System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting historical purchasing data for a user; means for collecting historical browsing data for the user; means for analyzing the historical purchasing data and the historical browsing data to determine purchasing habits of the user; means for generating purchasing advice for the user based on the determined purchasing habits; means for sending the generated purchasing advice to a terminal of the user; and means for receiving a response of the user and adding a specified product to a cart based on the response.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While online shopping is convenient, the large number of options and brands available means that it typically takes time and effort for users to find the perfect product. A particular problem is that it is difficult to receive recommendations that fully reflect a user's individual purchasing history and trends, hindering an efficient shopping experience. Therefore, there is a need for a system that analyzes a user's purchasing history and browsing history and provides efficient purchasing advice based on that information. [Means for solving the problem]

[0005] This invention solves the above-mentioned problems by providing a system including: means for collecting purchase history data for each user; means for collecting browsing history data for each user; means for analyzing the purchase history data and browsing history data to identify the user's purchasing tendencies; means for generating purchasing advice for the user based on the identified purchasing tendencies; means for sending the generated purchasing advice to the user's terminal; and means for receiving the user's response and adding specified products to a cart based on the response. Furthermore, this system has means for including discount information in the purchasing advice and means for presenting the generated purchasing advice to the user in a chat format, further improving the user's shopping experience.

[0006] "Purchase history data" refers to data that includes information about products purchased by a user in the past.

[0007] "Browse history data" refers to data that includes information about products viewed by a user on an online shop.

[0008] "Purchase trends" refers to the purchasing patterns and preferences that a user has demonstrated in the past.

[0009] "Buying advice" is information about products and offers suggested based on a user's purchasing habits.

[0010] An "add to cart means" is a method or process by which a user places selected items into the cart of an online purchasing system.

[0011] "Discount information" is information about price discounts and coupons for products.

[0012] "Chat format" refers to a communication method in which the user and the system interact through text.

[0013] "User Device" means the electronic device used by a User to access the System and receive and send information. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention relates to an online shopping support system that streamlines the user's shopping experience. This system analyzes the user's purchase history and browsing history and provides optimal purchasing advice. The following explains how the program of this system works.

[0036] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0037] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0038] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now."

[0039] Furthermore, when the user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart.

[0040] As a concrete example, consider a user named Tanaka who has purchased five shirts from a particular brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection, generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. If Tanaka responds "Yes," the server automatically adds the item to Tanaka's cart and assists in the purchase process.

[0041] As described above, the system analyzes users' past data and provides personalized purchasing advice, resulting in an efficient online shopping experience.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] The server retrieves the user's purchase history data from the database.

[0045] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0046] Step 2:

[0047] The server retrieves the user's browsing history data from the database.

[0048] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0049] Step 3:

[0050] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0051] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0052] Step 4:

[0053] The server generates optimal purchasing advice for the user based on the analysis results.

[0054] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0055] Step 5:

[0056] The server generates purchasing advice and sends it to the user's terminal.

[0057] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0058] Step 6:

[0059] The user responds to the advice from the bot.

[0060] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0061] Step 7:

[0062] The server parses the user's response and adds the specified product to the cart based on the response.

[0063] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[0064] Step 8:

[0065] The server assists the user in simplifying the purchasing process.

[0066] What it does: Autofills user purchase history, address information, and more, making the purchasing process easier.

[0067] Example 1

[0068] 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."

[0069] In recent years, with the spread of online shopping, many users are purchasing products via the Internet. However, the diversification of products has made user purchasing behavior increasingly complex, creating a need for quickly suggesting the most suitable products for each user. However, conventional systems have difficulty analyzing individual users' purchasing trends and providing appropriate purchasing advice, hindering improvements to the user experience. For this reason, there is a need for a system that can effectively collect and analyze users' purchasing and browsing histories and generate and provide optimal purchasing advice for each user.

[0070] 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.

[0071] In this invention, the server includes means for collecting purchase history data for each user from multiple data sources, means for collecting browsing history data for each user, means for identifying the user's purchasing tendencies using data analysis software based on the collected data, means for generating purchasing advice for the user using a generative AI model based on the identified purchasing tendencies, means for sending the generated purchasing advice to the user's terminal in chat format, and means for receiving the user's response, executing a corresponding action using a natural language processing model, and adding a specified product to a cart. This makes it possible to effectively utilize the user's past data and quickly provide individual purchasing advice.

[0072] "Data source" refers to the source of information extracted for collecting purchase history data and browsing history data, and refers to multiple data sources such as online shopping platforms, emails, and web browser history.

[0073] "Purchase history data" refers to data that includes detailed information about products purchased by a user in the past, such as the purchase date and time, price, and store.

[0074] "Browsing history data" refers to data that includes information about products viewed by a user using a web browser or application, the date and time of viewing, the URL of the page viewed, etc.

[0075] "Data analysis software" refers to analytical tools used to identify user purchasing trends based on collected data, and refers to data analysis libraries such as Python's Pandas and Scikit-learn.

[0076] A "generative AI model" is an artificial intelligence model used to generate purchasing advice in natural language based on a user's purchasing habits, and refers to advanced natural language processing models such as GPT-3.

[0077] "Chat" refers to providing information or advice to users in an interactive format, such as through text messages or an in-app chat window.

[0078] "Natural language processing model" refers to an artificial intelligence model used to analyze a user's text response and perform corresponding actions, and refers to natural language processing technologies such as BERT and GPT-3.

[0079] "Cart" refers to a virtual shopping basket on an online shopping platform that temporarily holds items you wish to purchase.

[0080] This invention relates to an online shopping support system that improves the efficiency of a user's shopping experience. The system is configured as follows, with a server, terminals, and users each playing a specific role.

[0081] First, the server uses cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) to collect data, and collects purchase history and browsing history data from multiple data sources. This includes information on products purchased and viewed by users. For example, it executes an SQL query to retrieve purchase history from a database and uses an API to retrieve browser browsing history.

[0082] The server then analyzes the collected data using data analysis libraries such as Python's Pandas and Scikit-learn to identify each user's purchasing trends, including purchasing frequency analysis for each brand, purchasing trends analysis for each product category, and seasonal purchasing trends using time series analysis.

[0083] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for the user. For example, if a user tends to frequently purchase products from a particular brand, the server will prioritize providing that brand's latest products and sale information. In this case, the server inputs the following prompt into the generative AI model: "Generate optimal purchasing advice based on the user's purchase history and browsing history. For example, notify a user who has purchased shirts from brand A five times in the past of information about new shirt sales."

[0084] The generated purchasing advice is sent from the server to the user's device in the form of a chat message, such as an email, SMS, or in-app notification. For example, a message like, "Hello, new items from Brand A that you've been interested in are now 30% off. Please consider purchasing now."

[0085] The user receives advice sent from the server using a device (e.g., a smartphone or PC). When the user responds to the advice, the server receives the response, analyzes it using a Natural Language Processing (NLP) model, and executes the corresponding action.

[0086] For example, if the user responds "Yes, I'd like to purchase," the server automatically adds the item to the user's cart and assists in the purchase process, including payment processing and shipping arrangements. Payments are processed using APIs from Stripe or PayPal, and shipping arrangements are made using APIs linked to shipping companies.

[0087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0088] Step 1: Data collection

[0089] The server uses databases and APIs to collect user purchase and browsing history data from multiple data sources. The input is a database query or API request, and the output is a dataset of purchase and browsing history for each user. Specifically, the server executes SQL queries to retrieve purchase history from the database and uses API requests to retrieve browser browsing history.

[0090] Step 2: Data Preprocessing

[0091] The server preprocesses the collected data for data analysis. The input of this step is the raw data collected, and the output is a clean dataset that can be analyzed. Specifically, the server handles missing values ​​and converts the data into the required format, for example, converting text data into categorical data.

[0092] Step 3: Data analysis

[0093] The server then analyzes the preprocessed data using Python data analysis libraries such as Pandas and Scikit-learn. The input for this step is a clean dataset, and the output is data showing each user's purchasing habits. Specifically, the server performs clustering and time series analysis to identify purchasing frequencies and patterns.

[0094] Step 4: Generate buying advice

[0095] The server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for each user based on the analysis results. The input to this step is the analysis result data, and the output is purchasing advice expressed in natural language. Specifically, the server inputs a prompt sentence into the generative AI model and obtains the generated text message. An example of a prompt sentence is: "Please generate optimal purchasing advice based on the user's purchase history and browsing history."

[0096] Step 5: Send advice

[0097] The server sends the generated purchasing advice to the user's device. The input of this step is the generated text message, and the output is the notification sent to the user's device. Specifically, the server retrieves the user's device information from the database and sends the message using an SMTP server or push notification service.

[0098] Step 6: Receiving user response

[0099] The user responds to the advice sent from the server. The input of this step is the user's response message, and the output is the response data received by the server. Specifically, the user enters a text message using a smartphone or PC.

[0100] Step 7: Parse and process the response

[0101] The server analyzes the user's response and performs an action based on it. The input of this step is the user's response data, and the output is a specific action (e.g., adding an item to cart). Specifically, the server uses a Natural Language Processing (NLP) model to analyze the text and perform the corresponding action (e.g., adding an item to cart).

[0102] Step 8: Checkout

[0103] After the user confirms the purchase, the server automatically proceeds with the purchase process. The input of this step is the purchase confirmation information, and the output is the completion of the purchase and the completion of delivery arrangements. Specifically, the server securely transmits payment information, sends a purchase confirmation email to the user, and processes the delivery via an API with the delivery company.

[0104] (Application example 1)

[0105] 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."

[0106] Conventional online shopping systems have difficulty providing efficient purchasing advice by properly utilizing users' purchase and browsing histories. As a result, users spend a great deal of time and effort searching for the right product, resulting in a decline in satisfaction. Furthermore, they lacked functionality to provide useful advice to users, such as specific brand or discount information, creating a demand for a more efficient and personalized shopping experience.

[0107] 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.

[0108] In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, means for transmitting the generated purchasing advice to the user's terminal, means for receiving the user's response and adding specified products to a cart based on the response, and means for obtaining offer information for specific brands based on the user's purchasing tendencies and including the obtained offer information in the generated purchasing advice. This enables users to efficiently find products and offers that are best suited to them, thereby improving and personalizing the shopping experience.

[0109] "Purchase history data" is information about products and services purchased by a user in the past.

[0110] "Browsing history data" is information about products and services that a user has previously viewed online.

[0111] "Purchase trends" are patterns of products and brands that a user is particularly interested in, identified from the user's purchase history and browsing history.

[0112] "Purchase advice" is recommended information for products and services provided to users based on the user's purchasing trends.

[0113] "User's device" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0114] A "cart" is a virtual shopping basket that temporarily stores items to be purchased when shopping online.

[0115] A "specific brand" refers to a brand that a user has frequently selected in their past purchasing or browsing history.

[0116] "Offer information" refers to information about discounts and special offers offered for specific products or brands.

[0117] "Chat style" refers to a style in which a user communicates with a system via a text-based interactive interface.

[0118] This invention is an online shopping support system that analyzes a user's purchase history and browsing history to provide optimal purchasing advice. The main components of the system are a server, a user terminal, and a program for analysis and advice generation.

[0119] The server collects purchase history data and browsing history data from multiple data sources. Specifically, it retrieves information about products the user has previously purchased and viewed from a database. This can be done using cloud services (e.g., AWS or Google Cloud). The server uses this data to perform analysis to identify individual purchasing trends for each user.

[0120] The analysis is performed automatically by a program written in Python, which uses the requests library to process HTTP requests. It aggregates data on purchase and browsing history to identify patterns of brands and products that users frequently purchase. Based on the analysis results, it obtains offer information for specific brands and products and generates purchasing advice.

[0121] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now." When the user responds to the advice, the server receives the response and automatically adds the specified product to the cart.

[0122] As a concrete example, suppose user A has purchased a particular brand five times in the past year. When user A starts shopping again, the server provides the latest sale information for the brand and generates a message such as, "New items from the brand you often buy are now 30% off." This message is delivered to user A, and if user A responds "Yes," the product is added to the cart.

[0123] An example prompt is:

[0124] "Generate purchasing advice based on user A's purchase and browsing history. Recommend new offers for brands that user A has previously purchased."

[0125] This invention allows users to efficiently find the products and special offers that are best suited to them, improving their shopping experience and saving time.

[0126] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0127] Step 1: Collect user purchase and browsing history data

[0128] The server collects information about products that a user has previously purchased or viewed from a database. The input is the user ID, and the output is purchase history data and browsing history data. Specifically, it uses a cloud service (such as AWS or Google Cloud) to obtain the necessary data via an API.

[0129] Step 2: Analyze purchase and browsing history data

[0130] The server analyzes the collected data to identify users' purchasing trends. The input is purchase history data and browsing history data, and the output is the user's purchasing trend patterns. This analysis is performed using a Python script to compile a list of frequently purchased brands and products.

[0131] Step 3: Generate buying advice based on identified buying trends

[0132] The server generates purchasing advice based on the user's purchasing trends from the analysis results. The input is the purchasing trend pattern, and the output is purchasing advice. For example, it obtains the latest sales information for brands that the user frequently purchases and generates an advice message.

[0133] Step 4: Send purchasing advice to the user's device

[0134] The server sends the generated purchasing advice to the user's smartphone or PC. The input is the purchasing advice message, and the output is the advice displayed on the user's device. Specifically, the message is displayed in chat format so that the user can easily check it.

[0135] Step 5: Receive and process the user's response

[0136] The server receives the user's response and determines the next action based on the response. The input is the user's response, and the output is the execution of the corresponding action. For example, if the user responds "yes," add the specified product to the cart.

[0137] Step 6: Add the specified product to your cart

[0138] The server automatically adds the specified product to the cart based on the user's response. The input is the product information included in the purchase advice and the user's response, and the output is the updated cart status. Specifically, the product is added to the user's cart, and the purchase process is supported.

[0139] The processing steps of this program enable the user to receive optimal shopping advice based on his or her purchasing tendencies and to purchase products efficiently.

[0140] 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.

[0141] This invention relates to an online shopping support system that streamlines users' shopping experiences and provides personalized services. This system not only analyzes users' purchase and browsing histories to provide optimal purchasing advice, but also recognizes users' emotions by combining it with an emotion engine and adjusts purchasing advice based on the results.

[0142] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0143] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0144] Furthermore, the system incorporates an emotion engine, which allows the server to recognize the user's emotions in real time. The emotion engine analyzes the user's text input, voice, or facial expressions to determine their emotions. Based on this emotion determination, the server can adjust the purchasing advice it generates.

[0145] For example, if a user inputs "I'm feeling sad today" while interacting with a chatbot, the server can recognize that emotion through its emotion engine and provide more comforting advice or suggestions based on the user's mood. Also, if the user's facial expression recognized through the camera on their smartphone or PC is a smile, the server can use that information to send a positive message.

[0146] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. As a concrete example, let's say a user named Tanaka has purchased five shirts from a specific brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection and generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends this to the user's device. Furthermore, if it is determined that Tanaka is in a relatively good mood, an additional message such as, "It's a good day today! We also recommend this shirt." is sent.

