denim jacket."

[0952] Input: predicted style

[0953] Output: Human-understandable fashion and makeup item suggestions

[0954] Step 8:

[0955] The device displays the proposed results received from the server to the user. Specifically, the proposed items are displayed in list format on a web page or mobile app screen so that the user can easily check them.

[0956] Input: Fashion and makeup suggestions

[0957] Output: The suggestions displayed to the user

[0958] As described above, the entire system functions in concert based on the specific operations performed at each processing step and their inputs and outputs. This series of processes allows users to efficiently find the fashion and makeup items that are best suited to them.

[0959] (Application example 1)

[0960] 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."

[0961] In recent years, there has been a demand for personalized recommendations of fashion and makeup items for customers with diverse needs. However, conventional systems have had difficulty in making recommendations that fully reflect the characteristics of each customer, making it difficult to recommend appropriate items. Furthermore, the difficulty of making recommendations in real time has limited the improvement of customer experience in physical stores.

[0962] 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.

[0963] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for analyzing the customer's characteristics using the recorded data, means for proposing optimal fashion and makeup items to the customer based on the analysis results, means for providing an interface through which the customer can input new data, means for predicting and proposing a style in real time based on the input data, and means for displaying the predicted style to the customer using a smartphone. This makes it possible to reflect the customer's individual characteristics in real time and propose optimal fashion and makeup items.

[0964] "Customer's past purchase history" refers to data on products and services that a customer has purchased in the past.

[0965] "Favorite items" refers to data on products and services that customers particularly like to purchase or use.

[0966] "Physical data" refers to information about a customer's physical characteristics, such as height, weight, and body type.

[0967] "Style preferences" refers to information about the trends and tastes of fashion and makeup that a customer particularly likes.

[0968] "Customer characteristics" are individual characteristics of a customer extracted based on the customer's purchasing history, favorite items, physical data, and style preferences.

[0969] A "machine learning model" is an algorithm that learns patterns in data and makes predictions or classifications based on new data.

[0970] A "smartphone" is a type of mobile phone, a device that has multi-functional computing capabilities and is capable of running a variety of applications.

[0971] An "interface" is the means by which a user inputs data into or receives information from a system.

[0972] "Real time" refers to a time period in which data is input and processed immediately, and the results are immediately available.

[0973] "Prediction" is the use of machine learning models to estimate future outcomes or trends based on given data.

[0974] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[0975] System configuration

[0976] Recording customer data

[0977] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[0978] Customer data analysis

[0979] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[0980] Style prediction with machine learning

[0981] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[0982] Proposal of the best fashion items

[0983] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[0984] Entering New Data

[0985] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[0986] Real-time predictions and suggestions

[0987] The server receives this new data, feeds it into machine learning models, and makes real-time predictions, which are then displayed to the user via their smartphone, where they can view suggested styles and products.

[0988] Specific examples

[0989] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the smartphone device displays the results to the user.

[0990] Prompt Sentence Examples

[0991] Enter the new user data in the following format:

[0992] Build: Slim

[0993] Favorite color: Blue

[0994] Previously purchased item: T-shirt

[0995] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0996] Step 1:

[0997] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or database.

[0998] Input: CSV file or database

[0999] Output: A list of customer data

[1000] The server uses database access and file I / O operations to retrieve customer history and preference data and store it in list format.

[1001] Step 2:

[1002] The server preprocesses the data and converts it into a format that can be used by the machine learning model, for example, converting text information about a customer's favorite colors and styles into numbers.

[1003] Input: List of customer data

[1004] Output: Preprocessed data frame

[1005] The server uses LabelEncoder to convert the character data into numerical data, making it easier for the machine learning model to process.

[1006] Step 3:

[1007] The server uses the preprocessed data to train a machine learning model, such as a random forest classifier.

[1008] Input: preprocessed data frame, style labels

[1009] Output: A trained machine learning model

[1010] The server separates the features and target variables and applies machine learning algorithms to train the model.

[1011] Step 4:

[1012] The terminal provides an interface for the user to enter new data, such as body measurements, favorite colors, and past purchase history.

[1013] Input: New data for the user

[1014] Output: A JSON object of the user-entered data

[1015] The user enters information according to the provided format, and the terminal converts it into JSON format and sends it to the server.

[1016] Step 5:

[1017] The server receives new data entered by the user, pre-processes it, and then feeds it into a trained machine learning model.

[1018] Input: A JSON object of new data entered by the user.

[1019] Output: Predicted style labels

[1020] The server preprocesses the new data and runs style predictions against the machine learning model.

[1021] Step 6:

[1022] The server suggests optimal fashion and makeup items to the user based on the predicted style.

[1023] Input: Predicted style labels

[1024] Output: A list of the best fashion and makeup items

[1025] The server selects suggested items based on the style prediction results and generates a list of them.

[1026] Step 7:

[1027] The terminal displays the suggested fashion and makeup items to the user.

[1028] Enter: a list of the best fashion and makeup items.

[1029] Output: Recommended items displayed to the user

[1030] The terminal displays the item list received from the server on a user interface, allowing the user to view these suggestions.

[1031] Each of the above steps makes it possible to reflect the individual characteristics of each customer in real time and suggest the most suitable fashion and makeup items.

[1032] 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.

[1033] The present invention provides a system that combines a customer's past purchase history, favorite items, physical data, style preferences, and an emotion engine that recognizes the user's emotions to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with the server, terminal, and user elements.

[1034] System configuration

[1035] Recording customer and sentiment data

[1036] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This record is saved in a CSV file or database.

[1037] Customer and sentiment data analysis

[1038] The server uses the recorded customer data and emotional data to analyze the characteristics of each customer, including extracting characteristics based on the customer's body type information, preferences, past purchase history, and emotional data.

[1039] Emotion recognition by emotion engine

[1040] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The recognized emotion data is sent to the server.

[1041] Style prediction with machine learning

[1042] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier) ​​that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[1043] Proposal of the best fashion items

[1044] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[1045] Entering new data and emotion data

[1046] Users can input new information, such as their latest physical data, preferences, and emotional data. The new data is added to the system and used for the next analysis and prediction.

[1047] Program processing

[1048] Data loading and preprocessing

[1049] The server reads the customer's past purchase data, preferences, body type information, and emotional data from CSV files, etc. This data includes the customer's body type information, favorite colors, past purchases, emotional state, etc.

[1050] Training a machine learning model

[1051] The server extracts input data (e.g., body type information, favorite colors, past purchases, emotional data) and target data (customer style) from the data, and trains a machine learning model to generate a style prediction model based on the customer data.

[1052] Entering new data and emotion data

[1053] The terminal provides an interface where the user can input new data (body type, favorite color, past purchases, emotional data, etc.) The input data is sent to the server.

[1054] Emotion recognition and data processing

[1055] The terminal receives the user's new data and uses the emotion engine to obtain emotion data, which is then sent to the server.

[1056] Proposal Generation

[1057] The server receives new customer data and sentiment data, inputs it into a machine learning model, and generates predictions, which are optimized to take the sentiment data into account.

