System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data, a means for arranging and storing the collected data, a means for analyzing the stored data, a means for generating investment advice based on the analysis result, and a means for distributing the generated investment advice to a user terminal.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] For sneaker collectors and investors, finding rare sneakers and evaluating them as potential investments is extremely important, but doing so requires collecting and analyzing large amounts of market data. However, doing this manually is time-consuming, labor-intensive, and often inaccurate. Furthermore, there is no established method for efficiently collecting data from multiple data sources. Therefore, a system is needed to efficiently collect and analyze data and support investment decisions. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, it includes a means for collecting data from multiple online marketplaces, auction sites, and social media. Second, it provides a means for organizing the collected data and storing it in a database. It also includes a means for analyzing the stored data and calculating sneaker rarity and price trends. Finally, it provides a means for generating investment advice based on the analysis results and distributing it to the user's terminal. This system allows users to make investment decisions efficiently and accurately.

[0006] The "means for collecting data" is a module for obtaining sneaker sales information from online marketplaces, auction sites, social networking sites, etc. via the Internet.

[0007] The "means for organizing and storing" is a module for classifying and organizing collected data and storing it in a database.

[0008] The "analysis means" refers to algorithms and software that calculate and analyze sneaker rarity and market trends based on the stored data.

[0009] The "means for generating investment advice" is a module that determines which sneakers have high investment value based on the analysis results and provides investment recommendations to users based on that information.

[0010] The "means for distributing to a user terminal" is a communication module for transmitting the generated investment advice to a user terminal such as a smartphone or computer.

[0011] An "online marketplace" refers to a platform where goods are bought and sold over the Internet, and is generally a place where a wide variety of sneakers are traded.

[0012] An "auction site" refers to a website where products are bought and sold through bidding, and where prices are determined to reflect the rarity of sneakers.

[0013] "SNS" is an abbreviation for social networking services, which are used as a forum for communication and information exchange between users and can also be a source of data on market trends.

[0014] A "database" is an information management system that efficiently stores collected and organized data and allows for quick retrieval. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] To put this invention into practice, a system is constructed that collects and analyzes sneaker market data and provides investment advice based on that data. The specific configuration and operation of the system are described below.

[0037] Data collection implementation

[0038] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. This involves sending HTTP requests to each data source to retrieve HTML pages containing sales information. The HTML pages are then parsed to extract necessary data such as the sneaker model name, sale date, and sale price.

[0039] For example, if a server were to collect data from "Online Marketplace A," the following steps would be taken: The server would access the product listing page of "Online Marketplace A" and retrieve the HTML. Using an HTML parsing library, it would extract information such as the sneaker name, price, and sale date.

[0040] Data Storage Implementation

[0041] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[0042] For example, if the server collects data on "Sneaker B," it will be stored in a database table as follows:

[0043] Model Name: Sneakers B

[0044] Sale date: 2023-09-15

[0045] Sale price: 300

[0046] Data Analysis Embodiments

[0047] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price and number of sales. A rarity score is also calculated, which can be used to predict future value increases.

[0048] As a specific example, the server analyzes data for "Sneaker C" and calculates the average price based on the sales history for the past 12 months. Based on this information, it determines that the scarcity score is high because sales are declining but the price is rising.

[0049] Investment Advice Generation Embodiments

[0050] The server generates investment advice based on the analysis results. This advice is based on factors that predict the future value of a particular sneaker (for example, price appreciation rate or rarity score). The advice is provided to the user in an easy-to-understand format.

[0051] For example, if the average price of "Sneaker D" has increased by 20% over the past six months and the number of sales has decreased, the server will generate a recommendation that "Sneaker D" will become more valuable in the future.

[0052] Implementation of the delivery of investment advice

[0053] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0054] For example, if a user receives an investment advice notification about "Sneaker E" on their smartphone, they can open the app to check the detailed information and make an investment based on that information.

[0055] In this way, the present invention provides a system that automatically processes everything from collecting sneaker market data to analyzing it, generating investment advice, and finally distributing it, allowing users to efficiently obtain accurate information and make optimal investment decisions.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The server accesses online marketplaces, auction sites, and social networking sites on the Internet to collect sneaker sales data. Specifically, it sends an HTTP request to the URL of each data source and retrieves the HTML page.