[0147] When the user responds to the advice from the bot, the server receives the response and executes the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. The server also automatically enters the necessary information to simplify the user's purchasing process, allowing them to complete the purchase smoothly.

[0148] As described above, this system not only analyzes users' past data and provides personalized purchasing advice, but also incorporates an emotion engine to provide more effective advice based on the user's emotions.

[0149] The processing flow will be explained below.

[0150] Step 1:

[0151] The server retrieves the user's purchase history data from the database.

[0152] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0153] Step 2:

[0154] The server retrieves the user's browsing history data from the database.

[0155] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0156] Step 3:

[0157] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0158] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0159] Step 4:

[0160] The server generates optimal purchasing advice for the user based on the analysis results.

[0161] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0162] Step 5:

[0163] The server uses an emotion engine to collect data to recognize the user's emotions.

[0164] Specific operation: Collects emotion data through text input, voice input, or facial expression analysis and passes it to the emotion engine.

[0165] Step 6:

[0166] The emotion engine analyzes the collected data and identifies the user's emotions.

[0167] What it does: Uses natural language processing and machine learning algorithms to determine emotions from a user's text, voice, or facial expressions.

[0168] Step 7:

[0169] The server adjusts purchasing advice based on the analysis results of the emotion engine.

[0170] Specific behavior: The recommended product list and message content are flexibly changed based on the user's emotional data. For example, if the user is sad, the system will recommend encouraging messages or products with a relaxing effect.

[0171] Step 8:

[0172] The server generates purchasing advice and sends it to the user's terminal.

[0173] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0174] Step 9:

[0175] The user responds to the advice from the bot.

[0176] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0177] Step 10:

[0178] The server parses the user's response and adds the specified product to the cart based on the response.

[0179] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[0180] Step 11:

[0181] The server assists the user in simplifying the purchasing process.

[0182] Specific operation: The auto-fill function completes the user's purchase history, address information, etc., allowing them to complete the purchase process smoothly.

[0183] Example 2

[0184] 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."

[0185] Conventional online shopping support systems can provide advice based on a user's purchasing and browsing history, but they have the problem of being unable to provide appropriate advice that takes into account the user's emotional state. Furthermore, it is difficult to respond in real time based on the user's reactions, limiting the ability to personalize the shopping experience. Therefore, there is a need for a system that can recognize a user's emotions and provide appropriate advice in real time.

[0186] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion analysis means for recognizing the user's emotions, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This makes it possible to provide personalized advice that takes the user's emotional state into consideration in real time.

[0187] "Purchase history data" is information about products and services purchased by a user in the past.

[0188] "Browser history data" is information about products and services that a user has viewed in the past.

[0189] "Analysis" refers to the act of processing and analyzing data to identify users' purchasing trends using purchase history data and browsing history data.

[0190] "Buying habits" are patterns of a user's preferences and interests that are identified based on the user's past purchasing and browsing behavior.

[0191] "Purchase advice" is information recommending optimal products and services to users based on the analysis results.

[0192] "Emotion analysis" is a technology that analyzes a user's text, voice, facial expressions, etc. to recognize their emotional state.

[0193] "Emotion recognition result" is information on the user's emotional state derived through emotion analysis.

[0194] "User terminal" means an electronic device used by a User to interact with the System, including a smartphone or personal computer.

[0195] "Add to cart" refers to the act of a user registering information about a product they wish to purchase in their online shopping cart.

[0196] "Adjustment" refers to the act of optimizing the content of generated purchasing advice in consideration of the emotion recognition results.

[0197] This invention is a system for streamlining a user's online shopping experience and providing personalized services. The system not only analyzes a user's purchase history and browsing history to generate optimal purchasing advice, but also incorporates an emotion engine to recognize the user's emotions and adjust the advice based on the results.

[0198] First, the server collects user purchase history and browsing history data from multiple data sources. This data includes information on products purchased and viewed by users. This data is retrieved from the API using the Python requests library and stored in a MySQL database.

[0199] The server then analyzes the collected data to identify each user's purchasing habits using machine learning algorithms, particularly clustering and classification algorithms, Python's scikit-learn library, and SQL aggregation queries.

[0200] The server then generates optimal purchasing advice for the user based on the analysis results. This process utilizes natural language generation (NLG) technology, template-based generative models, and statistical NLP techniques. For example, it generates advice that prioritizes product information for frequently purchased brands.

[0201] The server also uses an emotion engine to recognize users' emotions in real time. Emotion recognition uses machine learning models and natural language processing techniques to analyze users' text input, voice, and facial expressions. Specifically, it uses Python's nltk library and TensorFlow-based machine learning models.

[0202] Based on the emotion determination, the server adjusts the generated purchasing advice. For example, if the user inputs "I'm feeling sad today," the advice can be changed to a comforting message. Conversely, if the emotion engine determines that the user is in a relatively good mood, a positive message can be added.

[0203] The generated purchasing advice is sent from the server to the user's device, where the user can receive the advice in chat format via their smartphone or personal computer.

[0204] For example, if a user has purchased a particular brand of shirt five times in the past year, the server analyzes the brand's new collection and generates a message saying, "Hey, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. Furthermore, if the server determines that the user is in a relatively good mood, it sends an additional message saying, "It's a good day today! We also recommend this shirt."

[0205] When a user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. Furthermore, the server automatically fills in the necessary information, allowing the user to complete the purchase process smoothly.

[0206] Example prompt sentence:

[0207] "Add positive messages if the user is in a good mood."

[0208] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0209] Step 1:

[0210] The server collects user purchase history data and browsing history data from multiple data sources. Specifically, it executes API calls to retrieve purchase history data using the requests library and stores it in a MySQL database. The input of this process is purchase and browsing history data from each data source, and the output is the history data stored in the database.

[0211] Specific behavior:

[0212] The server sends a request to an API endpoint to retrieve the user's past purchases, which are then stored in a corresponding table in a MySQL database.

[0213] Step 2:

[0214] The server analyzes the collected data and identifies each user's purchasing trends. It uses Python's scikit-learn library to run machine learning algorithms to perform clustering and classification. The input for this process is the purchase history data and browsing history data stored in the database, and the output is the results of an analysis of each user's purchasing trends.

[0215] Specific behavior:

[0216] The server uses SQL queries to retrieve purchase and browsing history data, then applies machine learning algorithms to analyze user purchasing patterns. The results of the purchasing trend analysis are stored in a table.

[0217] Step 3:

[0218] The server generates optimal purchasing advice for the user based on the analysis results. It uses natural language generation (NLG) technology to generate advice based on the user's purchasing patterns. The input to this process is the analysis results of the user's purchasing habits, and the output is the generated purchasing advice message.

[0219] Specific behavior:

[0220] The server uses a template-based generative model to generate messages based on the user's purchasing history and trends, for example, "Mr. / Ms. XX, Product A, which you previously purchased, is now on sale again."

[0221] Step 4:

[0222] The server performs emotion analysis to recognize user emotions. It analyzes multiple data sources, including text input, voice, and facial expressions, and determines emotions using Python's nltk library and TensorFlow-based machine learning models. The input for this process is the user's text and voice data, and the output is the emotion recognition results.

[0223] Specific behavior:

[0224] The server analyzes the user's text input received via the chatbot and identifies emotions such as "happiness" or "sadness" through an emotion engine. The results of emotion recognition are stored in an internal data structure.

[0225] Step 5:

[0226] The server adjusts the generated purchasing advice content based on the emotion recognition results, adding encouraging messages for positive emotions and comforting messages for negative emotions. The inputs to this process are the emotion recognition results and the generated purchasing advice message, and the output is the adjusted purchasing advice message.

[0227] Specific behavior:

[0228] When a user types "I'm sad today," the server generates and adds a comforting message such as "Today may have been a tough day, but I recommend this product" to the original advice.

[0229] Step 6:

[0230] The server sends the adjusted purchasing advice to the user's device. Webhooks and API endpoints are used to send messages. Specifically, messages converted into JSON format are sent. The input to this process is the adjusted purchasing advice message, and the output is the advice message displayed on the user's device.

[0231] Specific behavior:

[0232] The server converts the generated advice message into JSON format and sends it to the user's smartphone or personal computer.

[0233] Step 7:

[0234] When the user responds to the advice from the bot, the server receives the response and performs the appropriate action. For example, if the response is "Yes, I'll buy it," the specified product is automatically added to the cart. The input of this process is the response message from the user, and the output is the information about the product added to the cart.

[0235] Specific behavior:

[0236] When the user responds "I'll buy it," the server receives the response, updates the database to check the availability of the corresponding product, automatically adds it to the cart, and automatically enters the necessary information for the purchase process to complete the process.

[0237] (Application example 2)

[0238] 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."

[0239] Conventional online shopping systems can provide purchasing advice based on a user's purchase and browsing history, but it is difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, they lack the ability to grasp and flexibly respond to changes in a user's emotions in real time. As a result, they are unable to improve the user's shopping experience and are unable to provide appropriate purchase promotions.

[0240] The identification process 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 collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion recognition means for recognizing the user's emotions in real time, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This enables personalized purchasing advice based on the user's emotional state, improving the user's shopping experience and promoting purchases more effectively.

[0241] "Purchase history data" refers to information about products purchased by a user in the past.

[0242] "Browser history data" refers to information about products viewed by a user on an online shopping site.

[0243] "Purchase trends" refer to a user's product selection patterns and preferences, which are identified by analyzing purchase history data and browsing history data.

[0244] "Buying advice" refers to product information and offers suggested to users based on their purchasing habits.

[0245] "Emotion recognition" refers to technology that analyzes a user's text input, voice input, or facial expressions to determine the user's emotional state.

[0246] "Emotion recognition means" refers to a technical method or device for detecting a user's emotions in real time and determining the emotion data.

[0247] A "terminal" is a device that a user uses to interface with an online shopping system, specifically a smartphone or PC.

[0248] A "cart" refers to a virtual shopping basket on an online shopping site that temporarily stores items that a user intends to purchase.

[0249] The system of the present invention is configured to collect user purchase history data and browsing history data, analyze this data, and provide optimal purchasing advice to the user. The system also recognizes the user's emotions in real time and adjusts purchasing advice based on the emotions. The components for realizing this system are described below.

[0250] Hardware and Software

[0251] 1. Hardware

[0252] Server: Responsible for data collection, analysis, emotion recognition, and purchase advice generation.

[0253] User device: A device, such as a smartphone or PC, through which a user interacts with the system.

[0254] 2. Software

[0255] User data acquisition module: Collects user purchase history data and browsing history data.

[0256] Analytics module: Analyzes collected data and identifies user purchasing trends.

[0257] Emotion Recognition Module: Recognizes emotions by analyzing the user's text input, voice input, or facial expressions.

[0258] Purchase advice generation module: Generates optimal purchase advice based on purchasing trends and emotion recognition results.

[0259] Data Processing and Computation

[0260] User Data Collection

[0261] The server uses the "user data acquisition module" to acquire the user's purchase history data and browsing history data, including information on products purchased and viewed in the past.

[0262] Data analysis

[0263] The server uses an "analysis module" to analyze the collected purchase history data and browsing history data, which allows the server to identify each user's purchasing trends.

[0264] Emotion recognition

[0265] When a user inputs text, voice, or shows a facial expression in front of the camera, the server uses an "emotion recognition module" to recognize the emotion in real time.

[0266] Generate buying advice

[0267] The server uses a "purchase advice generation module" to generate optimal purchase advice based on the user's purchasing tendencies and emotion recognition results.

[0268] Specific examples

[0269] Usage example 1:

[0270] 1. User A's purchase history data: User A has purchased a shirt from a specific brand X five times in the past year.

[0271] 2. User A's browsing history data: Recently, he has been browsing the new collection of Brand X.

[0272] Prompt statement (example):

[0273] I'm feeling a bit down today. What items would you recommend?

[0274] The server uses an emotion recognition module to analyze the text "I'm feeling a bit down today" and determine User A's emotional state as "sad."

[0275] The server then uses the "purchase advice generation module" based on the analysis and emotion recognition results to generate personalized purchase advice, such as:

[0276] Brand X's new shirts are on sale for 30% off. We're sure you'll find something perfect for you! Cheer up!

[0277] In this way, optimal purchasing advice can be provided according to the user's emotional state, improving the user's shopping experience and effectively promoting purchases.

[0278] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0279] Step 1:

[0280] The server uses the user data acquisition module to collect the user's purchase history data and browsing history data. This involves information on products the user has previously purchased and viewed. (Input) Purchase history data, browsing history data. This provides basic data for understanding the user's purchasing trends. (Output) Collected purchase history data and browsing history data.

[0281] Step 2:

[0282] The server uses an analysis module to analyze the collected purchase history data and browsing history data. This analysis identifies each user's purchasing trends. (Input) Purchase history data and browsing history data collected in step 1. (Output) Identified purchasing trend data. This clarifies the user's preferences and purchasing patterns.

[0283] Step 3:

[0284] When a user inputs text, voice, or shows facial expressions in front of the camera, the server uses the emotion recognition module to recognize the emotion in real time. (Input) User's text, voice, or facial expression data. (Output) Recognized emotion data. This allows the user's current emotional state to be understood.

[0285] Step 4:

[0286] The server uses a purchasing advice generation module to generate optimal purchasing advice based on the user's purchasing tendency data and emotion recognition results. (Input) The purchasing tendency data identified in step 2, the emotion data recognized in step 3. (Output) The generated purchasing advice. This advice is related to the user's past purchasing tendency and current emotional state.

[0287] Step 5:

[0288] The user's terminal receives the purchasing advice sent from the server and presents it to the user. (Input) Purchasing advice sent from the server. (Output) Purchasing advice message presented to the user. Here, the user can check the advice content and respond if necessary.

[0289] Step 6:

[0290] The server receives the user's response and adds the specified product to the cart based on the response. (Input) User response data. (Output) Product data added to the cart. This makes the user's purchasing process even smoother.

[0291] To give a concrete example, suppose a user inputs a prompt such as, "I'm feeling a bit down today. What item would you recommend?" This input is analyzed by the server, and the emotion recognition module determines that the emotion is "sad." As a result, a message to cheer the user up is suggested along with information that a new shirt from brand X, which the user previously purchased, is on discount. This series of processes is carried out in real time, providing the user with appropriate purchasing advice.

[0292] 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.

[0293] 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.

[0294] 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.

[0295] [Second embodiment]

[0296] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0297] 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.

[0298] 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).

[0299] 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.

[0300] 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.

[0301] 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).

[0302] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0303] 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.

[0304] 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.

[0305] 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.

[0306] 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.

[0307] 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."

[0308] This invention relates to an online shopping support system that streamlines the user's shopping experience. This system analyzes the user's purchase history and browsing history and provides optimal purchasing advice. The following explains how the program of this system works.

[0309] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0310] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0311] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now."

[0312] Furthermore, when the user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart.