[1058] The server uses LabelEncoder to reconvert the predicted numeric style into its original format (string) and provides it as a suggested result.

[1059] Specific examples

[1060] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model.

[1061] Additionally, when the emotion engine detects the user's emotion of joy, the server has the function of suggesting items with brighter colors and fun designs, allowing users to easily find fashion items that best suit them and match their current emotions.

[1062] As described above, the present invention provides a system that can quickly and accurately respond to the diverse needs and emotional states of customers and suggest optimal fashion and makeup items.

[1063] The processing flow will be explained below.

[1064] Step 1:

[1065] The server reads data from the customer_data.csv file, which contains the customer's past purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using Python's pandas library.

[1066] Step 2:

[1067] The server uses LabelEncoder to convert the customer's style information into a number, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for machine learning models to use.

[1068] Step 3:

[1069] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y), specifically, X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[1070] Step 4:

[1071] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[1072] Step 5:

[1073] Users input emotional data (e.g., facial expressions and tone of voice) along with new data (body type, favorite colors, past purchases, etc.), which is collected via the device and sent to the server.

[1074] Step 6:

[1075] The terminal converts the new customer data and emotion data into DataFrame format. Specifically, it creates the data as follows:

[1076] python

[1077] new_customer_data = pd.DataFrame({

[1078] 'customer_id': [1],

[1079] 'body_type': ['slim'],

[1080] 'fav_colors': ['blue'],

[1081] 'past_purchases': ['T-shirt'],

[1082] 'emotion': ['happy']

[1083] })

[1084] Step 7:

[1085] The server receives new customer data and passes it to the machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases', 'emotion']] and executes model.predict(customer_X) to get the prediction style.

[1086] Step 8:

[1087] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[1088] Step 9:

[1089] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[1090] python

[1091] print(recommendations)

[1092] Step 10:

[1093] The device displays the recommended styles received from the server to the user, allowing the user to see which fashion items are best suited to them. For example, if the server detects the emotion of joy, it will suggest items with bright colors and fun designs.

[1094] The above are the specific processing steps in this system.

[1095] Example 2

[1096] 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."

[1097] While conventional fashion recommendation systems take into account a customer's past purchasing history and style preferences, they are unable to make recommendations that take into account the customer's emotional state. This makes it difficult to make optimal recommendations that match the customer's current emotions. Furthermore, new data cannot be input in real time, making it impossible to always make predictions based on the latest customer data.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1099] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for recording emotional data using an emotion engine that recognizes user emotions, means for analyzing customer characteristics using the recorded data, means for predicting the customer's style using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and the emotional data, thereby enabling optimal suggestions that take into account the customer's emotional state and new data in real time.

[1100] "Customer's past purchasing history" refers to a record of the products and services that a customer has purchased in the past.

[1101] "Favorite Items" is a list of products and services that a customer particularly likes.

[1102] "Physical data" refers to information about a customer's physical characteristics and measurements, such as height, weight, and body type.

[1103] "Style preferences" refers to information about the customer's preferred fashion and design characteristics, such as color, material, and design pattern.

[1104] An "emotion engine" is software or hardware for recognizing and analyzing a user's emotions.

[1105] "Emotion data" is data on the user's emotional state as recognized by the emotion engine.

[1106] A "machine learning model" is an algorithm or model that learns from data and makes predictions or classifications.

[1107] "Style prediction" refers to predicting the best fashion and makeup items based on customer data.

[1108] "Preprocessing" is the process of preparing raw data in a form suitable for analysis and learning.

[1109] "Real-time" refers to processing and analysis occurring close to the moment the data is generated.

[1110] The "suggestion results" are a list of fashion and makeup items that the system recommends to the customer.

[1111] The present invention is a system that collects a customer's past purchase history, favorite items, physical data, style preferences, and emotional data, and uses machine learning models to suggest optimal fashion and makeup items for each customer. This system operates in cooperation with the elements of a server, terminals, and users.

[1112] Recording customer and sentiment data

[1113] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This data is saved in a CSV file or database. Programming languages ​​such as Python and R are used as the software to implement the system.

[1114] Customer and sentiment data analysis

[1115] The server uses the recorded customer data and emotional data to analyze each customer's characteristics. This analysis includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. The data analysis uses the pandas and numpy libraries.

[1116] Emotion recognition by emotion engine

[1117] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and tone of voice. The recognized emotion data is sent to the server. Tools such as OpenCV and OpenSmile are used for emotion recognition.

[1118] Style prediction with machine learning

[1119] The server predicts a customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style. Libraries such as Scikit-learn and TensorFlow are used.

[1120] Proposal of the best fashion items

[1121] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[1122] Entering new data and emotion data

[1123] Users can input new information such as their latest physical data, preferences, emotional data, etc. The new data will be added to the system and used for the next analysis and prediction.

[1124] Specific examples

[1125] For example, if a user inputs new information such as "slim body type," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with bright colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[1126] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1127] Step 1:

[1128] The server reads the customer's purchase history, favorite items, physical data, and style preferences from a CSV file. The input data is in CSV format, and the server converts it into a data frame using the pandas library and performs data preprocessing. Specifically, it complements missing data and corrects outliers.

[1129] Input: CSV file (purchase history, favorites, body data, style preferences)

[1130] Output: Preprocessed data frame

[1131] Step 2:

[1132] The server receives the user's emotional data sent from the device. The device analyzes the user's facial expressions and tone of voice in real time and generates emotional data using an emotion engine. The server stores this data and uses it for later analysis.

[1133] Input: Emotion data

[1134] Output: Stored emotion data

[1135] Step 3:

[1136] The server analyzes user characteristics based on the preprocessed customer data and emotion data. Here, characteristics are extracted based on the customer's body shape information, purchase history, preferences, and emotion data. The system is implemented using the pandas and numpy libraries.

[1137] Input: Preprocessed data frame, emotion data

[1138] Output: Analysis results (customer characteristics)

[1139] Step 4:

[1140] The server uses the analysis results to train a machine learning model, a random forest classifier implemented using the Scikit-learn library, which generates a model to predict the optimal style based on the customer's physical data, purchase history, and emotional data.

[1141] Input: Analysis results (customer characteristics)

[1142] Output: A trained machine learning model

[1143] Step 5:

[1144] The user can input new data through the terminal. The terminal provides an interface for inputting the user's new physical data, preferences, and emotional state. The input data is transmitted to the server in real time via AJAX.

[1145] Input: New user data (physical data, preferences, emotional state)

[1146] Output: New data sent to the server

[1147] Step 6:

[1148] The server receives new user data and stored emotion data, inputs them into the machine learning model, and performs style prediction. The prediction results are converted back to their original string form using LabelEncoder. Then, the suggestion results are optimized taking the emotion data into account.

[1149] Input: New user data, emotion data

[1150] Output: Optimized proposal results

[1151] Step 7:

[1152] The server then sends the optimized recommendations to the user's device, where the user can view the suggested fashion and makeup items. This allows users to easily find the fashion items that best suit them.

[1153] Input: Optimized proposal results

[1154] Output: The proposed results presented to the user

[1155] Examples of specific prompts include "slim figure," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy." Based on this information, the system can make suggestions that are appropriate for the user.

[1156] (Application example 2)

[1157] 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."

[1158] Conventional fashion and makeup product recommendation systems are based solely on a customer's purchasing history and style preferences, and do not take into account the customer's emotional state when selecting items. As a result, customer satisfaction is reduced and optimal product recommendations cannot be made. It is also difficult to respond quickly and accurately to individual customer needs.

[1159] The identification processing by the identification 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 recording a customer's past purchase history, favorite items, body data, style preferences, and emotional state, means for analyzing the customer's characteristics using the recorded data, means for recognizing the user's emotions using an emotion recognition engine, means for predicting the customer's style based on the analysis results using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and emotional data. This makes it possible to suggest optimal products taking the customer's emotional state into consideration, thereby improving customer satisfaction.

[1160] "Purchase history" is a record of products that a customer has purchased in the past.

[1161] "Favorite Items" is a list of products or items that a customer particularly likes.

[1162] "Physical data" refers to data such as a customer's body type, size, height, and weight.

[1163] "Style preferences" is information about the fashion and makeup styles that a customer prefers.

[1164] "Emotional state" is data that indicates the user's current mood or emotion (for example, joy or sadness).

[1165] An "emotion recognition engine" is a program or system that analyzes a user's facial expressions and tone of voice to recognize their emotions.

[1166] A "machine learning model" is an algorithm that uses data to predict customer behavior and preferences.

[1167] "Optimal fashion and makeup items" are fashion and makeup products that are recommended based on the customer's characteristics and emotional state.

[1168] A "server" is a computer system for recording, analyzing, processing, and storing data.

[1169] A "smartphone application" is a software program that runs on a smartphone and has the function of suggesting fashion and makeup items to customers.

[1170] This invention is a system that records a customer's past purchase history, favorite items, physical data, style preferences, and emotional state, and then suggests the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[1171] System configuration

[1172] Recording customer and sentiment data

[1173] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also uses an emotion recognition engine to recognize the user's emotional state and saves this data in a CSV file or database. Specifically, the information entered by the user using their smartphone is sent to the server, which then records it in the database.

[1174] Customer and sentiment data analysis

[1175] The server analyzes each customer's characteristics using machine learning models based on the recorded customer data and emotional data. This includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. Machine learning models such as random forest classifiers are used.

[1176] Emotion recognition by emotion engine

[1177] The device is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The emotion recognition engine uses the EmotionEngine, a hypothetical library. The recognized emotion data is sent to a server for analysis.

[1178] Style prediction with machine learning

[1179] The server predicts a customer's style using a machine learning model that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[1180] Proposal of the best fashion items

[1181] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations based on the user's emotional state.

[1182] Entering new data and emotion data

[1183] Users input new information such as their latest physical data, preferences, and emotional data via their smartphones, allowing the system to continuously use the latest data for analysis and prediction.

[1184] Specific examples

[1185] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with brighter colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[1186] Prompt Sentence Examples

[1187] An example prompt for new data from the user might look something like this:

[1188] "Enter the user's physical and preference data, as well as their current emotional state. Example: 'Slim build, favorite color is blue, past purchase: T-shirts, current emotion: joy'"

[1189] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1190] Step 1:

[1191] The server records the customer's past purchase history, favorite items, physical data, style preferences, and emotional state. These data are stored in a CSV file or a database. As input, it uses the data submitted by the user, and as output, it gets the customer data recorded in a CSV file or a database.

[1192] Step 2:

[1193] The server analyzes the recorded customer data and emotion data. Specifically, it uses a machine learning model (e.g., a random forest classifier) ​​to extract customer characteristics. The customer data and emotion data stored in the database are used as input, and the customer style prediction result is obtained as output.

[1194] Step 3:

[1195] The device uses an emotion recognition engine to recognize the user's emotions. When the user points their face at the smartphone camera, the emotion recognition engine analyzes their facial expressions and tone of voice. The input is the user's facial image and voice data, and the output is recognized emotion data.

[1196] Step 4:

[1197] The device sends the recognized emotion data to the server. The emotion data sent from the device is used as input, and the server receives it and stores it in a database. The updated database is obtained as output.

[1198] Step 5:

[1199] The server initiates the process of predicting the customer's style using a machine learning model. The customer data and sentiment data stored in the database are used as input. The machine learning model runs the data and produces a predicted style as output.

[1200] Step 6:

[1201] The server then recommends the most suitable fashion and makeup items to the customer based on the prediction results and emotion data. The input is style data and emotion data predicted by the machine learning model. These data are combined for data processing, and the output is a list of the most suitable items.

[1202] Step 7:

[1203] The user uses a smartphone to input new data. The input form includes items such as physical data, preferences, emotional state, etc. The new information entered by the user is used as input, and the output is the new data that is sent to the server.

[1204] Step 8:

[1205] The terminal sends new data from the user to the server. As input, it uses the data entered into the terminal and sends it to the server. As output, the server receives the new data and adds it to the database.

[1206] Step 9:

[1207] The server uses the updated data to retrain the machine learning model for the next round of predictions and suggestions. The updated customer and sentiment data are used as input. The machine learning algorithm is retrained and the output is a predictive model with improved accuracy.

[1208] 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.

[1209] 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.

[1210] 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.

[1211] [Fourth embodiment]

[1212] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1213] 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.

[1214] 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).

[1215] 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.

[1216] 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.

[1217] 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).

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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."

[1225] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[1226] System configuration

[1227] Recording customer data

[1228] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[1229] Customer data analysis

[1230] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[1231] Style prediction with machine learning

[1232] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[1233] Proposal of the best fashion items

[1234] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[1235] Entering New Data

[1236] Users can input their latest physical data, preferences, and other information. The new data is added to the system and used for the next analysis and prediction.

[1237] Program processing

[1238] Data loading and preprocessing

[1239] The server reads the customer's past purchase data, preferences, and body type information from a CSV file, etc. This data includes the customer's body type, favorite colors, past purchases, etc.

[1240] The server uses LabelEncoder to convert textual information into numbers, converting the data into a format that is easy for machine learning models to use. This preprocessing step ensures that the data is properly prepared.

[1241] Training the model

[1242] The server extracts input data (e.g., body type information, favorite colors, past purchases) and target data (customer style) from the data and trains a machine learning model, which generates a model that predicts style based on the customer's data.

[1243] Entering and Processing New Data

[1244] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[1245] The server takes this new data and feeds it into a machine learning model to make predictions.

[1246] Presentation of results

[1247] The server uses a machine learning model to convert the predicted style into a format that humans can understand and suggests the most suitable fashion items to the user.

[1248] The terminal displays the recommendation results received from the server to the user, allowing the user to easily find the item that best suits them.