[0313] As a concrete example, consider a user named Tanaka who has purchased five shirts from a particular brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection, generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. If Tanaka responds "Yes," the server automatically adds the item to Tanaka's cart and assists in the purchase process.

[0314] As described above, the system analyzes users' past data and provides personalized purchasing advice, resulting in an efficient online shopping experience.

[0315] The processing flow will be explained below.

[0316] Step 1:

[0317] The server retrieves the user's purchase history data from the database.

[0318] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0319] Step 2:

[0320] The server retrieves the user's browsing history data from the database.

[0321] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0322] Step 3:

[0323] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0324] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0325] Step 4:

[0326] The server generates optimal purchasing advice for the user based on the analysis results.

[0327] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0328] Step 5:

[0329] The server generates purchasing advice and sends it to the user's terminal.

[0330] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0331] Step 6:

[0332] The user responds to the advice from the bot.

[0333] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0334] Step 7:

[0335] The server parses the user's response and adds the specified product to the cart based on the response.

[0336] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[0337] Step 8:

[0338] The server assists the user in simplifying the purchasing process.

[0339] What it does: Autofills user purchase history, address information, and more, making the purchasing process easier.

[0340] Example 1

[0341] 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."

[0342] In recent years, with the spread of online shopping, many users are purchasing products via the Internet. However, the diversification of products has made user purchasing behavior increasingly complex, creating a need for quickly suggesting the most suitable products for each user. However, conventional systems have difficulty analyzing individual users' purchasing trends and providing appropriate purchasing advice, hindering improvements to the user experience. For this reason, there is a need for a system that can effectively collect and analyze users' purchasing and browsing histories and generate and provide optimal purchasing advice for each user.

[0343] 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.

[0344] In this invention, the server includes means for collecting purchase history data for each user from multiple data sources, means for collecting browsing history data for each user, means for identifying the user's purchasing tendencies using data analysis software based on the collected data, means for generating purchasing advice for the user using a generative AI model based on the identified purchasing tendencies, means for sending the generated purchasing advice to the user's terminal in chat format, and means for receiving the user's response, executing a corresponding action using a natural language processing model, and adding a specified product to a cart. This makes it possible to effectively utilize the user's past data and quickly provide individual purchasing advice.

[0345] "Data source" refers to the source of information extracted for collecting purchase history data and browsing history data, and refers to multiple data sources such as online shopping platforms, emails, and web browser history.

[0346] "Purchase history data" refers to data that includes detailed information about products purchased by a user in the past, such as the purchase date and time, price, and store.

[0347] "Browsing history data" refers to data that includes information about products viewed by a user using a web browser or application, the date and time of viewing, the URL of the page viewed, etc.

[0348] "Data analysis software" refers to analytical tools used to identify user purchasing trends based on collected data, and refers to data analysis libraries such as Python's Pandas and Scikit-learn.

[0349] A "generative AI model" is an artificial intelligence model used to generate purchasing advice in natural language based on a user's purchasing habits, and refers to advanced natural language processing models such as GPT-3.

[0350] "Chat" refers to providing information or advice to users in an interactive format, such as through text messages or an in-app chat window.

[0351] "Natural language processing model" refers to an artificial intelligence model used to analyze a user's text response and perform corresponding actions, and refers to natural language processing technologies such as BERT and GPT-3.

[0352] "Cart" refers to a virtual shopping basket on an online shopping platform that temporarily holds items you wish to purchase.

[0353] This invention relates to an online shopping support system that improves the efficiency of a user's shopping experience. The system is configured as follows, with a server, terminals, and users each playing a specific role.

[0354] First, the server uses cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) to collect data, and collects purchase history and browsing history data from multiple data sources. This includes information on products purchased and viewed by users. For example, it executes an SQL query to retrieve purchase history from a database and uses an API to retrieve browser browsing history.

[0355] The server then analyzes the collected data using data analysis libraries such as Python's Pandas and Scikit-learn to identify each user's purchasing trends, including purchasing frequency analysis for each brand, purchasing trends analysis for each product category, and seasonal purchasing trends using time series analysis.

[0356] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for the user. For example, if a user tends to frequently purchase products from a particular brand, the server will prioritize providing that brand's latest products and sale information. In this case, the server inputs the following prompt into the generative AI model: "Generate optimal purchasing advice based on the user's purchase history and browsing history. For example, notify a user who has purchased shirts from brand A five times in the past of information about new shirt sales."

[0357] The generated purchasing advice is sent from the server to the user's device in the form of a chat message, such as an email, SMS, or in-app notification. For example, a message like, "Hello, new items from Brand A that you've been interested in are now 30% off. Please consider purchasing now."

[0358] The user receives advice sent from the server using a device (e.g., a smartphone or PC). When the user responds to the advice, the server receives the response, analyzes it using a Natural Language Processing (NLP) model, and executes the corresponding action.

[0359] For example, if the user responds "Yes, I'd like to purchase," the server automatically adds the item to the user's cart and assists in the purchase process, including payment processing and shipping arrangements. Payments are processed using APIs from Stripe or PayPal, and shipping arrangements are made using APIs linked to shipping companies.

[0360] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0361] Step 1: Data collection

[0362] The server uses databases and APIs to collect user purchase and browsing history data from multiple data sources. The input is a database query or API request, and the output is a dataset of purchase and browsing history for each user. Specifically, the server executes SQL queries to retrieve purchase history from the database and uses API requests to retrieve browser browsing history.

[0363] Step 2: Data Preprocessing

[0364] The server preprocesses the collected data for data analysis. The input of this step is the raw data collected, and the output is a clean dataset that can be analyzed. Specifically, the server handles missing values ​​and converts the data into the required format, for example, converting text data into categorical data.

[0365] Step 3: Data analysis

[0366] The server then analyzes the preprocessed data using Python data analysis libraries such as Pandas and Scikit-learn. The input for this step is a clean dataset, and the output is data showing each user's purchasing habits. Specifically, the server performs clustering and time series analysis to identify purchasing frequencies and patterns.

[0367] Step 4: Generate buying advice

[0368] The server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for each user based on the analysis results. The input to this step is the analysis result data, and the output is purchasing advice expressed in natural language. Specifically, the server inputs a prompt sentence into the generative AI model and obtains the generated text message. An example of a prompt sentence is: "Please generate optimal purchasing advice based on the user's purchase history and browsing history."

[0369] Step 5: Send advice

[0370] The server sends the generated purchasing advice to the user's device. The input of this step is the generated text message, and the output is the notification sent to the user's device. Specifically, the server retrieves the user's device information from the database and sends the message using an SMTP server or push notification service.

[0371] Step 6: Receiving user response

[0372] The user responds to the advice sent from the server. The input of this step is the user's response message, and the output is the response data received by the server. Specifically, the user enters a text message using a smartphone or PC.

[0373] Step 7: Parse and process the response

[0374] The server analyzes the user's response and performs an action based on it. The input of this step is the user's response data, and the output is a specific action (e.g., adding an item to cart). Specifically, the server uses a Natural Language Processing (NLP) model to analyze the text and perform the corresponding action (e.g., adding an item to cart).

[0375] Step 8: Checkout

[0376] After the user confirms the purchase, the server automatically proceeds with the purchase process. The input of this step is the purchase confirmation information, and the output is the completion of the purchase and the completion of delivery arrangements. Specifically, the server securely transmits payment information, sends a purchase confirmation email to the user, and processes the delivery via an API with the delivery company.

[0377] (Application example 1)

[0378] 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."

[0379] Conventional online shopping systems have difficulty providing efficient purchasing advice by properly utilizing users' purchase and browsing histories. As a result, users spend a great deal of time and effort searching for the right product, resulting in a decline in satisfaction. Furthermore, they lacked functionality to provide useful advice to users, such as specific brand or discount information, creating a demand for a more efficient and personalized shopping experience.

[0380] 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.

[0381] In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, means for transmitting the generated purchasing advice to the user's terminal, means for receiving the user's response and adding specified products to a cart based on the response, and means for obtaining offer information for specific brands based on the user's purchasing tendencies and including the obtained offer information in the generated purchasing advice. This enables users to efficiently find products and offers that are best suited to them, thereby improving and personalizing the shopping experience.

[0382] "Purchase history data" is information about products and services purchased by a user in the past.

[0383] "Browsing history data" is information about products and services that a user has previously viewed online.

[0384] "Purchase trends" are patterns of products and brands that a user is particularly interested in, identified from the user's purchase history and browsing history.

[0385] "Purchase advice" is recommended information for products and services provided to users based on the user's purchasing trends.

[0386] "User's device" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0387] A "cart" is a virtual shopping basket that temporarily stores items to be purchased when shopping online.

[0388] A "specific brand" refers to a brand that a user has frequently selected in their past purchasing or browsing history.

[0389] "Offer information" refers to information about discounts and special offers offered for specific products or brands.

[0390] "Chat style" refers to a style in which a user communicates with a system via a text-based interactive interface.

[0391] This invention is an online shopping support system that analyzes a user's purchase history and browsing history to provide optimal purchasing advice. The main components of the system are a server, a user terminal, and a program for analysis and advice generation.

[0392] The server collects purchase history data and browsing history data from multiple data sources. Specifically, it retrieves information about products the user has previously purchased and viewed from a database. This can be done using cloud services (e.g., AWS or Google Cloud). The server uses this data to perform analysis to identify individual purchasing trends for each user.

[0393] The analysis is performed automatically by a program written in Python, which uses the requests library to process HTTP requests. It aggregates data on purchase and browsing history to identify patterns of brands and products that users frequently purchase. Based on the analysis results, it obtains offer information for specific brands and products and generates purchasing advice.

[0394] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now." When the user responds to the advice, the server receives the response and automatically adds the specified product to the cart.

[0395] As a concrete example, suppose user A has purchased a particular brand five times in the past year. When user A starts shopping again, the server provides the latest sale information for the brand and generates a message such as, "New items from the brand you often buy are now 30% off." This message is delivered to user A, and if user A responds "Yes," the product is added to the cart.

[0396] An example prompt is:

[0397] "Generate purchasing advice based on user A's purchase and browsing history. Recommend new offers for brands that user A has previously purchased."

[0398] This invention allows users to efficiently find the products and special offers that are best suited to them, improving their shopping experience and saving time.

[0399] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0400] Step 1: Collect user purchase and browsing history data

[0401] The server collects information about products that a user has previously purchased or viewed from a database. The input is the user ID, and the output is purchase history data and browsing history data. Specifically, it uses a cloud service (such as AWS or Google Cloud) to obtain the necessary data via an API.

[0402] Step 2: Analyze purchase and browsing history data

[0403] The server analyzes the collected data to identify users' purchasing trends. The input is purchase history data and browsing history data, and the output is the user's purchasing trend patterns. This analysis is performed using a Python script to compile a list of frequently purchased brands and products.

[0404] Step 3: Generate buying advice based on identified buying trends

[0405] The server generates purchasing advice based on the user's purchasing trends from the analysis results. The input is the purchasing trend pattern, and the output is purchasing advice. For example, it obtains the latest sales information for brands that the user frequently purchases and generates an advice message.

[0406] Step 4: Send purchasing advice to the user's device

[0407] The server sends the generated purchasing advice to the user's smartphone or PC. The input is the purchasing advice message, and the output is the advice displayed on the user's device. Specifically, the message is displayed in chat format so that the user can easily check it.

[0408] Step 5: Receive and process the user's response

[0409] The server receives the user's response and determines the next action based on the response. The input is the user's response, and the output is the execution of the corresponding action. For example, if the user responds "yes," add the specified product to the cart.

[0410] Step 6: Add the specified product to your cart

[0411] The server automatically adds the specified product to the cart based on the user's response. The input is the product information included in the purchase advice and the user's response, and the output is the updated cart status. Specifically, the product is added to the user's cart, and the purchase process is supported.

[0412] The processing steps of this program enable the user to receive optimal shopping advice based on his or her purchasing tendencies and to purchase products efficiently.

[0413] 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.

[0414] This invention relates to an online shopping support system that streamlines users' shopping experiences and provides personalized services. This system not only analyzes users' purchase and browsing histories to provide optimal purchasing advice, but also recognizes users' emotions by combining it with an emotion engine and adjusts purchasing advice based on the results.

[0415] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0416] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0417] Furthermore, the system incorporates an emotion engine, which allows the server to recognize the user's emotions in real time. The emotion engine analyzes the user's text input, voice, or facial expressions to determine their emotions. Based on this emotion determination, the server can adjust the purchasing advice it generates.

[0418] For example, if a user inputs "I'm feeling sad today" while interacting with a chatbot, the server can recognize that emotion through its emotion engine and provide more comforting advice or suggestions based on the user's mood. Also, if the user's facial expression recognized through the camera on their smartphone or PC is a smile, the server can use that information to send a positive message.

[0419] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. As a concrete example, let's say a user named Tanaka has purchased five shirts from a specific brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection and generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends this to the user's device. Furthermore, if it is determined that Tanaka is in a relatively good mood, an additional message such as, "It's a good day today! We also recommend this shirt." is sent.

[0420] When the user responds to the advice from the bot, the server receives the response and executes the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. The server also automatically enters the necessary information to simplify the user's purchasing process, allowing them to complete the purchase smoothly.

[0421] As described above, this system not only analyzes users' past data and provides personalized purchasing advice, but also incorporates an emotion engine to provide more effective advice based on the user's emotions.

[0422] The processing flow will be explained below.

[0423] Step 1:

[0424] The server retrieves the user's purchase history data from the database.

[0425] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0426] Step 2:

[0427] The server retrieves the user's browsing history data from the database.

[0428] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0429] Step 3:

[0430] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0431] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0432] Step 4:

[0433] The server generates optimal purchasing advice for the user based on the analysis results.

[0434] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0435] Step 5:

[0436] The server uses an emotion engine to collect data to recognize the user's emotions.

[0437] Specific operation: Collects emotion data through text input, voice input, or facial expression analysis and passes it to the emotion engine.

[0438] Step 6:

[0439] The emotion engine analyzes the collected data and identifies the user's emotions.

[0440] What it does: Uses natural language processing and machine learning algorithms to determine emotions from a user's text, voice, or facial expressions.

[0441] Step 7:

[0442] The server adjusts purchasing advice based on the analysis results of the emotion engine.

[0443] Specific behavior: The recommended product list and message content are flexibly changed based on the user's emotional data. For example, if the user is sad, the system will recommend encouraging messages or products with a relaxing effect.

[0444] Step 8:

[0445] The server generates purchasing advice and sends it to the user's terminal.

[0446] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0447] Step 9:

[0448] The user responds to the advice from the bot.

[0449] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0450] Step 10:

[0451] The server parses the user's response and adds the specified product to the cart based on the response.

[0452] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[0453] Step 11:

[0454] The server assists the user in simplifying the purchasing process.

[0455] Specific operation: The auto-fill function completes the user's purchase history, address information, etc., allowing them to complete the purchase process smoothly.

[0456] Example 2

[0457] 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."