[1249] Specific examples

[1250] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the device displays the results to the user.

[1251] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[1252] The processing flow will be explained below.

[1253] Step 1:

[1254] The server reads data from the customer_data.csv file, which contains customer purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using the Python pandas library.

[1255] Step 2:

[1256] The server uses LabelEncoder to convert the customer's style information into a numerical value, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for the machine learning model to process.

[1257] Step 3:

[1258] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y). Specifically, it executes X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[1259] Step 4:

[1260] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[1261] Step 5:

[1262] The user inputs new data (body type, favorite colors, past purchases, etc.) This data is collected through the terminal and sent to the server.

[1263] Step 6:

[1264] The terminal converts the new customer data you enter into a DataFrame format. Specifically, it creates the data as follows:

[1265] python

[1266] new_customer_data = pd.DataFrame({

[1267] 'customer_id': [1],

[1268] 'body_type': ['slim'],

[1269] 'fav_colors': ['blue'],

[1270] 'past_purchases': ['T-shirt']

[1271] })

[1272] Step 7:

[1273] The server receives new customer data and passes it to a pre-trained machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases']] and executes model.predict(customer_X) to get the prediction style.

[1274] Step 8:

[1275] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[1276] Step 9:

[1277] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[1278] python

[1279] print(recommendations)

[1280] Step 10:

[1281] The terminal displays the recommended styles received from the server to the user, allowing the user to check the fashion items that best suit them.

[1282] The above are the specific processing steps in this system.

[1283] Example 1

[1284] 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."

[1285] Conventional systems for suggesting fashion and makeup items have been unable to fully reflect the individual characteristics and preferences of customers, resulting in low customer satisfaction. Furthermore, data entry is cumbersome, making them impractical. To address these issues, a system is needed that can efficiently analyze diverse customer information and quickly suggest the best items for each individual customer.

[1286] 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.

[1287] In this invention, the server includes: means for recording a customer's past purchase history, favorite items, physical data, and style preferences; means for analyzing the customer's characteristics using the recorded data; means for training a machine learning model using the analysis results to predict the customer's style; means for suggesting optimal fashion and makeup items to the customer based on the prediction results of the machine learning model; means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer; and means for promptly and accurately suggesting optimal fashion and makeup items to the customer in response to the individual needs of the customer.

[1288] "Customer's past purchase history" refers to a record of products and services previously purchased by a customer, including, for example, the date and time of purchase, the name, quantity, and price of the purchased items.

[1289] "Favorite Items" is a list of products or services that a customer particularly likes, including items that the customer purchases frequently and items of special interest.

[1290] "Physical Data" refers to data about a customer's body shape and physical characteristics, including, for example, height, weight, body fat percentage, and waist circumference.

[1291] "Style preferences" refers to data about a customer's preferred fashion and makeup styles, including their preferred clothing colors and designs, and favorite brands.

[1292] "Means of Recording" refers to the method or system for storing customer data, including, for example, means for storing data in the form of a database or a CSV file.

[1293] "Means for analyzing characteristics" refers to methods or systems for extracting and analyzing customer characteristics based on recorded data, including, for example, data analysis software and algorithms.

[1294] A "machine learning model" is an algorithm or program that can learn from data and make predictions or classifications. Examples include models such as random forests and neural networks.

[1295] "Training means" refers to a method or system for effectively training a machine learning model, including, for example, means for splitting a dataset and tuning model parameters.

[1296] "Means for suggesting" refers to methods or systems that present suitable products or services to customers based on analysis and prediction results. Examples include recommendation systems and notification functions.

[1297] "Information input methods" are the methods or interfaces that allow customers to enter new data into a system. Examples include input fields on web forms or mobile apps.

[1298] "Means for processing input information" refers to methods or systems that analyze new data acquired from customers and convert it into an appropriate format. For example, this may include data pre-processing algorithms.

[1299] The "means for displaying the recommendation results" refers to a method or system for visually displaying the recommendation results from the server to the user. For example, this includes the display screen of a web page or a mobile app.

[1300] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with each element of the server, terminal, and user.

[1301] System configuration

[1302] Recording customer data

[1303] The server records the customer's past purchase history, favorite items, physical data, and style preferences. This includes the ability to save the customer's purchase and physical data to a CSV file or database. For example, the data can be read from a CSV file using the Python pandas library.

[1304] Customer data analysis

[1305] The server analyzes customer characteristics based on the recorded data. Specifically, data analysis software and algorithms are used to extract characteristics based on the customer's body type, preferences, and past purchase history. Data frame manipulation using pandas and preprocessing techniques using sklearn are used here.

[1306] Style prediction using machine learning models

[1307] The server uses a machine learning model to predict the customer's style. This model can be a random forest or a neural network. Specifically, the server can use the random forest classifier from the sklearn library. The model is trained by splitting the dataset and adjusting parameters.

[1308] Proposal of the best fashion items

[1309] The server then uses the predictions made by the machine learning model to suggest the best fashion and makeup items for each customer, for example by retrieving items from a database that are suitable for a specific style and generating a specific product list.

[1310] Entering New Data

[1311] The device provides an interface through which users can input new data, including their current physical data and preferences. The input data is sent in real time to a server for analysis.

[1312] Program processing

[1313] The server reads the customer data, converts the text information into numbers using LabelEncoder, and standardizes them. The preprocessed data is then used to train machine learning models.

[1314] Next, when the user inputs new data using the device, the data is sent to the server. The server preprocesses this new data and inputs it into the machine learning model to make predictions. Finally, the server generates item suggestions based on the prediction results and sends them to the device. The device then displays the suggestions to the user, providing them with the most suitable fashion items.

[1315] Specific examples

[1316] For example, if a user enters information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and processes it using LabelEncoder and StandardScaler. Next, a machine learning model is used to predict "casual style," and based on the results, suggestions such as "blue T-shirts" and "denim jackets" are made. These suggestions are then displayed on the device, allowing the user to easily find the items that best suit them.

[1317] Prompt Sentence Examples

[1318] Body type: Slim

[1319] Favorite color: Blue

[1320] Previous purchase: T-shirt

[1321] As described above, the present invention provides a system that quickly and accurately responds to the diverse needs of customers and suggests optimal fashion and makeup items.

[1322] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1323] Step 1:

[1324] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or a database. Specifically, it uses the pandas library to read the data with the pandas.read_csv() method, which results in the customer data in a data frame format.

[1325] Input: CSV file containing customer data

[1326] Output: Customer data in dataframe format

[1327] Step 2:

[1328] The server performs preprocessing on the loaded data, which includes converting categorical data to numeric values ​​using LabelEncoder, and then normalizing the data using StandardScaler.

[1329] Input: Customer data in dataframe format

[1330] Output: Customer data converted to numbers and normalized

[1331] Step 3:

[1332] The server uses the preprocessed data to train a machine learning model. Specifically, it splits the data into a training set and a test set and trains the model using a random forest classifier. This step uses train_test_split and RandomForestClassifier.