[0458] Conventional online shopping support systems can provide advice based on a user's purchasing and browsing history, but they have the problem of being unable to provide appropriate advice that takes into account the user's emotional state. Furthermore, it is difficult to respond in real time based on the user's reactions, limiting the ability to personalize the shopping experience. Therefore, there is a need for a system that can recognize a user's emotions and provide appropriate advice in real time.

[0459] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion analysis means for recognizing the user's emotions, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This makes it possible to provide personalized advice that takes the user's emotional state into consideration in real time.

[0460] "Purchase history data" is information about products and services purchased by a user in the past.

[0461] "Browser history data" is information about products and services that a user has viewed in the past.

[0462] "Analysis" refers to the act of processing and analyzing data to identify users' purchasing trends using purchase history data and browsing history data.

[0463] "Buying habits" are patterns of a user's preferences and interests that are identified based on the user's past purchasing and browsing behavior.

[0464] "Purchase advice" is information recommending optimal products and services to users based on the analysis results.

[0465] "Emotion analysis" is a technology that analyzes a user's text, voice, facial expressions, etc. to recognize their emotional state.

[0466] "Emotion recognition result" is information on the user's emotional state derived through emotion analysis.

[0467] "User terminal" means an electronic device used by a User to interact with the System, including a smartphone or personal computer.

[0468] "Add to cart" refers to the act of a user registering information about a product they wish to purchase in their online shopping cart.

[0469] "Adjustment" refers to the act of optimizing the content of generated purchasing advice in consideration of the emotion recognition results.

[0470] This invention is a system for streamlining a user's online shopping experience and providing personalized services. The system not only analyzes a user's purchase history and browsing history to generate optimal purchasing advice, but also incorporates an emotion engine to recognize the user's emotions and adjust the advice based on the results.

[0471] First, the server collects user purchase history and browsing history data from multiple data sources. This data includes information on products purchased and viewed by users. This data is retrieved from the API using the Python requests library and stored in a MySQL database.

[0472] The server then analyzes the collected data to identify each user's purchasing habits using machine learning algorithms, particularly clustering and classification algorithms, Python's scikit-learn library, and SQL aggregation queries.

[0473] The server then generates optimal purchasing advice for the user based on the analysis results. This process utilizes natural language generation (NLG) technology, template-based generative models, and statistical NLP techniques. For example, it generates advice that prioritizes product information for frequently purchased brands.

[0474] The server also uses an emotion engine to recognize users' emotions in real time. Emotion recognition uses machine learning models and natural language processing techniques to analyze users' text input, voice, and facial expressions. Specifically, it uses Python's nltk library and TensorFlow-based machine learning models.

[0475] Based on the emotion determination, the server adjusts the generated purchasing advice. For example, if the user inputs "I'm feeling sad today," the advice can be changed to a comforting message. Conversely, if the emotion engine determines that the user is in a relatively good mood, a positive message can be added.

[0476] The generated purchasing advice is sent from the server to the user's device, where the user can receive the advice in chat format via their smartphone or personal computer.

[0477] For example, if a user has purchased a particular brand of shirt five times in the past year, the server analyzes the brand's new collection and generates a message saying, "Hey, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. Furthermore, if the server determines that the user is in a relatively good mood, it sends an additional message saying, "It's a good day today! We also recommend this shirt."

[0478] When a user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. Furthermore, the server automatically fills in the necessary information, allowing the user to complete the purchase process smoothly.

[0479] Example prompt sentence:

[0480] "Add positive messages if the user is in a good mood."

[0481] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0482] Step 1:

[0483] The server collects user purchase history data and browsing history data from multiple data sources. Specifically, it executes API calls to retrieve purchase history data using the requests library and stores it in a MySQL database. The input of this process is purchase and browsing history data from each data source, and the output is the history data stored in the database.

[0484] Specific behavior:

[0485] The server sends a request to an API endpoint to retrieve the user's past purchases, which are then stored in a corresponding table in a MySQL database.

[0486] Step 2:

[0487] The server analyzes the collected data and identifies each user's purchasing trends. It uses Python's scikit-learn library to run machine learning algorithms to perform clustering and classification. The input for this process is the purchase history data and browsing history data stored in the database, and the output is the results of an analysis of each user's purchasing trends.

[0488] Specific behavior:

[0489] The server uses SQL queries to retrieve purchase and browsing history data, then applies machine learning algorithms to analyze user purchasing patterns. The results of the purchasing trend analysis are stored in a table.

[0490] Step 3:

[0491] The server generates optimal purchasing advice for the user based on the analysis results. It uses natural language generation (NLG) technology to generate advice based on the user's purchasing patterns. The input to this process is the analysis results of the user's purchasing habits, and the output is the generated purchasing advice message.

[0492] Specific behavior:

[0493] The server uses a template-based generative model to generate messages based on the user's purchasing history and trends, for example, "Mr. / Ms. XX, Product A, which you previously purchased, is now on sale again."

[0494] Step 4:

[0495] The server performs emotion analysis to recognize user emotions. It analyzes multiple data sources, including text input, voice, and facial expressions, and determines emotions using Python's nltk library and TensorFlow-based machine learning models. The input for this process is the user's text and voice data, and the output is the emotion recognition results.

[0496] Specific behavior:

[0497] The server analyzes the user's text input received via the chatbot and identifies emotions such as "happiness" or "sadness" through an emotion engine. The results of emotion recognition are stored in an internal data structure.

[0498] Step 5:

[0499] The server adjusts the generated purchasing advice content based on the emotion recognition results, adding encouraging messages for positive emotions and comforting messages for negative emotions. The inputs to this process are the emotion recognition results and the generated purchasing advice message, and the output is the adjusted purchasing advice message.

[0500] Specific behavior:

[0501] When a user types "I'm sad today," the server generates and adds a comforting message such as "Today may have been a tough day, but I recommend this product" to the original advice.

[0502] Step 6:

[0503] The server sends the adjusted purchasing advice to the user's device. Webhooks and API endpoints are used to send messages. Specifically, messages converted into JSON format are sent. The input to this process is the adjusted purchasing advice message, and the output is the advice message displayed on the user's device.

[0504] Specific behavior:

[0505] The server converts the generated advice message into JSON format and sends it to the user's smartphone or personal computer.

[0506] Step 7:

[0507] When the user responds to the advice from the bot, the server receives the response and performs the appropriate action. For example, if the response is "Yes, I'll buy it," the specified product is automatically added to the cart. The input of this process is the response message from the user, and the output is the information about the product added to the cart.

[0508] Specific behavior:

[0509] When the user responds "I'll buy it," the server receives the response, updates the database to check the availability of the corresponding product, automatically adds it to the cart, and automatically enters the necessary information for the purchase process to complete the process.

[0510] (Application example 2)

[0511] 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."

[0512] Conventional online shopping systems can provide purchasing advice based on a user's purchase and browsing history, but it is difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, they lack the ability to grasp and flexibly respond to changes in a user's emotions in real time. As a result, they are unable to improve the user's shopping experience and are unable to provide appropriate purchase promotions.

[0513] The identification process 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 collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion recognition means for recognizing the user's emotions in real time, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This enables personalized purchasing advice based on the user's emotional state, improving the user's shopping experience and promoting purchases more effectively.

[0514] "Purchase history data" refers to information about products purchased by a user in the past.

[0515] "Browser history data" refers to information about products viewed by a user on an online shopping site.

[0516] "Purchase trends" refer to a user's product selection patterns and preferences, which are identified by analyzing purchase history data and browsing history data.

[0517] "Buying advice" refers to product information and offers suggested to users based on their purchasing habits.

[0518] "Emotion recognition" refers to technology that analyzes a user's text input, voice input, or facial expressions to determine the user's emotional state.

[0519] "Emotion recognition means" refers to a technical method or device for detecting a user's emotions in real time and determining the emotion data.

[0520] A "terminal" is a device that a user uses to interface with an online shopping system, specifically a smartphone or PC.

[0521] A "cart" refers to a virtual shopping basket on an online shopping site that temporarily stores items that a user intends to purchase.

[0522] The system of the present invention is configured to collect user purchase history data and browsing history data, analyze this data, and provide optimal purchasing advice to the user. The system also recognizes the user's emotions in real time and adjusts purchasing advice based on the emotions. The components for realizing this system are described below.

[0523] Hardware and Software

[0524] 1. Hardware

[0525] Server: Responsible for data collection, analysis, emotion recognition, and purchase advice generation.

[0526] User device: A device, such as a smartphone or PC, through which a user interacts with the system.

[0527] 2. Software

[0528] User data acquisition module: Collects user purchase history data and browsing history data.

[0529] Analytics module: Analyzes collected data and identifies user purchasing trends.

[0530] Emotion Recognition Module: Recognizes emotions by analyzing the user's text input, voice input, or facial expressions.

[0531] Purchase advice generation module: Generates optimal purchase advice based on purchasing trends and emotion recognition results.

[0532] Data Processing and Computation

[0533] User Data Collection

[0534] The server uses the "user data acquisition module" to acquire the user's purchase history data and browsing history data, including information on products purchased and viewed in the past.

[0535] Data analysis

[0536] The server uses an "analysis module" to analyze the collected purchase history data and browsing history data, which allows the server to identify each user's purchasing trends.

[0537] Emotion recognition

[0538] When a user inputs text, voice, or shows a facial expression in front of the camera, the server uses an "emotion recognition module" to recognize the emotion in real time.

[0539] Generate buying advice

[0540] The server uses a "purchase advice generation module" to generate optimal purchase advice based on the user's purchasing tendencies and emotion recognition results.

[0541] Specific examples

[0542] Usage example 1:

[0543] 1. User A's purchase history data: User A has purchased a shirt from a specific brand X five times in the past year.

[0544] 2. User A's browsing history data: Recently, he has been browsing the new collection of Brand X.

[0545] Prompt statement (example):

[0546] I'm feeling a bit down today. What items would you recommend?

[0547] The server uses an emotion recognition module to analyze the text "I'm feeling a bit down today" and determine User A's emotional state as "sad."

[0548] The server then uses the "purchase advice generation module" based on the analysis and emotion recognition results to generate personalized purchase advice, such as:

[0549] Brand X's new shirts are on sale for 30% off. We're sure you'll find something perfect for you! Cheer up!

[0550] In this way, optimal purchasing advice can be provided according to the user's emotional state, improving the user's shopping experience and effectively promoting purchases.

[0551] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0552] Step 1:

[0553] The server uses the user data acquisition module to collect the user's purchase history data and browsing history data. This involves information on products the user has previously purchased and viewed. (Input) Purchase history data, browsing history data. This provides basic data for understanding the user's purchasing trends. (Output) Collected purchase history data and browsing history data.

[0554] Step 2:

[0555] The server uses an analysis module to analyze the collected purchase history data and browsing history data. This analysis identifies each user's purchasing trends. (Input) Purchase history data and browsing history data collected in step 1. (Output) Identified purchasing trend data. This clarifies the user's preferences and purchasing patterns.

[0556] Step 3:

[0557] When a user inputs text, voice, or shows facial expressions in front of the camera, the server uses the emotion recognition module to recognize the emotion in real time. (Input) User's text, voice, or facial expression data. (Output) Recognized emotion data. This allows the user's current emotional state to be understood.

[0558] Step 4:

[0559] The server uses a purchasing advice generation module to generate optimal purchasing advice based on the user's purchasing tendency data and emotion recognition results. (Input) The purchasing tendency data identified in step 2, the emotion data recognized in step 3. (Output) The generated purchasing advice. This advice is related to the user's past purchasing tendency and current emotional state.

[0560] Step 5:

[0561] The user's terminal receives the purchasing advice sent from the server and presents it to the user. (Input) Purchasing advice sent from the server. (Output) Purchasing advice message presented to the user. Here, the user can check the advice content and respond if necessary.

[0562] Step 6:

[0563] The server receives the user's response and adds the specified product to the cart based on the response. (Input) User response data. (Output) Product data added to the cart. This makes the user's purchasing process even smoother.

[0564] To give a concrete example, suppose a user inputs a prompt such as, "I'm feeling a bit down today. What item would you recommend?" This input is analyzed by the server, and the emotion recognition module determines that the emotion is "sad." As a result, a message to cheer the user up is suggested along with information that a new shirt from brand X, which the user previously purchased, is on discount. This series of processes is carried out in real time, providing the user with appropriate purchasing advice.

[0565] 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.

[0566] 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.

[0567] 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.

[0568] [Third embodiment]

[0569] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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).

[0575] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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."

[0581] This invention relates to an online shopping support system that streamlines the user's shopping experience. This system analyzes the user's purchase history and browsing history and provides optimal purchasing advice. The following explains how the program of this system works.

[0582] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0583] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0584] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now."

[0585] Furthermore, when the user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart.

[0586] As a concrete example, consider a user named Tanaka who has purchased five shirts from a particular brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection, generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. If Tanaka responds "Yes," the server automatically adds the item to Tanaka's cart and assists in the purchase process.

[0587] As described above, the system analyzes users' past data and provides personalized purchasing advice, resulting in an efficient online shopping experience.

[0588] The processing flow will be explained below.

[0589] Step 1:

[0590] The server retrieves the user's purchase history data from the database.

[0591] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0592] Step 2:

[0593] The server retrieves the user's browsing history data from the database.

[0594] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0595] Step 3:

[0596] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0597] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0598] Step 4:

[0599] The server generates optimal purchasing advice for the user based on the analysis results.

[0600] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0601] Step 5:

[0602] The server generates purchasing advice and sends it to the user's terminal.

[0603] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0604] Step 6:

[0605] The user responds to the advice from the bot.

[0606] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0607] Step 7:

[0608] The server parses the user's response and adds the specified product to the cart based on the response.

[0609] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[0610] Step 8:

[0611] The server assists the user in simplifying the purchasing process.

[0612] What it does: Autofills user purchase history, address information, and more, making the purchasing process easier.

[0613] Example 1

[0614] 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."

[0615] In recent years, with the spread of online shopping, many users are purchasing products via the Internet. However, the diversification of products has made user purchasing behavior increasingly complex, creating a need for quickly suggesting the most suitable products for each user. However, conventional systems have difficulty analyzing individual users' purchasing trends and providing appropriate purchasing advice, hindering improvements to the user experience. For this reason, there is a need for a system that can effectively collect and analyze users' purchasing and browsing histories and generate and provide optimal purchasing advice for each user.

[0616] 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.

[0617] In this invention, the server includes means for collecting purchase history data for each user from multiple data sources, means for collecting browsing history data for each user, means for identifying the user's purchasing tendencies using data analysis software based on the collected data, means for generating purchasing advice for the user using a generative AI model based on the identified purchasing tendencies, means for sending the generated purchasing advice to the user's terminal in chat format, and means for receiving the user's response, executing a corresponding action using a natural language processing model, and adding a specified product to a cart. This makes it possible to effectively utilize the user's past data and quickly provide individual purchasing advice.

[0618] "Data source" refers to the source of information extracted for collecting purchase history data and browsing history data, and refers to multiple data sources such as online shopping platforms, emails, and web browser history.