[1333] Input: Customer data converted to numbers and normalized

[1334] Output: A trained machine learning model

[1335] Step 4:

[1336] The terminal provides an interface through which the user can input new data, such as body type information, favorite colors, past purchases, etc. This allows the user's latest data to be collected.

[1337] Input: User's new body type, favorite colors, past purchases

[1338] Output: The user's new data

[1339] Step 5:

[1340] The device sends new data entered by the user to the server using an HTTP request. The server receives this data and performs preprocessing. Again, it uses LabelEncoder and StandardScaler to convert the new data into a format suitable for the machine learning model.

[1341] Input: User's new data

[1342] Output: Preprocessed new user data

[1343] Step 6:

[1344] The server inputs the preprocessed new user data into the machine learning model and makes predictions. Specifically, it uses the new data to predict style and selects the most suitable fashion items based on that prediction.

[1345] Input: Preprocessed new user data

[1346] Output: Predicted style and suggested fashion items based on it

[1347] Step 7:

[1348] The server converts the prediction results into a human-understandable format and suggests the most suitable fashion and makeup items for the user, for example, "For a casual style, a blue T-shirt and denim jacket."

[1349] Input: predicted style

[1350] Output: Human-understandable fashion and makeup item suggestions

[1351] Step 8:

[1352] The device displays the proposed results received from the server to the user. Specifically, the proposed items are displayed in list format on a web page or mobile app screen so that the user can easily check them.

[1353] Input: Fashion and makeup suggestions

[1354] Output: The suggestions displayed to the user

[1355] As described above, the entire system functions in concert based on the specific operations performed at each processing step and their inputs and outputs. This series of processes allows users to efficiently find the fashion and makeup items that are best suited to them.

[1356] (Application example 1)

[1357] 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."

[1358] In recent years, there has been a demand for personalized recommendations of fashion and makeup items for customers with diverse needs. However, conventional systems have had difficulty in making recommendations that fully reflect the characteristics of each customer, making it difficult to recommend appropriate items. Furthermore, the difficulty of making recommendations in real time has limited the improvement of customer experience in physical stores.

[1359] 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.

[1360] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for analyzing the customer's characteristics using the recorded data, means for proposing optimal fashion and makeup items to the customer based on the analysis results, means for providing an interface through which the customer can input new data, means for predicting and proposing a style in real time based on the input data, and means for displaying the predicted style to the customer using a smartphone. This makes it possible to reflect the customer's individual characteristics in real time and propose optimal fashion and makeup items.

[1361] "Customer's past purchase history" refers to data on products and services that a customer has purchased in the past.

[1362] "Favorite items" refers to data on products and services that customers particularly like to purchase or use.

[1363] "Physical data" refers to information about a customer's physical characteristics, such as height, weight, and body type.

[1364] "Style preferences" refers to information about the trends and tastes of fashion and makeup that a customer particularly likes.

[1365] "Customer characteristics" are individual characteristics of a customer extracted based on the customer's purchasing history, favorite items, physical data, and style preferences.

[1366] A "machine learning model" is an algorithm that learns patterns in data and makes predictions or classifications based on new data.

[1367] A "smartphone" is a type of mobile phone, a device that has multi-functional computing capabilities and is capable of running a variety of applications.

[1368] An "interface" is the means by which a user inputs data into or receives information from a system.

[1369] "Real time" refers to a time period in which data is input and processed immediately, and the results are immediately available.

[1370] "Prediction" is the use of machine learning models to estimate future outcomes or trends based on given data.

[1371] The present invention is a system that analyzes a customer's past purchase history, favorite items, physical data, and style preferences to suggest the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[1372] System configuration

[1373] Recording customer data

[1374] The server records the customer's past purchase history, favorite items, physical data, and style preferences, and stores this information in, for example, a CSV file or a database.

[1375] Customer data analysis

[1376] The server uses the recorded customer data to analyze each customer's characteristics, including extracting characteristics based on the customer's body type, preferences, and past purchase history.

[1377] Style prediction with machine learning

[1378] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, etc. as input and outputs a predicted style.

[1379] Proposal of the best fashion items

[1380] The server suggests the best fashion and makeup items for each customer based on the predictions made by the machine learning model.

[1381] Entering New Data

[1382] The terminal provides an interface where the user can input new data (body type, favorite colors, past purchases, etc.) which is then sent to the server.

[1383] Real-time predictions and suggestions

[1384] The server receives this new data, feeds it into machine learning models, and makes real-time predictions, which are then displayed to the user via their smartphone, where they can view suggested styles and products.

[1385] Specific examples

[1386] For example, if a user inputs new information such as "slim build," "favorite color is blue," and "past purchases include T-shirts," the server receives this information and uses a pre-trained machine learning model to predict that a "casual style" would be appropriate. Based on this result, the server suggests the most suitable fashion items for the user, and the smartphone device displays the results to the user.

[1387] Prompt Sentence Examples

[1388] Enter the new user data in the following format:

[1389] Build: Slim

[1390] Favorite color: Blue

[1391] Previously purchased item: T-shirt

[1392] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1393] Step 1:

[1394] The server reads the customer's past purchase history, favorite items, physical data, and style preferences from a CSV file or database.

[1395] Input: CSV file or database

[1396] Output: A list of customer data

[1397] The server uses database access and file I / O operations to retrieve customer history and preference data and store it in list format.

[1398] Step 2:

[1399] The server preprocesses the data and converts it into a format that can be used by the machine learning model, for example, converting text information about a customer's favorite colors and styles into numbers.

[1400] Input: List of customer data

[1401] Output: Preprocessed data frame

[1402] The server uses LabelEncoder to convert the character data into numerical data, making it easier for the machine learning model to process.

[1403] Step 3:

[1404] The server uses the preprocessed data to train a machine learning model, such as a random forest classifier.

[1405] Input: preprocessed data frame, style labels

[1406] Output: A trained machine learning model

[1407] The server separates the features and target variables and applies machine learning algorithms to train the model.

[1408] Step 4:

[1409] The terminal provides an interface for the user to enter new data, such as body measurements, favorite colors, and past purchase history.

[1410] Input: New data for the user

[1411] Output: A JSON object of the user-entered data

[1412] The user enters information according to the provided format, and the terminal converts it into JSON format and sends it to the server.

[1413] Step 5:

[1414] The server receives new data entered by the user, pre-processes it, and then feeds it into a trained machine learning model.

[1415] Input: A JSON object of new data entered by the user.

[1416] Output: Predicted style labels

[1417] The server preprocesses the new data and runs style predictions against the machine learning model.

[1418] Step 6:

[1419] The server suggests optimal fashion and makeup items to the user based on the predicted style.

[1420] Input: Predicted style labels

[1421] Output: A list of the best fashion and makeup items

[1422] The server selects suggested items based on the style prediction results and generates a list of them.

[1423] Step 7:

[1424] The terminal displays the suggested fashion and makeup items to the user.

[1425] Enter: a list of the best fashion and makeup items.