[0619] "Purchase history data" refers to data that includes detailed information about products purchased by a user in the past, such as the purchase date and time, price, and store.

[0620] "Browsing history data" refers to data that includes information about products viewed by a user using a web browser or application, the date and time of viewing, the URL of the page viewed, etc.

[0621] "Data analysis software" refers to analytical tools used to identify user purchasing trends based on collected data, and refers to data analysis libraries such as Python's Pandas and Scikit-learn.

[0622] A "generative AI model" is an artificial intelligence model used to generate purchasing advice in natural language based on a user's purchasing habits, and refers to advanced natural language processing models such as GPT-3.

[0623] "Chat" refers to providing information or advice to users in an interactive format, such as through text messages or an in-app chat window.

[0624] "Natural language processing model" refers to an artificial intelligence model used to analyze a user's text response and perform corresponding actions, and refers to natural language processing technologies such as BERT and GPT-3.

[0625] "Cart" refers to a virtual shopping basket on an online shopping platform that temporarily holds items you wish to purchase.

[0626] This invention relates to an online shopping support system that improves the efficiency of a user's shopping experience. The system is configured as follows, with a server, terminals, and users each playing a specific role.

[0627] First, the server uses cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) to collect data, and collects purchase history and browsing history data from multiple data sources. This includes information on products purchased and viewed by users. For example, it executes an SQL query to retrieve purchase history from a database and uses an API to retrieve browser browsing history.

[0628] The server then analyzes the collected data using data analysis libraries such as Python's Pandas and Scikit-learn to identify each user's purchasing trends, including purchasing frequency analysis for each brand, purchasing trends analysis for each product category, and seasonal purchasing trends using time series analysis.

[0629] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for the user. For example, if a user tends to frequently purchase products from a particular brand, the server will prioritize providing that brand's latest products and sale information. In this case, the server inputs the following prompt into the generative AI model: "Generate optimal purchasing advice based on the user's purchase history and browsing history. For example, notify a user who has purchased shirts from brand A five times in the past of information about new shirt sales."

[0630] The generated purchasing advice is sent from the server to the user's device in the form of a chat message, such as an email, SMS, or in-app notification. For example, a message like, "Hello, new items from Brand A that you've been interested in are now 30% off. Please consider purchasing now."

[0631] The user receives advice sent from the server using a device (e.g., a smartphone or PC). When the user responds to the advice, the server receives the response, analyzes it using a Natural Language Processing (NLP) model, and executes the corresponding action.

[0632] For example, if the user responds "Yes, I'd like to purchase," the server automatically adds the item to the user's cart and assists in the purchase process, including payment processing and shipping arrangements. Payments are processed using APIs from Stripe or PayPal, and shipping arrangements are made using APIs linked to shipping companies.

[0633] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0634] Step 1: Data collection

[0635] The server uses databases and APIs to collect user purchase and browsing history data from multiple data sources. The input is a database query or API request, and the output is a dataset of purchase and browsing history for each user. Specifically, the server executes SQL queries to retrieve purchase history from the database and uses API requests to retrieve browser browsing history.

[0636] Step 2: Data Preprocessing

[0637] The server preprocesses the collected data for data analysis. The input of this step is the raw data collected, and the output is a clean dataset that can be analyzed. Specifically, the server handles missing values ​​and converts the data into the required format, for example, converting text data into categorical data.

[0638] Step 3: Data analysis

[0639] The server then analyzes the preprocessed data using Python data analysis libraries such as Pandas and Scikit-learn. The input for this step is a clean dataset, and the output is data showing each user's purchasing habits. Specifically, the server performs clustering and time series analysis to identify purchasing frequencies and patterns.

[0640] Step 4: Generate buying advice

[0641] The server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for each user based on the analysis results. The input to this step is the analysis result data, and the output is purchasing advice expressed in natural language. Specifically, the server inputs a prompt sentence into the generative AI model and obtains the generated text message. An example of a prompt sentence is: "Please generate optimal purchasing advice based on the user's purchase history and browsing history."

[0642] Step 5: Send advice

[0643] The server sends the generated purchasing advice to the user's device. The input of this step is the generated text message, and the output is the notification sent to the user's device. Specifically, the server retrieves the user's device information from the database and sends the message using an SMTP server or push notification service.

[0644] Step 6: Receiving user response

[0645] The user responds to the advice sent from the server. The input of this step is the user's response message, and the output is the response data received by the server. Specifically, the user enters a text message using a smartphone or PC.

[0646] Step 7: Parse and process the response

[0647] The server analyzes the user's response and performs an action based on it. The input of this step is the user's response data, and the output is a specific action (e.g., adding an item to cart). Specifically, the server uses a Natural Language Processing (NLP) model to analyze the text and perform the corresponding action (e.g., adding an item to cart).

[0648] Step 8: Checkout

[0649] After the user confirms the purchase, the server automatically proceeds with the purchase process. The input of this step is the purchase confirmation information, and the output is the completion of the purchase and the completion of delivery arrangements. Specifically, the server securely transmits payment information, sends a purchase confirmation email to the user, and processes the delivery via an API with the delivery company.

[0650] (Application example 1)

[0651] 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."

[0652] Conventional online shopping systems have difficulty providing efficient purchasing advice by properly utilizing users' purchase and browsing histories. As a result, users spend a great deal of time and effort searching for the right product, resulting in a decline in satisfaction. Furthermore, they lacked functionality to provide useful advice to users, such as specific brand or discount information, creating a demand for a more efficient and personalized shopping experience.

[0653] 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.

[0654] In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, means for transmitting the generated purchasing advice to the user's terminal, means for receiving the user's response and adding specified products to a cart based on the response, and means for obtaining offer information for specific brands based on the user's purchasing tendencies and including the obtained offer information in the generated purchasing advice. This enables users to efficiently find products and offers that are best suited to them, thereby improving and personalizing the shopping experience.

[0655] "Purchase history data" is information about products and services purchased by a user in the past.

[0656] "Browsing history data" is information about products and services that a user has previously viewed online.

[0657] "Purchase trends" are patterns of products and brands that a user is particularly interested in, identified from the user's purchase history and browsing history.

[0658] "Purchase advice" is recommended information for products and services provided to users based on the user's purchasing trends.

[0659] "User's device" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0660] A "cart" is a virtual shopping basket that temporarily stores items to be purchased when shopping online.

[0661] A "specific brand" refers to a brand that a user has frequently selected in their past purchasing or browsing history.

[0662] "Offer information" refers to information about discounts and special offers offered for specific products or brands.

[0663] "Chat style" refers to a style in which a user communicates with a system via a text-based interactive interface.

[0664] This invention is an online shopping support system that analyzes a user's purchase history and browsing history to provide optimal purchasing advice. The main components of the system are a server, a user terminal, and a program for analysis and advice generation.

[0665] The server collects purchase history data and browsing history data from multiple data sources. Specifically, it retrieves information about products the user has previously purchased and viewed from a database. This can be done using cloud services (e.g., AWS or Google Cloud). The server uses this data to perform analysis to identify individual purchasing trends for each user.

[0666] The analysis is performed automatically by a program written in Python, which uses the requests library to process HTTP requests. It aggregates data on purchase and browsing history to identify patterns of brands and products that users frequently purchase. Based on the analysis results, it obtains offer information for specific brands and products and generates purchasing advice.

[0667] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now." When the user responds to the advice, the server receives the response and automatically adds the specified product to the cart.

[0668] As a concrete example, suppose user A has purchased a particular brand five times in the past year. When user A starts shopping again, the server provides the latest sale information for the brand and generates a message such as, "New items from the brand you often buy are now 30% off." This message is delivered to user A, and if user A responds "Yes," the product is added to the cart.

[0669] An example prompt is:

[0670] "Generate purchasing advice based on user A's purchase and browsing history. Recommend new offers for brands that user A has previously purchased."

[0671] This invention allows users to efficiently find the products and special offers that are best suited to them, improving their shopping experience and saving time.

[0672] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0673] Step 1: Collect user purchase and browsing history data

[0674] The server collects information about products that a user has previously purchased or viewed from a database. The input is the user ID, and the output is purchase history data and browsing history data. Specifically, it uses a cloud service (such as AWS or Google Cloud) to obtain the necessary data via an API.

[0675] Step 2: Analyze purchase and browsing history data

[0676] The server analyzes the collected data to identify users' purchasing trends. The input is purchase history data and browsing history data, and the output is the user's purchasing trend patterns. This analysis is performed using a Python script to compile a list of frequently purchased brands and products.

[0677] Step 3: Generate buying advice based on identified buying trends

[0678] The server generates purchasing advice based on the user's purchasing trends from the analysis results. The input is the purchasing trend pattern, and the output is purchasing advice. For example, it obtains the latest sales information for brands that the user frequently purchases and generates an advice message.

[0679] Step 4: Send purchasing advice to the user's device

[0680] The server sends the generated purchasing advice to the user's smartphone or PC. The input is the purchasing advice message, and the output is the advice displayed on the user's device. Specifically, the message is displayed in chat format so that the user can easily check it.

[0681] Step 5: Receive and process the user's response

[0682] The server receives the user's response and determines the next action based on the response. The input is the user's response, and the output is the execution of the corresponding action. For example, if the user responds "yes," add the specified product to the cart.

[0683] Step 6: Add the specified product to your cart

[0684] The server automatically adds the specified product to the cart based on the user's response. The input is the product information included in the purchase advice and the user's response, and the output is the updated cart status. Specifically, the product is added to the user's cart, and the purchase process is supported.

[0685] The processing steps of this program enable the user to receive optimal shopping advice based on his or her purchasing tendencies and to purchase products efficiently.

[0686] 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.

[0687] This invention relates to an online shopping support system that streamlines users' shopping experiences and provides personalized services. This system not only analyzes users' purchase and browsing histories to provide optimal purchasing advice, but also recognizes users' emotions by combining it with an emotion engine and adjusts purchasing advice based on the results.

[0688] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0689] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0690] Furthermore, the system incorporates an emotion engine, which allows the server to recognize the user's emotions in real time. The emotion engine analyzes the user's text input, voice, or facial expressions to determine their emotions. Based on this emotion determination, the server can adjust the purchasing advice it generates.

[0691] For example, if a user inputs "I'm feeling sad today" while interacting with a chatbot, the server can recognize that emotion through its emotion engine and provide more comforting advice or suggestions based on the user's mood. Also, if the user's facial expression recognized through the camera on their smartphone or PC is a smile, the server can use that information to send a positive message.

[0692] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. As a concrete example, let's say a user named Tanaka has purchased five shirts from a specific brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection and generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends this to the user's device. Furthermore, if it is determined that Tanaka is in a relatively good mood, an additional message such as, "It's a good day today! We also recommend this shirt." is sent.

[0693] When the user responds to the advice from the bot, the server receives the response and executes the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. The server also automatically enters the necessary information to simplify the user's purchasing process, allowing them to complete the purchase smoothly.

[0694] As described above, this system not only analyzes users' past data and provides personalized purchasing advice, but also incorporates an emotion engine to provide more effective advice based on the user's emotions.

[0695] The processing flow will be explained below.

[0696] Step 1:

[0697] The server retrieves the user's purchase history data from the database.

[0698] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0699] Step 2:

[0700] The server retrieves the user's browsing history data from the database.

[0701] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0702] Step 3:

[0703] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0704] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0705] Step 4:

[0706] The server generates optimal purchasing advice for the user based on the analysis results.

[0707] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0708] Step 5:

[0709] The server uses an emotion engine to collect data to recognize the user's emotions.

[0710] Specific operation: Collects emotion data through text input, voice input, or facial expression analysis and passes it to the emotion engine.

[0711] Step 6:

[0712] The emotion engine analyzes the collected data and identifies the user's emotions.

[0713] What it does: Uses natural language processing and machine learning algorithms to determine emotions from a user's text, voice, or facial expressions.

[0714] Step 7:

[0715] The server adjusts purchasing advice based on the analysis results of the emotion engine.

[0716] Specific behavior: The recommended product list and message content are flexibly changed based on the user's emotional data. For example, if the user is sad, the system will recommend encouraging messages or products with a relaxing effect.

[0717] Step 8:

[0718] The server generates purchasing advice and sends it to the user's terminal.

[0719] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0720] Step 9:

[0721] The user responds to the advice from the bot.

[0722] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0723] Step 10:

[0724] The server parses the user's response and adds the specified product to the cart based on the response.

[0725] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[0726] Step 11:

[0727] The server assists the user in simplifying the purchasing process.

[0728] Specific operation: The auto-fill function completes the user's purchase history, address information, etc., allowing them to complete the purchase process smoothly.

[0729] Example 2

[0730] 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."

[0731] Conventional online shopping support systems can provide advice based on a user's purchasing and browsing history, but they have the problem of being unable to provide appropriate advice that takes into account the user's emotional state. Furthermore, it is difficult to respond in real time based on the user's reactions, limiting the ability to personalize the shopping experience. Therefore, there is a need for a system that can recognize a user's emotions and provide appropriate advice in real time.

[0732] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion analysis means for recognizing the user's emotions, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This makes it possible to provide personalized advice that takes the user's emotional state into consideration in real time.

[0733] "Purchase history data" is information about products and services purchased by a user in the past.

[0734] "Browser history data" is information about products and services that a user has viewed in the past.

[0735] "Analysis" refers to the act of processing and analyzing data to identify users' purchasing trends using purchase history data and browsing history data.

[0736] "Buying habits" are patterns of a user's preferences and interests that are identified based on the user's past purchasing and browsing behavior.

[0737] "Purchase advice" is information recommending optimal products and services to users based on the analysis results.

[0738] "Emotion analysis" is a technology that analyzes a user's text, voice, facial expressions, etc. to recognize their emotional state.

[0739] "Emotion recognition result" is information on the user's emotional state derived through emotion analysis.

[0740] "User terminal" means an electronic device used by a User to interact with the System, including a smartphone or personal computer.

[0741] "Add to cart" refers to the act of a user registering information about a product they wish to purchase in their online shopping cart.

[0742] "Adjustment" refers to the act of optimizing the content of generated purchasing advice in consideration of the emotion recognition results.

[0743] This invention is a system for streamlining a user's online shopping experience and providing personalized services. The system not only analyzes a user's purchase history and browsing history to generate optimal purchasing advice, but also incorporates an emotion engine to recognize the user's emotions and adjust the advice based on the results.

[0744] First, the server collects user purchase history and browsing history data from multiple data sources. This data includes information on products purchased and viewed by users. This data is retrieved from the API using the Python requests library and stored in a MySQL database.

[0745] The server then analyzes the collected data to identify each user's purchasing habits using machine learning algorithms, particularly clustering and classification algorithms, Python's scikit-learn library, and SQL aggregation queries.

[0746] The server then generates optimal purchasing advice for the user based on the analysis results. This process utilizes natural language generation (NLG) technology, template-based generative models, and statistical NLP techniques. For example, it generates advice that prioritizes product information for frequently purchased brands.