[1426] Output: Recommended items displayed to the user

[1427] The terminal displays the item list received from the server on a user interface, allowing the user to view these suggestions.

[1428] Each of the above steps makes it possible to reflect the individual characteristics of each customer in real time and suggest the most suitable fashion and makeup items.

[1429] 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.

[1430] The present invention provides a system that combines a customer's past purchase history, favorite items, physical data, style preferences, and an emotion engine that recognizes the user's emotions to suggest the most suitable fashion and makeup items for each customer. This system operates in cooperation with the server, terminal, and user elements.

[1431] System configuration

[1432] Recording customer and sentiment data

[1433] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This record is saved in a CSV file or database.

[1434] Customer and sentiment data analysis

[1435] The server uses the recorded customer data and emotional data to analyze the characteristics of each customer, including extracting characteristics based on the customer's body type information, preferences, past purchase history, and emotional data.

[1436] Emotion recognition by emotion engine

[1437] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The recognized emotion data is sent to the server.

[1438] Style prediction with machine learning

[1439] The server predicts the customer's style using a machine learning model (e.g., a random forest classifier) ​​that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[1440] Proposal of the best fashion items

[1441] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[1442] Entering new data and emotion data

[1443] Users can input new information, such as their latest physical data, preferences, and emotional data. The new data is added to the system and used for the next analysis and prediction.

[1444] Program processing

[1445] Data loading and preprocessing

[1446] The server reads the customer's past purchase data, preferences, body type information, and emotional data from CSV files, etc. This data includes the customer's body type information, favorite colors, past purchases, emotional state, etc.

[1447] Training a machine learning model

[1448] The server extracts input data (e.g., body type information, favorite colors, past purchases, emotional data) and target data (customer style) from the data, and trains a machine learning model to generate a style prediction model based on the customer data.

[1449] Entering new data and emotion data

[1450] The terminal provides an interface where the user can input new data (body type, favorite color, past purchases, emotional data, etc.) The input data is sent to the server.

[1451] Emotion recognition and data processing

[1452] The terminal receives the user's new data and uses the emotion engine to obtain emotion data, which is then sent to the server.

[1453] Proposal Generation

[1454] The server receives new customer data and sentiment data, inputs it into a machine learning model, and generates predictions, which are optimized to take the sentiment data into account.

[1455] The server uses LabelEncoder to reconvert the predicted numeric style into its original format (string) and provides it as a suggested result.

[1456] Specific examples

[1457] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model.

[1458] Additionally, when the emotion engine detects the user's emotion of joy, the server has the function of suggesting items with brighter colors and fun designs, allowing users to easily find fashion items that best suit them and match their current emotions.

[1459] As described above, the present invention provides a system that can quickly and accurately respond to the diverse needs and emotional states of customers and suggest optimal fashion and makeup items.

[1460] The processing flow will be explained below.

[1461] Step 1:

[1462] The server reads data from the customer_data.csv file, which contains the customer's past purchase history, favorite items, physical data, and style preferences, and converts the data into a DataFrame using Python's pandas library.

[1463] Step 2:

[1464] The server uses LabelEncoder to convert the customer's style information into a number, specifically by executing data['style'] = le.fit_transform(data['style']). This conversion makes it easier for machine learning models to use.

[1465] Step 3:

[1466] The server extracts the customer's body type, favorite colors, and past purchases as input data (X), and style information as target data (y), specifically, X = data[['body_type', 'fav_colors', 'past_purchases']] and y = data['style'].

[1467] Step 4:

[1468] The server trains a machine learning model using RandomForestClassifier, specifically by running model.fit(X, y) to generate a style prediction model based on the customer data.

[1469] Step 5:

[1470] Users input emotional data (e.g., facial expressions and tone of voice) along with new data (body type, favorite colors, past purchases, etc.), which is collected via the device and sent to the server.

[1471] Step 6:

[1472] The terminal converts the new customer data and emotion data into DataFrame format. Specifically, it creates the data as follows:

[1473] python

[1474] new_customer_data = pd.DataFrame({

[1475] 'customer_id': [1],

[1476] 'body_type': ['slim'],

[1477] 'fav_colors': ['blue'],

[1478] 'past_purchases': ['T-shirt'],

[1479] 'emotion': ['happy']

[1480] })

[1481] Step 7:

[1482] The server receives new customer data and passes it to the machine learning model to make predictions. Specifically, it extracts customer_X = new_customer_data[['body_type', 'fav_colors', 'past_purchases', 'emotion']] and executes model.predict(customer_X) to get the prediction style.

[1483] Step 8:

[1484] The server uses LabelEncoder to reconvert the predicted style of the numbers into a human-readable format (string), specifically by executing new_customer_data['Style'] = le.inverse_transform(predicted_style).

[1485] Step 9:

[1486] The server compiles the prediction results into a DataFrame containing the customer ID and the recommended style, and returns it to the device. The returned data might look something like this:

[1487] python

[1488] print(recommendations)

[1489] Step 10:

[1490] The device displays the recommended styles received from the server to the user, allowing the user to see which fashion items are best suited to them. For example, if the server detects the emotion of joy, it will suggest items with bright colors and fun designs.

[1491] The above are the specific processing steps in this system.

[1492] Example 2

[1493] 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."

[1494] While conventional fashion recommendation systems take into account a customer's past purchasing history and style preferences, they are unable to make recommendations that take into account the customer's emotional state. This makes it difficult to make optimal recommendations that match the customer's current emotions. Furthermore, new data cannot be input in real time, making it impossible to always make predictions based on the latest customer data.

[1495] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1496] In this invention, the server includes means for recording a customer's past purchase history, favorite items, physical data, and style preferences, means for recording emotional data using an emotion engine that recognizes user emotions, means for analyzing customer characteristics using the recorded data, means for predicting the customer's style using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and the emotional data, thereby enabling optimal suggestions that take into account the customer's emotional state and new data in real time.

[1497] "Customer's past purchasing history" refers to a record of the products and services that a customer has purchased in the past.

[1498] "Favorite Items" is a list of products and services that a customer particularly likes.

[1499] "Physical data" refers to information about a customer's physical characteristics and measurements, such as height, weight, and body type.

[1500] "Style preferences" refers to information about the customer's preferred fashion and design characteristics, such as color, material, and design pattern.

[1501] An "emotion engine" is software or hardware for recognizing and analyzing a user's emotions.

[1502] "Emotion data" is data on the user's emotional state as recognized by the emotion engine.

[1503] A "machine learning model" is an algorithm or model that learns from data and makes predictions or classifications.

[1504] "Style prediction" refers to predicting the best fashion and makeup items based on customer data.

[1505] "Preprocessing" is the process of preparing raw data in a form suitable for analysis and learning.

[1506] "Real-time" refers to processing and analysis occurring close to the moment the data is generated.

[1507] The "suggestion results" are a list of fashion and makeup items that the system recommends to the customer.