[0747] The server also uses an emotion engine to recognize users' emotions in real time. Emotion recognition uses machine learning models and natural language processing techniques to analyze users' text input, voice, and facial expressions. Specifically, it uses Python's nltk library and TensorFlow-based machine learning models.

[0748] Based on the emotion determination, the server adjusts the generated purchasing advice. For example, if the user inputs "I'm feeling sad today," the advice can be changed to a comforting message. Conversely, if the emotion engine determines that the user is in a relatively good mood, a positive message can be added.

[0749] The generated purchasing advice is sent from the server to the user's device, where the user can receive the advice in chat format via their smartphone or personal computer.

[0750] For example, if a user has purchased a particular brand of shirt five times in the past year, the server analyzes the brand's new collection and generates a message saying, "Hey, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. Furthermore, if the server determines that the user is in a relatively good mood, it sends an additional message saying, "It's a good day today! We also recommend this shirt."

[0751] When a user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. Furthermore, the server automatically fills in the necessary information, allowing the user to complete the purchase process smoothly.

[0752] Example prompt sentence:

[0753] "Add positive messages if the user is in a good mood."

[0754] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0755] Step 1:

[0756] The server collects user purchase history data and browsing history data from multiple data sources. Specifically, it executes API calls to retrieve purchase history data using the requests library and stores it in a MySQL database. The input of this process is purchase and browsing history data from each data source, and the output is the history data stored in the database.

[0757] Specific behavior:

[0758] The server sends a request to an API endpoint to retrieve the user's past purchases, which are then stored in a corresponding table in a MySQL database.

[0759] Step 2:

[0760] The server analyzes the collected data and identifies each user's purchasing trends. It uses Python's scikit-learn library to run machine learning algorithms to perform clustering and classification. The input for this process is the purchase history data and browsing history data stored in the database, and the output is the results of an analysis of each user's purchasing trends.

[0761] Specific behavior:

[0762] The server uses SQL queries to retrieve purchase and browsing history data, then applies machine learning algorithms to analyze user purchasing patterns. The results of the purchasing trend analysis are stored in a table.

[0763] Step 3:

[0764] The server generates optimal purchasing advice for the user based on the analysis results. It uses natural language generation (NLG) technology to generate advice based on the user's purchasing patterns. The input to this process is the analysis results of the user's purchasing habits, and the output is the generated purchasing advice message.

[0765] Specific behavior:

[0766] The server uses a template-based generative model to generate messages based on the user's purchasing history and trends, for example, "Mr. / Ms. XX, Product A, which you previously purchased, is now on sale again."

[0767] Step 4:

[0768] The server performs emotion analysis to recognize user emotions. It analyzes multiple data sources, including text input, voice, and facial expressions, and determines emotions using Python's nltk library and TensorFlow-based machine learning models. The input for this process is the user's text and voice data, and the output is the emotion recognition results.

[0769] Specific behavior:

[0770] The server analyzes the user's text input received via the chatbot and identifies emotions such as "happiness" or "sadness" through an emotion engine. The results of emotion recognition are stored in an internal data structure.

[0771] Step 5:

[0772] The server adjusts the generated purchasing advice content based on the emotion recognition results, adding encouraging messages for positive emotions and comforting messages for negative emotions. The inputs to this process are the emotion recognition results and the generated purchasing advice message, and the output is the adjusted purchasing advice message.

[0773] Specific behavior:

[0774] When a user types "I'm sad today," the server generates and adds a comforting message such as "Today may have been a tough day, but I recommend this product" to the original advice.

[0775] Step 6:

[0776] The server sends the adjusted purchasing advice to the user's device. Webhooks and API endpoints are used to send messages. Specifically, messages converted into JSON format are sent. The input to this process is the adjusted purchasing advice message, and the output is the advice message displayed on the user's device.

[0777] Specific behavior:

[0778] The server converts the generated advice message into JSON format and sends it to the user's smartphone or personal computer.

[0779] Step 7:

[0780] When the user responds to the advice from the bot, the server receives the response and performs the appropriate action. For example, if the response is "Yes, I'll buy it," the specified product is automatically added to the cart. The input of this process is the response message from the user, and the output is the information about the product added to the cart.

[0781] Specific behavior:

[0782] When the user responds "I'll buy it," the server receives the response, updates the database to check the availability of the corresponding product, automatically adds it to the cart, and automatically enters the necessary information for the purchase process to complete the process.

[0783] (Application example 2)

[0784] 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."

[0785] Conventional online shopping systems can provide purchasing advice based on a user's purchase and browsing history, but it is difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, they lack the ability to grasp and flexibly respond to changes in a user's emotions in real time. As a result, they are unable to improve the user's shopping experience and are unable to provide appropriate purchase promotions.

[0786] The identification process 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 collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion recognition means for recognizing the user's emotions in real time, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This enables personalized purchasing advice based on the user's emotional state, improving the user's shopping experience and promoting purchases more effectively.

[0787] "Purchase history data" refers to information about products purchased by a user in the past.

[0788] "Browser history data" refers to information about products viewed by a user on an online shopping site.

[0789] "Purchase trends" refer to a user's product selection patterns and preferences, which are identified by analyzing purchase history data and browsing history data.

[0790] "Buying advice" refers to product information and offers suggested to users based on their purchasing habits.

[0791] "Emotion recognition" refers to technology that analyzes a user's text input, voice input, or facial expressions to determine the user's emotional state.

[0792] "Emotion recognition means" refers to a technical method or device for detecting a user's emotions in real time and determining the emotion data.

[0793] A "terminal" is a device that a user uses to interface with an online shopping system, specifically a smartphone or PC.

[0794] A "cart" refers to a virtual shopping basket on an online shopping site that temporarily stores items that a user intends to purchase.

[0795] The system of the present invention is configured to collect user purchase history data and browsing history data, analyze this data, and provide optimal purchasing advice to the user. The system also recognizes the user's emotions in real time and adjusts purchasing advice based on the emotions. The components for realizing this system are described below.

[0796] Hardware and Software

[0797] 1. Hardware

[0798] Server: Responsible for data collection, analysis, emotion recognition, and purchase advice generation.

[0799] User device: A device, such as a smartphone or PC, through which a user interacts with the system.

[0800] 2. Software

[0801] User data acquisition module: Collects user purchase history data and browsing history data.

[0802] Analytics module: Analyzes collected data and identifies user purchasing trends.

[0803] Emotion Recognition Module: Recognizes emotions by analyzing the user's text input, voice input, or facial expressions.

[0804] Purchase advice generation module: Generates optimal purchase advice based on purchasing trends and emotion recognition results.

[0805] Data Processing and Computation

[0806] User Data Collection

[0807] The server uses the "user data acquisition module" to acquire the user's purchase history data and browsing history data, including information on products purchased and viewed in the past.

[0808] Data analysis

[0809] The server uses an "analysis module" to analyze the collected purchase history data and browsing history data, which allows the server to identify each user's purchasing trends.

[0810] Emotion recognition

[0811] When a user inputs text, voice, or shows a facial expression in front of the camera, the server uses an "emotion recognition module" to recognize the emotion in real time.

[0812] Generate buying advice

[0813] The server uses a "purchase advice generation module" to generate optimal purchase advice based on the user's purchasing tendencies and emotion recognition results.

[0814] Specific examples

[0815] Usage example 1:

[0816] 1. User A's purchase history data: User A has purchased a shirt from a specific brand X five times in the past year.

[0817] 2. User A's browsing history data: Recently, he has been browsing the new collection of Brand X.

[0818] Prompt statement (example):

[0819] I'm feeling a bit down today. What items would you recommend?

[0820] The server uses an emotion recognition module to analyze the text "I'm feeling a bit down today" and determine User A's emotional state as "sad."

[0821] The server then uses the "purchase advice generation module" based on the analysis and emotion recognition results to generate personalized purchase advice, such as:

[0822] Brand X's new shirts are on sale for 30% off. We're sure you'll find something perfect for you! Cheer up!

[0823] In this way, optimal purchasing advice can be provided according to the user's emotional state, improving the user's shopping experience and effectively promoting purchases.

[0824] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0825] Step 1:

[0826] The server uses the user data acquisition module to collect the user's purchase history data and browsing history data. This involves information on products the user has previously purchased and viewed. (Input) Purchase history data, browsing history data. This provides basic data for understanding the user's purchasing trends. (Output) Collected purchase history data and browsing history data.

[0827] Step 2:

[0828] The server uses an analysis module to analyze the collected purchase history data and browsing history data. This analysis identifies each user's purchasing trends. (Input) Purchase history data and browsing history data collected in step 1. (Output) Identified purchasing trend data. This clarifies the user's preferences and purchasing patterns.

[0829] Step 3:

[0830] When a user inputs text, voice, or shows facial expressions in front of the camera, the server uses the emotion recognition module to recognize the emotion in real time. (Input) User's text, voice, or facial expression data. (Output) Recognized emotion data. This allows the user's current emotional state to be understood.

[0831] Step 4:

[0832] The server uses a purchasing advice generation module to generate optimal purchasing advice based on the user's purchasing tendency data and emotion recognition results. (Input) The purchasing tendency data identified in step 2, the emotion data recognized in step 3. (Output) The generated purchasing advice. This advice is related to the user's past purchasing tendency and current emotional state.

[0833] Step 5:

[0834] The user's terminal receives the purchasing advice sent from the server and presents it to the user. (Input) Purchasing advice sent from the server. (Output) Purchasing advice message presented to the user. Here, the user can check the advice content and respond if necessary.

[0835] Step 6:

[0836] The server receives the user's response and adds the specified product to the cart based on the response. (Input) User response data. (Output) Product data added to the cart. This makes the user's purchasing process even smoother.

[0837] To give a concrete example, suppose a user inputs a prompt such as, "I'm feeling a bit down today. What item would you recommend?" This input is analyzed by the server, and the emotion recognition module determines that the emotion is "sad." As a result, a message to cheer the user up is suggested along with information that a new shirt from brand X, which the user previously purchased, is on discount. This series of processes is carried out in real time, providing the user with appropriate purchasing advice.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] [Fourth embodiment]

[0842] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0843] 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.

[0844] 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).

[0845] 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.

[0846] 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.

[0847] 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).

[0848] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] This invention relates to an online shopping support system that streamlines the user's shopping experience. This system analyzes the user's purchase history and browsing history and provides optimal purchasing advice. The following explains how the program of this system works.

[0856] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0857] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0858] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now."

[0859] Furthermore, when the user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart.

[0860] As a concrete example, consider a user named Tanaka who has purchased five shirts from a particular brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection, generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. If Tanaka responds "Yes," the server automatically adds the item to Tanaka's cart and assists in the purchase process.

[0861] As described above, the system analyzes users' past data and provides personalized purchasing advice, resulting in an efficient online shopping experience.

[0862] The processing flow will be explained below.

[0863] Step 1:

[0864] The server retrieves the user's purchase history data from the database.

[0865] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0866] Step 2:

[0867] The server retrieves the user's browsing history data from the database.

[0868] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0869] Step 3:

[0870] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0871] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0872] Step 4:

[0873] The server generates optimal purchasing advice for the user based on the analysis results.

[0874] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0875] Step 5:

[0876] The server generates purchasing advice and sends it to the user's terminal.

[0877] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0878] Step 6:

[0879] The user responds to the advice from the bot.

[0880] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0881] Step 7:

[0882] The server parses the user's response and adds the specified product to the cart based on the response.

[0883] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[0884] Step 8:

[0885] The server assists the user in simplifying the purchasing process.

[0886] What it does: Autofills user purchase history, address information, and more, making the purchasing process easier.

[0887] Example 1

[0888] 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."

[0889] In recent years, with the spread of online shopping, many users are purchasing products via the Internet. However, the diversification of products has made user purchasing behavior increasingly complex, creating a need for quickly suggesting the most suitable products for each user. However, conventional systems have difficulty analyzing individual users' purchasing trends and providing appropriate purchasing advice, hindering improvements to the user experience. For this reason, there is a need for a system that can effectively collect and analyze users' purchasing and browsing histories and generate and provide optimal purchasing advice for each user.

[0890] 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.

[0891] In this invention, the server includes means for collecting purchase history data for each user from multiple data sources, means for collecting browsing history data for each user, means for identifying the user's purchasing tendencies using data analysis software based on the collected data, means for generating purchasing advice for the user using a generative AI model based on the identified purchasing tendencies, means for sending the generated purchasing advice to the user's terminal in chat format, and means for receiving the user's response, executing a corresponding action using a natural language processing model, and adding a specified product to a cart. This makes it possible to effectively utilize the user's past data and quickly provide individual purchasing advice.

[0892] "Data source" refers to the source of information extracted for collecting purchase history data and browsing history data, and refers to multiple data sources such as online shopping platforms, emails, and web browser history.

[0893] "Purchase history data" refers to data that includes detailed information about products purchased by a user in the past, such as the purchase date and time, price, and store.

[0894] "Browsing history data" refers to data that includes information about products viewed by a user using a web browser or application, the date and time of viewing, the URL of the page viewed, etc.

[0895] "Data analysis software" refers to analytical tools used to identify user purchasing trends based on collected data, and refers to data analysis libraries such as Python's Pandas and Scikit-learn.

[0896] A "generative AI model" is an artificial intelligence model used to generate purchasing advice in natural language based on a user's purchasing habits, and refers to advanced natural language processing models such as GPT-3.

[0897] "Chat" refers to providing information or advice to users in an interactive format, such as through text messages or an in-app chat window.

[0898] "Natural language processing model" refers to an artificial intelligence model used to analyze a user's text response and perform corresponding actions, and refers to natural language processing technologies such as BERT and GPT-3.

[0899] "Cart" refers to a virtual shopping basket on an online shopping platform that temporarily holds items you wish to purchase.

[0900] This invention relates to an online shopping support system that improves the efficiency of a user's shopping experience. The system is configured as follows, with a server, terminals, and users each playing a specific role.

[0901] First, the server uses cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) to collect data, and collects purchase history and browsing history data from multiple data sources. This includes information on products purchased and viewed by users. For example, it executes an SQL query to retrieve purchase history from a database and uses an API to retrieve browser browsing history.

[0902] The server then analyzes the collected data using data analysis libraries such as Python's Pandas and Scikit-learn to identify each user's purchasing trends, including purchasing frequency analysis for each brand, purchasing trends analysis for each product category, and seasonal purchasing trends using time series analysis.

[0903] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for the user. For example, if a user tends to frequently purchase products from a particular brand, the server will prioritize providing that brand's latest products and sale information. In this case, the server inputs the following prompt into the generative AI model: "Generate optimal purchasing advice based on the user's purchase history and browsing history. For example, notify a user who has purchased shirts from brand A five times in the past of information about new shirt sales."

[0904] The generated purchasing advice is sent from the server to the user's device in the form of a chat message, such as an email, SMS, or in-app notification. For example, a message like, "Hello, new items from Brand A that you've been interested in are now 30% off. Please consider purchasing now."

[0905] The user receives advice sent from the server using a device (e.g., a smartphone or PC). When the user responds to the advice, the server receives the response, analyzes it using a Natural Language Processing (NLP) model, and executes the corresponding action.

[0906] For example, if the user responds "Yes, I'd like to purchase," the server automatically adds the item to the user's cart and assists in the purchase process, including payment processing and shipping arrangements. Payments are processed using APIs from Stripe or PayPal, and shipping arrangements are made using APIs linked to shipping companies.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Step 1: Data collection

[0909] The server uses databases and APIs to collect user purchase and browsing history data from multiple data sources. The input is a database query or API request, and the output is a dataset of purchase and browsing history for each user. Specifically, the server executes SQL queries to retrieve purchase history from the database and uses API requests to retrieve browser browsing history.

[0910] Step 2: Data Preprocessing

[0911] The server preprocesses the collected data for data analysis. The input of this step is the raw data collected, and the output is a clean dataset that can be analyzed. Specifically, the server handles missing values ​​and converts the data into the required format, for example, converting text data into categorical data.

[0912] Step 3: Data analysis

[0913] The server then analyzes the preprocessed data using Python data analysis libraries such as Pandas and Scikit-learn. The input for this step is a clean dataset, and the output is data showing each user's purchasing habits. Specifically, the server performs clustering and time series analysis to identify purchasing frequencies and patterns.

[0914] Step 4: Generate buying advice

[0915] The server uses a generative AI model (e.g., GPT-3) to generate purchasing advice for each user based on the analysis results. The input to this step is the analysis result data, and the output is purchasing advice expressed in natural language. Specifically, the server inputs a prompt sentence into the generative AI model and obtains the generated text message. An example of a prompt sentence is: "Please generate optimal purchasing advice based on the user's purchase history and browsing history."

[0916] Step 5: Send advice

[0917] The server sends the generated purchasing advice to the user's device. The input of this step is the generated text message, and the output is the notification sent to the user's device. Specifically, the server retrieves the user's device information from the database and sends the message using an SMTP server or push notification service.

[0918] Step 6: Receiving user response

[0919] The user responds to the advice sent from the server. The input of this step is the user's response message, and the output is the response data received by the server. Specifically, the user enters a text message using a smartphone or PC.

[0920] Step 7: Parse and process the response

[0921] The server analyzes the user's response and performs an action based on it. The input of this step is the user's response data, and the output is a specific action (e.g., adding an item to cart). Specifically, the server uses a Natural Language Processing (NLP) model to analyze the text and perform the corresponding action (e.g., adding an item to cart).

[0922] Step 8: Checkout

[0923] After the user confirms the purchase, the server automatically proceeds with the purchase process. The input of this step is the purchase confirmation information, and the output is the completion of the purchase and the completion of delivery arrangements. Specifically, the server securely transmits payment information, sends a purchase confirmation email to the user, and processes the delivery via an API with the delivery company.

[0924] (Application example 1)

[0925] 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."

[0926] Conventional online shopping systems have difficulty providing efficient purchasing advice by properly utilizing users' purchase and browsing histories. As a result, users spend a great deal of time and effort searching for the right product, resulting in a decline in satisfaction. Furthermore, they lacked functionality to provide useful advice to users, such as specific brand or discount information, creating a demand for a more efficient and personalized shopping experience.

[0927] 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.

[0928] In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, means for transmitting the generated purchasing advice to the user's terminal, means for receiving the user's response and adding specified products to a cart based on the response, and means for obtaining offer information for specific brands based on the user's purchasing tendencies and including the obtained offer information in the generated purchasing advice. This enables users to efficiently find products and offers that are best suited to them, thereby improving and personalizing the shopping experience.

[0929] "Purchase history data" is information about products and services purchased by a user in the past.

[0930] "Browsing history data" is information about products and services that a user has previously viewed online.

[0931] "Purchase trends" are patterns of products and brands that a user is particularly interested in, identified from the user's purchase history and browsing history.

[0932] "Purchase advice" is recommended information for products and services provided to users based on the user's purchasing trends.

[0933] "User's device" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0934] A "cart" is a virtual shopping basket that temporarily stores items to be purchased when shopping online.

[0935] A "specific brand" refers to a brand that a user has frequently selected in their past purchasing or browsing history.

[0936] "Offer information" refers to information about discounts and special offers offered for specific products or brands.

[0937] "Chat style" refers to a style in which a user communicates with a system via a text-based interactive interface.

[0938] This invention is an online shopping support system that analyzes a user's purchase history and browsing history to provide optimal purchasing advice. The main components of the system are a server, a user terminal, and a program for analysis and advice generation.

[0939] The server collects purchase history data and browsing history data from multiple data sources. Specifically, it retrieves information about products the user has previously purchased and viewed from a database. This can be done using cloud services (e.g., AWS or Google Cloud). The server uses this data to perform analysis to identify individual purchasing trends for each user.

[0940] The analysis is performed automatically by a program written in Python, which uses the requests library to process HTTP requests. It aggregates data on purchase and browsing history to identify patterns of brands and products that users frequently purchase. Based on the analysis results, it obtains offer information for specific brands and products and generates purchasing advice.

[0941] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. For example, a message such as "Hello, new items from a brand you're interested in are now 30% off. Please consider purchasing now." When the user responds to the advice, the server receives the response and automatically adds the specified product to the cart.

[0942] As a concrete example, suppose user A has purchased a particular brand five times in the past year. When user A starts shopping again, the server provides the latest sale information for the brand and generates a message such as, "New items from the brand you often buy are now 30% off." This message is delivered to user A, and if user A responds "Yes," the product is added to the cart.

[0943] An example prompt is:

[0944] "Generate purchasing advice based on user A's purchase and browsing history. Recommend new offers for brands that user A has previously purchased."

[0945] This invention allows users to efficiently find the products and special offers that are best suited to them, improving their shopping experience and saving time.

[0946] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0947] Step 1: Collect user purchase and browsing history data

[0948] The server collects information about products that a user has previously purchased or viewed from a database. The input is the user ID, and the output is purchase history data and browsing history data. Specifically, it uses a cloud service (such as AWS or Google Cloud) to obtain the necessary data via an API.

[0949] Step 2: Analyze purchase and browsing history data

[0950] The server analyzes the collected data to identify users' purchasing trends. The input is purchase history data and browsing history data, and the output is the user's purchasing trend patterns. This analysis is performed using a Python script to compile a list of frequently purchased brands and products.

[0951] Step 3: Generate buying advice based on identified buying trends

[0952] The server generates purchasing advice based on the user's purchasing trends from the analysis results. The input is the purchasing trend pattern, and the output is purchasing advice. For example, it obtains the latest sales information for brands that the user frequently purchases and generates an advice message.

[0953] Step 4: Send purchasing advice to the user's device

[0954] The server sends the generated purchasing advice to the user's smartphone or PC. The input is the purchasing advice message, and the output is the advice displayed on the user's device. Specifically, the message is displayed in chat format so that the user can easily check it.

[0955] Step 5: Receive and process the user's response

[0956] The server receives the user's response and determines the next action based on the response. The input is the user's response, and the output is the execution of the corresponding action. For example, if the user responds "yes," add the specified product to the cart.

[0957] Step 6: Add the specified product to your cart

[0958] The server automatically adds the specified product to the cart based on the user's response. The input is the product information included in the purchase advice and the user's response, and the output is the updated cart status. Specifically, the product is added to the user's cart, and the purchase process is supported.

[0959] The processing steps of this program enable the user to receive optimal shopping advice based on his or her purchasing tendencies and to purchase products efficiently.

[0960] 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.

[0961] This invention relates to an online shopping support system that streamlines users' shopping experiences and provides personalized services. This system not only analyzes users' purchase and browsing histories to provide optimal purchasing advice, but also recognizes users' emotions by combining it with an emotion engine and adjusts purchasing advice based on the results.

[0962] First, the server collects user purchase history data and browsing history data from multiple data sources, including information on products the user has previously purchased and viewed. Using this data, the server performs analysis to identify individual purchasing trends for each user.

[0963] The server then generates optimal purchasing advice for the user based on the analysis results. For example, if a user has frequently purchased products from a particular brand in the past, the server will prioritize providing information about the latest products and sales from that brand. The server will also include discount and coupon information in the advice, allowing the user to receive more attractive offers.

[0964] Furthermore, the system incorporates an emotion engine, which allows the server to recognize the user's emotions in real time. The emotion engine analyzes the user's text input, voice, or facial expressions to determine their emotions. Based on this emotion determination, the server can adjust the purchasing advice it generates.

[0965] For example, if a user inputs "I'm feeling sad today" while interacting with a chatbot, the server can recognize that emotion through its emotion engine and provide more comforting advice or suggestions based on the user's mood. Also, if the user's facial expression recognized through the camera on their smartphone or PC is a smile, the server can use that information to send a positive message.

[0966] The generated purchasing advice is sent from the server to the user's device. The user can receive this advice in chat format via their smartphone or PC. As a concrete example, let's say a user named Tanaka has purchased five shirts from a specific brand A in the past year. When Tanaka is looking for a new shirt, the server analyzes Brand A's new collection and generates a message saying, "Tanaka, new shirts from Brand A are on sale for 30% off," and sends this to the user's device. Furthermore, if it is determined that Tanaka is in a relatively good mood, an additional message such as, "It's a good day today! We also recommend this shirt." is sent.

[0967] When the user responds to the advice from the bot, the server receives the response and executes the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. The server also automatically enters the necessary information to simplify the user's purchasing process, allowing them to complete the purchase smoothly.

[0968] As described above, this system not only analyzes users' past data and provides personalized purchasing advice, but also incorporates an emotion engine to provide more effective advice based on the user's emotions.

[0969] The processing flow will be explained below.

[0970] Step 1:

[0971] The server retrieves the user's purchase history data from the database.

[0972] Specific operation: Using the SQL query "SELECT FROM Purchase History WHERE User ID = 'Specific User ID'", the results are loaded into memory.

[0973] Step 2:

[0974] The server retrieves the user's browsing history data from the database.

[0975] Specific operation: Using the SQL query "SELECT FROM browsing history WHERE user ID = 'specific user ID'", executes the query and loads the results into memory.

[0976] Step 3:

[0977] The server analyzes the purchase history data and browsing history data collected to identify users' purchasing trends.

[0978] What it does: Uses data mining algorithms to analyze purchase frequency, product category, and brand trends.

[0979] Step 4:

[0980] The server generates optimal purchasing advice for the user based on the analysis results.

[0981] What it does: It uses a specific algorithm to create a list of recommended products, calculate the relevance score for each product, and retrieve discount and coupon information to include in the recommendations.

[0982] Step 5:

[0983] The server uses an emotion engine to collect data to recognize the user's emotions.

[0984] Specific operation: Collects emotion data through text input, voice input, or facial expression analysis and passes it to the emotion engine.

[0985] Step 6:

[0986] The emotion engine analyzes the collected data and identifies the user's emotions.

[0987] What it does: Uses natural language processing and machine learning algorithms to determine emotions from a user's text, voice, or facial expressions.

[0988] Step 7:

[0989] The server adjusts purchasing advice based on the analysis results of the emotion engine.

[0990] Specific behavior: The recommended product list and message content are flexibly changed based on the user's emotional data. For example, if the user is sad, the system will recommend encouraging messages or products with a relaxing effect.

[0991] Step 8:

[0992] The server generates purchasing advice and sends it to the user's terminal.

[0993] Specific behavior: Uses push notification APIs or messaging services to send the specified message to the user's smartphone or PC.

[0994] Step 9:

[0995] The user responds to the advice from the bot.

[0996] What it does: Receives a text response from the user, such as "yes" or "no," through the bot's interface.

[0997] Step 10:

[0998] The server parses the user's response and adds the specified product to the cart based on the response.

[0999] Specific operation: Execute the query "INSERT INTO Cart (User ID, Product ID) VALUES ('User ID', 'Product ID')" and reflect it in the cart.

[1000] Step 11:

[1001] The server assists the user in simplifying the purchasing process.

[1002] Specific operation: The auto-fill function completes the user's purchase history, address information, etc., allowing them to complete the purchase process smoothly.

[1003] Example 2

[1004] 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."

[1005] Conventional online shopping support systems can provide advice based on a user's purchasing and browsing history, but they have the problem of being unable to provide appropriate advice that takes into account the user's emotional state. Furthermore, it is difficult to respond in real time based on the user's reactions, limiting the ability to personalize the shopping experience. Therefore, there is a need for a system that can recognize a user's emotions and provide appropriate advice in real time.

[1006] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion analysis means for recognizing the user's emotions, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This makes it possible to provide personalized advice that takes the user's emotional state into consideration in real time.

[1007] "Purchase history data" is information about products and services purchased by a user in the past.

[1008] "Browser history data" is information about products and services that a user has viewed in the past.

[1009] "Analysis" refers to the act of processing and analyzing data to identify users' purchasing trends using purchase history data and browsing history data.

[1010] "Buying habits" are patterns of a user's preferences and interests that are identified based on the user's past purchasing and browsing behavior.

[1011] "Purchase advice" is information recommending optimal products and services to users based on the analysis results.

[1012] "Emotion analysis" is a technology that analyzes a user's text, voice, facial expressions, etc. to recognize their emotional state.

[1013] "Emotion recognition result" is information on the user's emotional state derived through emotion analysis.

[1014] "User terminal" means an electronic device used by a User to interact with the System, including a smartphone or personal computer.

[1015] "Add to cart" refers to the act of a user registering information about a product they wish to purchase in their online shopping cart.

[1016] "Adjustment" refers to the act of optimizing the content of generated purchasing advice in consideration of the emotion recognition results.

[1017] This invention is a system for streamlining a user's online shopping experience and providing personalized services. The system not only analyzes a user's purchase history and browsing history to generate optimal purchasing advice, but also incorporates an emotion engine to recognize the user's emotions and adjust the advice based on the results.

[1018] First, the server collects user purchase history and browsing history data from multiple data sources. This data includes information on products purchased and viewed by users. This data is retrieved from the API using the Python requests library and stored in a MySQL database.

[1019] The server then analyzes the collected data to identify each user's purchasing habits using machine learning algorithms, particularly clustering and classification algorithms, Python's scikit-learn library, and SQL aggregation queries.

[1020] The server then generates optimal purchasing advice for the user based on the analysis results. This process utilizes natural language generation (NLG) technology, template-based generative models, and statistical NLP techniques. For example, it generates advice that prioritizes product information for frequently purchased brands.

[1021] The server also uses an emotion engine to recognize users' emotions in real time. Emotion recognition uses machine learning models and natural language processing techniques to analyze users' text input, voice, and facial expressions. Specifically, it uses Python's nltk library and TensorFlow-based machine learning models.

[1022] Based on the emotion determination, the server adjusts the generated purchasing advice. For example, if the user inputs "I'm feeling sad today," the advice can be changed to a comforting message. Conversely, if the emotion engine determines that the user is in a relatively good mood, a positive message can be added.

[1023] The generated purchasing advice is sent from the server to the user's device, where the user can receive the advice in chat format via their smartphone or personal computer.