[1508] The present invention is a system that collects a customer's past purchase history, favorite items, physical data, style preferences, and emotional data, and uses machine learning models to suggest optimal fashion and makeup items for each customer. This system operates in cooperation with the elements of a server, terminals, and users.

[1509] Recording customer and sentiment data

[1510] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also records emotional data using an emotion engine that recognizes the user's emotions. This data is saved in a CSV file or database. Programming languages ​​such as Python and R are used as the software to implement the system.

[1511] Customer and sentiment data analysis

[1512] The server uses the recorded customer data and emotional data to analyze each customer's characteristics. This analysis includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. The data analysis uses the pandas and numpy libraries.

[1513] Emotion recognition by emotion engine

[1514] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and tone of voice. The recognized emotion data is sent to the server. Tools such as OpenCV and OpenSmile are used for emotion recognition.

[1515] Style prediction with machine learning

[1516] The server predicts a customer's style using a machine learning model (e.g., a random forest classifier). The model takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style. Libraries such as Scikit-learn and TensorFlow are used.

[1517] Proposal of the best fashion items

[1518] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations according to the user's emotional state.

[1519] Entering new data and emotion data

[1520] Users can input new information such as their latest physical data, preferences, emotional data, etc. The new data will be added to the system and used for the next analysis and prediction.

[1521] Specific examples

[1522] For example, if a user inputs new information such as "slim body type," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with bright colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[1523] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1524] Step 1:

[1525] The server reads the customer's purchase history, favorite items, physical data, and style preferences from a CSV file. The input data is in CSV format, and the server converts it into a data frame using the pandas library and performs data preprocessing. Specifically, it complements missing data and corrects outliers.

[1526] Input: CSV file (purchase history, favorites, body data, style preferences)

[1527] Output: Preprocessed data frame

[1528] Step 2:

[1529] The server receives the user's emotional data sent from the device. The device analyzes the user's facial expressions and tone of voice in real time and generates emotional data using an emotion engine. The server stores this data and uses it for later analysis.

[1530] Input: Emotion data

[1531] Output: Stored emotion data

[1532] Step 3:

[1533] The server analyzes user characteristics based on the preprocessed customer data and emotion data. Here, characteristics are extracted based on the customer's body shape information, purchase history, preferences, and emotion data. The system is implemented using the pandas and numpy libraries.

[1534] Input: Preprocessed data frame, emotion data

[1535] Output: Analysis results (customer characteristics)

[1536] Step 4:

[1537] The server uses the analysis results to train a machine learning model, a random forest classifier implemented using the Scikit-learn library, which generates a model to predict the optimal style based on the customer's physical data, purchase history, and emotional data.

[1538] Input: Analysis results (customer characteristics)

[1539] Output: A trained machine learning model

[1540] Step 5:

[1541] The user can input new data through the terminal. The terminal provides an interface for inputting the user's new physical data, preferences, and emotional state. The input data is transmitted to the server in real time via AJAX.

[1542] Input: New user data (physical data, preferences, emotional state)

[1543] Output: New data sent to the server

[1544] Step 6:

[1545] The server receives new user data and stored emotion data, inputs them into the machine learning model, and performs style prediction. The prediction results are converted back to their original string form using LabelEncoder. Then, the suggestion results are optimized taking the emotion data into account.

[1546] Input: New user data, emotion data

[1547] Output: Optimized proposal results

[1548] Step 7:

[1549] The server then sends the optimized recommendations to the user's device, where the user can view the suggested fashion and makeup items. This allows users to easily find the fashion items that best suit them.

[1550] Input: Optimized proposal results

[1551] Output: The proposed results presented to the user

[1552] Examples of specific prompts include "slim figure," "favorite color is blue," "past purchase: T-shirt," and "current emotion: joy." Based on this information, the system can make suggestions that are appropriate for the user.

[1553] (Application example 2)

[1554] 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."

[1555] Conventional fashion and makeup product recommendation systems are based solely on a customer's purchasing history and style preferences, and do not take into account the customer's emotional state when selecting items. As a result, customer satisfaction is reduced and optimal product recommendations cannot be made. It is also difficult to respond quickly and accurately to individual customer needs.

[1556] The identification processing by the identification 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 recording a customer's past purchase history, favorite items, body data, style preferences, and emotional state, means for analyzing the customer's characteristics using the recorded data, means for recognizing the user's emotions using an emotion recognition engine, means for predicting the customer's style based on the analysis results using a machine learning model, and means for suggesting optimal fashion and makeup items to the customer based on the prediction results and emotional data. This makes it possible to suggest optimal products taking the customer's emotional state into consideration, thereby improving customer satisfaction.

[1557] "Purchase history" is a record of products that a customer has purchased in the past.

[1558] "Favorite Items" is a list of products or items that a customer particularly likes.

[1559] "Physical data" refers to data such as a customer's body type, size, height, and weight.

[1560] "Style preferences" is information about the fashion and makeup styles that a customer prefers.

[1561] "Emotional state" is data that indicates the user's current mood or emotion (for example, joy or sadness).

[1562] An "emotion recognition engine" is a program or system that analyzes a user's facial expressions and tone of voice to recognize their emotions.

[1563] A "machine learning model" is an algorithm that uses data to predict customer behavior and preferences.

[1564] "Optimal fashion and makeup items" are fashion and makeup products that are recommended based on the customer's characteristics and emotional state.

[1565] A "server" is a computer system for recording, analyzing, processing, and storing data.

[1566] A "smartphone application" is a software program that runs on a smartphone and has the function of suggesting fashion and makeup items to customers.

[1567] This invention is a system that records a customer's past purchase history, favorite items, physical data, style preferences, and emotional state, and then suggests the most suitable fashion and makeup items for each individual customer. This system operates in cooperation with the server, terminal, and user elements.

[1568] System configuration

[1569] Recording customer and sentiment data

[1570] The server records the customer's past purchase history, favorite items, physical data, and style preferences. It also uses an emotion recognition engine to recognize the user's emotional state and saves this data in a CSV file or database. Specifically, the information entered by the user using their smartphone is sent to the server, which then records it in the database.

[1571] Customer and sentiment data analysis

[1572] The server analyzes each customer's characteristics using machine learning models based on the recorded customer data and emotional data. This includes extracting characteristics based on the customer's body type, preferences, past purchase history, and emotional data. Machine learning models such as random forest classifiers are used.

[1573] Emotion recognition by emotion engine

[1574] The device is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions, tone of voice, etc. The emotion recognition engine uses the EmotionEngine, a hypothetical library. The recognized emotion data is sent to a server for analysis.

[1575] Style prediction with machine learning

[1576] The server predicts a customer's style using a machine learning model that takes the customer's physical data, past purchase history, and emotional data as input and outputs a predicted style.

[1577] Proposal of the best fashion items

[1578] The server then recommends the most suitable fashion and makeup items for each customer based on the predictions made by the machine learning model and emotional data, and also has the ability to adjust the recommendations based on the user's emotional state.

[1579] Entering new data and emotion data

[1580] Users input new information such as their latest physical data, preferences, and emotional data via their smartphones, allowing the system to continuously use the latest data for analysis and prediction.

[1581] Specific examples

[1582] For example, if a user inputs new information such as "slim build," "favorite color is blue," "past purchases: T-shirts," and "current emotion: joy," the server uses this information to predict that a "casual style" would be appropriate using a pre-trained machine learning model. Furthermore, if the emotion engine detects the user's emotion of joy, the server will suggest items with brighter colors and fun designs. In this way, users can easily find the fashion items that best suit them.

[1583] Prompt Sentence Examples

[1584] An example prompt for new data from the user might look something like this:

[1585] "Enter the user's physical and preference data, as well as their current emotional state. Example: 'Slim build, favorite color is blue, past purchase: T-shirts, current emotion: joy'"

[1586] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1587] Step 1:

[1588] The server records the customer's past purchase history, favorite items, physical data, style preferences, and emotional state. These data are stored in a CSV file or a database. As input, it uses the data submitted by the user, and as output, it gets the customer data recorded in a CSV file or a database.

[1589] Step 2:

[1590] The server analyzes the recorded customer data and emotion data. Specifically, it uses a machine learning model (e.g., a random forest classifier) ​​to extract customer characteristics. The customer data and emotion data stored in the database are used as input, and the customer style prediction result is obtained as output.

[1591] Step 3:

[1592] The device uses an emotion recognition engine to recognize the user's emotions. When the user points their face at the smartphone camera, the emotion recognition engine analyzes their facial expressions and tone of voice. The input is the user's facial image and voice data, and the output is recognized emotion data.

[1593] Step 4:

[1594] The device sends the recognized emotion data to the server. The emotion data sent from the device is used as input, and the server receives it and stores it in a database. The updated database is obtained as output.

[1595] Step 5:

[1596] The server initiates the process of predicting the customer's style using a machine learning model. The customer data and sentiment data stored in the database are used as input. The machine learning model runs the data and produces a predicted style as output.

[1597] Step 6:

[1598] The server then recommends the most suitable fashion and makeup items to the customer based on the prediction results and emotion data. The input is style data and emotion data predicted by the machine learning model. These data are combined for data processing, and the output is a list of the most suitable items.

[1599] Step 7:

[1600] The user uses a smartphone to input new data. The input form includes items such as physical data, preferences, emotional state, etc. The new information entered by the user is used as input, and the output is the new data that is sent to the server.

[1601] Step 8:

[1602] The terminal sends new data from the user to the server. As input, it uses the data entered into the terminal and sends it to the server. As output, the server receives the new data and adds it to the database.

[1603] Step 9:

[1604] The server uses the updated data to retrain the machine learning model for the next round of predictions and suggestions. The updated customer and sentiment data are used as input. The machine learning algorithm is retrained and the output is a predictive model with improved accuracy.

[1605] 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.

[1606] 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.

[1607] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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).

[1612] 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.

[1613] 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."

[1614] 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.

[1615] 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).

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] The following is further disclosed regarding the above embodiment.

[1627] (Claim 1)

[1628] a means of recording a customer's past purchase history, favorite items, physical data, and style preferences;

[1629] means for analyzing customer characteristics using said recorded data;

[1630] A means for proposing optimal fashion and makeup items to the customer based on the analysis results;

[1631] A system including:

[1632] (Claim 2)

[1633] 10. The system of claim 1, further comprising means for inputting new data from the customer.

[1634] (Claim 3)

[1635] The system of claim 1 , further comprising: means for predicting a customer's style based on the analysis using a machine learning model.

[1636] "Example 1"

[1637] (Claim 1)

[1638] a means of recording a customer's past purchase history, favorite items, physical data, and style preferences;

[1639] means for analyzing customer characteristics using said recorded data;

[1640] means for using the analysis results to train a machine learning model to predict a customer's style;

[1641] A means for proposing optimal fashion and makeup items to a customer based on the prediction results of the machine learning model;

[1642] means for allowing a customer to input new information and for receiving and processing said new information;

[1643] means for displaying the proposal results to a user;

[1644] A system including:

[1645] (Claim 2)

[1646] 10. The system of claim 1, further comprising means for inputting updated physical data and preferences from the customer.

[1647] (Claim 3)

[1648] 10. The system of claim 1, further comprising means for performing label encoding and scaling of customer data as data preprocessing.

[1649] "Application Example 1"

[1650] (Claim 1)

[1651] a means of recording a customer's past purchase history, favorite items, physical data, and style preferences;

[1652] means for analyzing customer characteristics using said recorded data;

[1653] A means for proposing optimal fashion and makeup items to the customer based on the analysis results;

[1654] a means for providing an interface through which the customer can input new data;

[1655] A means of predicting and suggesting styles in real time based on input data;

[1656] a means for displaying the predicted style to the customer using a smartphone;

[1657] A system including:

[1658] (Claim 2)

[1659] 10. The system of claim 1, further comprising means for inputting new data from the customer.

[1660] (Claim 3)

[1661] The system of claim 1 , further comprising: means for predicting a customer's style based on the analysis using a machine learning model.

[1662] "Example 2: Combining Emotion Engines"

[1663] (Claim 1)

[1664] a means of recording a customer's past purchase history, favorite items, physical data, and style preferences;

[1665] means for recording emotion data with an emotion engine that recognizes the emotion of a user;

[1666] means for analyzing customer characteristics using said recorded data;

[1667] A means of predicting customer style using machine learning models;

[1668] a means for proposing optimal fashion and makeup items to a customer based on the prediction results and emotion data;

[1669] A system including:

[1670] (Claim 2)

[1671] 10. The system of claim 1, further comprising means for inputting new data and sentiment data from the customer.

[1672] (Claim 3)

[1673] 10. The system of claim 1, further comprising means for optimizing the suggestion results by taking into account the sentiment data.

[1674] "Application example 2 when combining emotion engines"

[1675] (Claim 1)

[1676] a means for recording a customer's past purchase history, favorite items, physical data, style preferences, and emotional state;

[1677] means for analyzing customer characteristics using said recorded data;

[1678] means for recognizing a user's emotion using an emotion recognition engine;

[1679] means for predicting a customer's style based on said analysis using a machine learning model;

[1680] means for suggesting optimal fashion and makeup items to a customer based on the prediction results and emotion data;

[1681] A system including:

[1682] (Claim 2)

[1683] 10. The system of claim 1, further comprising means for inputting new data from the customer.

[1684] (Claim 3)

[1685] 10. The system of claim 1, further comprising a smartphone application for displaying the optimal fashion and makeup items. [Explanation of symbols]

[1686] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of recording a customer's past purchase history, favorite items, physical data, and style preferences; means for analyzing customer characteristics using said recorded data; A means for proposing optimal fashion and makeup items to the customer based on the analysis results; A system including:

2. 10. The system of claim 1, further comprising means for inputting new data from a customer.

3. The system of claim 1 , further comprising: means for predicting a customer's style based on the analysis using a machine learning model.

Images