[1024] For example, if a user has purchased a particular brand of shirt five times in the past year, the server analyzes the brand's new collection and generates a message saying, "Hey, new shirts from Brand A are on sale for 30% off," and sends it to the user's device. Furthermore, if the server determines that the user is in a relatively good mood, it sends an additional message saying, "It's a good day today! We also recommend this shirt."

[1025] When a user responds to the advice from the bot, the server receives the response and performs the corresponding action. For example, if the user responds "Yes, I'll buy it," the server automatically adds the product to the cart. Furthermore, the server automatically fills in the necessary information, allowing the user to complete the purchase process smoothly.

[1026] Example prompt sentence:

[1027] "Add positive messages if the user is in a good mood."

[1028] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1029] Step 1:

[1030] The server collects user purchase history data and browsing history data from multiple data sources. Specifically, it executes API calls to retrieve purchase history data using the requests library and stores it in a MySQL database. The input of this process is purchase and browsing history data from each data source, and the output is the history data stored in the database.

[1031] Specific behavior:

[1032] The server sends a request to an API endpoint to retrieve the user's past purchases, which are then stored in a corresponding table in a MySQL database.

[1033] Step 2:

[1034] The server analyzes the collected data and identifies each user's purchasing trends. It uses Python's scikit-learn library to run machine learning algorithms to perform clustering and classification. The input for this process is the purchase history data and browsing history data stored in the database, and the output is the results of an analysis of each user's purchasing trends.

[1035] Specific behavior:

[1036] The server uses SQL queries to retrieve purchase and browsing history data, then applies machine learning algorithms to analyze user purchasing patterns. The results of the purchasing trend analysis are stored in a table.

[1037] Step 3:

[1038] The server generates optimal purchasing advice for the user based on the analysis results. It uses natural language generation (NLG) technology to generate advice based on the user's purchasing patterns. The input to this process is the analysis results of the user's purchasing habits, and the output is the generated purchasing advice message.

[1039] Specific behavior:

[1040] The server uses a template-based generative model to generate messages based on the user's purchasing history and trends, for example, "Mr. / Ms. XX, Product A, which you previously purchased, is now on sale again."

[1041] Step 4:

[1042] The server performs emotion analysis to recognize user emotions. It analyzes multiple data sources, including text input, voice, and facial expressions, and determines emotions using Python's nltk library and TensorFlow-based machine learning models. The input for this process is the user's text and voice data, and the output is the emotion recognition results.

[1043] Specific behavior:

[1044] The server analyzes the user's text input received via the chatbot and identifies emotions such as "happiness" or "sadness" through an emotion engine. The results of emotion recognition are stored in an internal data structure.

[1045] Step 5:

[1046] The server adjusts the generated purchasing advice content based on the emotion recognition results, adding encouraging messages for positive emotions and comforting messages for negative emotions. The inputs to this process are the emotion recognition results and the generated purchasing advice message, and the output is the adjusted purchasing advice message.

[1047] Specific behavior:

[1048] When a user types "I'm sad today," the server generates and adds a comforting message such as "Today may have been a tough day, but I recommend this product" to the original advice.

[1049] Step 6:

[1050] The server sends the adjusted purchasing advice to the user's device. Webhooks and API endpoints are used to send messages. Specifically, messages converted into JSON format are sent. The input to this process is the adjusted purchasing advice message, and the output is the advice message displayed on the user's device.

[1051] Specific behavior:

[1052] The server converts the generated advice message into JSON format and sends it to the user's smartphone or personal computer.

[1053] Step 7:

[1054] When the user responds to the advice from the bot, the server receives the response and performs the appropriate action. For example, if the response is "Yes, I'll buy it," the specified product is automatically added to the cart. The input of this process is the response message from the user, and the output is the information about the product added to the cart.

[1055] Specific behavior:

[1056] When the user responds "I'll buy it," the server receives the response, updates the database to check the availability of the corresponding product, automatically adds it to the cart, and automatically enters the necessary information for the purchase process to complete the process.

[1057] (Application example 2)

[1058] 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."

[1059] Conventional online shopping systems can provide purchasing advice based on a user's purchase and browsing history, but it is difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, they lack the ability to grasp and flexibly respond to changes in a user's emotions in real time. As a result, they are unable to improve the user's shopping experience and are unable to provide appropriate purchase promotions.

[1060] The identification process 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 collecting purchase history data for each user, means for collecting browsing history data for each user, means for analyzing the purchase history data and the browsing history data to identify the user's purchasing tendencies, means for generating purchasing advice for the user based on the identified purchasing tendencies, emotion recognition means for recognizing the user's emotions in real time, means for adjusting the purchasing advice based on the emotion recognition result, means for sending the generated purchasing advice to the user's terminal, and means for receiving the user's response and adding specified products to the cart based on the response. This enables personalized purchasing advice based on the user's emotional state, improving the user's shopping experience and promoting purchases more effectively.

[1061] "Purchase history data" refers to information about products purchased by a user in the past.

[1062] "Browser history data" refers to information about products viewed by a user on an online shopping site.

[1063] "Purchase trends" refer to a user's product selection patterns and preferences, which are identified by analyzing purchase history data and browsing history data.

[1064] "Buying advice" refers to product information and offers suggested to users based on their purchasing habits.

[1065] "Emotion recognition" refers to technology that analyzes a user's text input, voice input, or facial expressions to determine the user's emotional state.

[1066] "Emotion recognition means" refers to a technical method or device for detecting a user's emotions in real time and determining the emotion data.

[1067] A "terminal" is a device that a user uses to interface with an online shopping system, specifically a smartphone or PC.

[1068] A "cart" refers to a virtual shopping basket on an online shopping site that temporarily stores items that a user intends to purchase.

[1069] The system of the present invention is configured to collect user purchase history data and browsing history data, analyze this data, and provide optimal purchasing advice to the user. The system also recognizes the user's emotions in real time and adjusts purchasing advice based on the emotions. The components for realizing this system are described below.

[1070] Hardware and Software

[1071] 1. Hardware

[1072] Server: Responsible for data collection, analysis, emotion recognition, and purchase advice generation.

[1073] User device: A device, such as a smartphone or PC, through which a user interacts with the system.

[1074] 2. Software

[1075] User data acquisition module: Collects user purchase history data and browsing history data.

[1076] Analytics module: Analyzes collected data and identifies user purchasing trends.

[1077] Emotion Recognition Module: Recognizes emotions by analyzing the user's text input, voice input, or facial expressions.

[1078] Purchase advice generation module: Generates optimal purchase advice based on purchasing trends and emotion recognition results.

[1079] Data Processing and Computation

[1080] User Data Collection

[1081] The server uses the "user data acquisition module" to acquire the user's purchase history data and browsing history data, including information on products purchased and viewed in the past.

[1082] Data analysis

[1083] The server uses an "analysis module" to analyze the collected purchase history data and browsing history data, which allows the server to identify each user's purchasing trends.

[1084] Emotion recognition

[1085] When a user inputs text, voice, or shows a facial expression in front of the camera, the server uses an "emotion recognition module" to recognize the emotion in real time.

[1086] Generate buying advice

[1087] The server uses a "purchase advice generation module" to generate optimal purchase advice based on the user's purchasing tendencies and emotion recognition results.

[1088] Specific examples

[1089] Usage example 1:

[1090] 1. User A's purchase history data: User A has purchased a shirt from a specific brand X five times in the past year.

[1091] 2. User A's browsing history data: Recently, he has been browsing the new collection of Brand X.

[1092] Prompt statement (example):

[1093] I'm feeling a bit down today. What items would you recommend?

[1094] The server uses an emotion recognition module to analyze the text "I'm feeling a bit down today" and determine User A's emotional state as "sad."

[1095] The server then uses the "purchase advice generation module" based on the analysis and emotion recognition results to generate personalized purchase advice, such as:

[1096] Brand X's new shirts are on sale for 30% off. We're sure you'll find something perfect for you! Cheer up!

[1097] In this way, optimal purchasing advice can be provided according to the user's emotional state, improving the user's shopping experience and effectively promoting purchases.

[1098] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1099] Step 1:

[1100] The server uses the user data acquisition module to collect the user's purchase history data and browsing history data. This involves information on products the user has previously purchased and viewed. (Input) Purchase history data, browsing history data. This provides basic data for understanding the user's purchasing trends. (Output) Collected purchase history data and browsing history data.

[1101] Step 2:

[1102] The server uses an analysis module to analyze the collected purchase history data and browsing history data. This analysis identifies each user's purchasing trends. (Input) Purchase history data and browsing history data collected in step 1. (Output) Identified purchasing trend data. This clarifies the user's preferences and purchasing patterns.

[1103] Step 3:

[1104] When a user inputs text, voice, or shows facial expressions in front of the camera, the server uses the emotion recognition module to recognize the emotion in real time. (Input) User's text, voice, or facial expression data. (Output) Recognized emotion data. This allows the user's current emotional state to be understood.

[1105] Step 4:

[1106] The server uses a purchasing advice generation module to generate optimal purchasing advice based on the user's purchasing tendency data and emotion recognition results. (Input) The purchasing tendency data identified in step 2, the emotion data recognized in step 3. (Output) The generated purchasing advice. This advice is related to the user's past purchasing tendency and current emotional state.

[1107] Step 5:

[1108] The user's terminal receives the purchasing advice sent from the server and presents it to the user. (Input) Purchasing advice sent from the server. (Output) Purchasing advice message presented to the user. Here, the user can check the advice content and respond if necessary.

[1109] Step 6:

[1110] The server receives the user's response and adds the specified product to the cart based on the response. (Input) User response data. (Output) Product data added to the cart. This makes the user's purchasing process even smoother.

[1111] To give a concrete example, suppose a user inputs a prompt such as, "I'm feeling a bit down today. What item would you recommend?" This input is analyzed by the server, and the emotion recognition module determines that the emotion is "sad." As a result, a message to cheer the user up is suggested along with information that a new shirt from brand X, which the user previously purchased, is on discount. This series of processes is carried out in real time, providing the user with appropriate purchasing advice.

[1112] 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.

[1113] 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.

[1114] 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.

[1115] 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.

[1116] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1117] 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.

[1118] 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).

[1119] 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.

[1120] 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."

[1121] 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.

[1122] 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).

[1123] 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.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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.

[1133] The following is further disclosed regarding the above embodiment.

[1134] (Claim 1)

[1135] A means of collecting purchase history data for each user,

[1136] A means of collecting browsing history data on a per-user basis;

[1137] A means for analyzing purchase history data and browsing history data to identify user purchasing trends;

[1138] means for generating purchasing advice for the user based on the identified purchasing tendencies;

[1139] means for transmitting the generated purchasing advice to the user's terminal;

[1140] means for receiving a user response and adding the specified item to the cart based on the response;

[1141] A system including:

[1142] (Claim 2)

[1143] 10. The system of claim 1, further comprising means for including discount information in the purchasing advice.

[1144] (Claim 3)

[1145] 2. The system according to claim 1, further comprising means for presenting the generated purchasing advice to the user in a chat format.

[1146] "Example 1"

[1147] (Claim 1)

[1148] A means of collecting purchase history data for each user from multiple data sources,

[1149] A means of collecting browsing history data on a per-user basis;

[1150] Using the collected data, we use data analysis software to identify users' purchasing trends;

[1151] a means for generating purchasing advice for the user using a generative AI model based on the identified purchasing trends;

[1152] A means for sending the generated purchasing advice to the user's device in chat format;

[1153] means for receiving a user response and performing a corresponding action using a natural language processing model to add the specified product to the cart;

[1154] A system including:

[1155] (Claim 2)

[1156] 10. The system of claim 1, further comprising means for including discount information in the purchasing advice.

[1157] (Claim 3)

[1158] 10. The system of claim 1, further comprising means for providing purchasing advice to the user via email, SMS, or in-app notification.

[1159] "Application Example 1"

[1160] (Claim 1)

[1161] A means of collecting purchase history data for each user,

[1162] A means of collecting browsing history data on a per-user basis;

[1163] A means for analyzing purchase history data and browsing history data to identify user purchasing trends;

[1164] means for generating purchasing advice for the user based on the identified purchasing tendencies;

[1165] means for transmitting the generated purchasing advice to the user's terminal;

[1166] means for receiving a user response and adding the specified item to the cart based on the response;

[1167] A means for obtaining offer information for a particular brand based on the user's purchasing habits and including it in the generated purchase advice;

[1168] A system including:

[1169] (Claim 2)

[1170] 10. The system of claim 1, further comprising means for including discount information in the purchasing advice.

[1171] (Claim 3)

[1172] 2. The system according to claim 1, further comprising means for presenting the generated purchasing advice to the user in a chat format.

[1173] "Example 2: Combining Emotion Engines"

[1174] (Claim 1)

[1175] A means of collecting purchase history data for each user,

[1176] A means of collecting browsing history data on a per-user basis;

[1177] A means for analyzing purchase history data and browsing history data to identify user purchasing trends;

[1178] means for generating purchasing advice for the user based on the identified purchasing tendencies;

[1179] an emotion analysis means for recognizing the emotion of a user;

[1180] a means for adjusting purchasing advice based on emotion recognition results;

[1181] means for transmitting the generated purchasing advice to the user's terminal;

[1182] means for receiving a user response and adding the specified item to the cart based on the response;

[1183] A system including:

[1184] (Claim 2)

[1185] 10. The system of claim 1, further comprising means for including discount information in the purchasing advice.

[1186] (Claim 3)

[1187] 2. The system according to claim 1, further comprising means for presenting the generated purchasing advice to the user in a chat format.

[1188] "Application example 2 when combining emotion engines"

[1189] (Claim 1)

[1190] A means of collecting purchase history data for each user,

[1191] A means of collecting browsing history data on a per-user basis;

[1192] A means for analyzing purchase history data and browsing history data to identify user purchasing trends;

[1193] means for generating purchasing advice for the user based on the identified purchasing tendencies;

[1194] an emotion recognition means for recognizing a user's emotion in real time;

[1195] a means for adjusting purchase advice based on emotion recognition results;

[1196] means for transmitting the generated purchasing advice to the user's terminal;

[1197] means for receiving a user response and adding the specified item to the cart based on the response;

[1198] A system including:

[1199] (Claim 2)

[1200] 10. The system of claim 1, further comprising means for including discount information in the purchasing advice.

[1201] (Claim 3)

[1202] 2. The system according to claim 1, further comprising means for presenting the generated purchasing advice to the user in a chat format. [Explanation of symbols]

[1203] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting purchase history data for each user, A means of collecting browsing history data on a per-user basis; A means for analyzing purchase history data and browsing history data to identify user purchasing trends; means for generating purchasing advice for the user based on the identified purchasing tendencies; means for transmitting the generated purchasing advice to the user's terminal; means for receiving a user response and adding the specified item to the cart based on the response; A system including:

2. 10. The system of claim 1, further comprising means for including discount information in the purchasing advice.

3. 2. The system according to claim 1, further comprising means for presenting the generated purchasing advice to the user in a chat format.

Images