[0059] Step 2:

[0060] The server parses the HTML page and extracts information such as the sneaker model name, release date, and sale price. For example, an HTML parsing library is used to extract the necessary data from specific tags.

[0061] Step 3:

[0062] The server temporarily organizes the extracted data into a data structure such as a list or dictionary, then establishes a connection to the database and stores the data in the appropriate tables.

[0063] Step 4:

[0064] To analyze the stored data, the server queries the database to retrieve the necessary information, for example, sales data for a particular sneaker for the past year.

[0065] Step 5:

[0066] The server uses the acquired data to analyze sneaker rarity and price trends, calculating declines in sales and increases in price to calculate a rarity score.

[0067] Step 6:

[0068] The server generates investment advice based on the analysis results. For example, if it predicts that a particular pair of sneakers is likely to increase in value in the future, it generates a recommendation for that sneaker.

[0069] Step 7:

[0070] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[0071] Step 8:

[0072] Users receive investment advice delivered to their devices, then open an app or email to check detailed information, and use that information to make optimal investment decisions.

[0073] Example 1

[0074] 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."

[0075] In conventional market analysis systems, the collection, organization, and analysis of market data, as well as the generation and distribution of investment advice, were all carried out separately, resulting in complex processes and making it difficult to update data and make investment decisions in real time.In addition, the limited scope of data collection meant that data coverage and analytical accuracy were low.

[0076] 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.

[0077] In this invention, the server includes a means for collecting market data, a means for organizing and storing the collected market data, and a means for analyzing the stored market data. This automates the entire process of data collection, analysis, and investment advice generation and distribution in the sneaker market, enabling real-time data updates and efficient investment decisions.

[0078] "Market data" refers to data including sales information, price information, sales dates, number of transactions, etc., of products traded in the market.

[0079] "Online marketplace" refers to a platform for buying and selling goods over the Internet.

[0080] "Auction Site" means a website where bidding and auctioning of items takes place online.

[0081] "Social networking service" refers to a service on the Internet that enables users to share content and communicate with each other.

[0082] An "information terminal" is a device that a user uses to receive information, and includes a smartphone, a computer, etc.

[0083] "Database" refers to a management system for efficiently storing and retrieving data.

[0084] "Analysis" refers to the process of analyzing collected data to find specific patterns or trends.

[0085] "Investment advice" refers to information that recommends appropriate investment actions based on the results of data analysis.

[0086] This invention is a system that collects and analyzes sneaker market data and provides investment advice based on that data. This system automatically performs a series of processes: collecting necessary information from various data sources, analyzing the data, generating investment advice, and distributing it to users.

[0087] Data collection implementation

[0088] The server collects market data from online marketplaces, auction sites, and social networking services. Specifically, it sends HTTP requests and parses the HTML pages it retrieves to extract information such as sneaker model name, release date, and sale price. It uses an HTML parsing library such as Beautiful Soup to parse the HTML.

[0089] Examples:

[0090] The server periodically accesses "Online Market A" and retrieves the HTML of the product list page.

[0091] The server uses Beautiful Soup to parse the HTML and extract data such as the name of the sneaker "Model X," the release date "2023-09-15," and the sale price "$300."

[0092] Data Storage Implementation

[0093] The extracted market data is organized and stored in a database on the server, which includes fields such as sneaker model name, release date, and sales price.

[0094] Examples:

[0095] The server connects to the database and inserts the newly extracted "Model X" data into the sneaker information table.

[0096] The database stores the following information: model name "Model X," sales date "2023-09-15," and sales price "$300."

[0097] Data Analysis Embodiments

[0098] The server runs an algorithm that analyzes the stored data. This involves calculating sneaker rarity and price trends based on past sales data. The data is analyzed using Python's Scikit-learn and Pandas libraries to calculate average prices, sales numbers, and rarity scores.

[0099] Examples:

[0100] The server calculates price trends using Model Y sales data from the past 12 months.

[0101] The server calculates the average price and number of sales, and if it sees that the number of sales is decreasing and the price is increasing, it gives a high scarcity score.

[0102] Investment Advice Generation Embodiments

[0103] The server generates investment advice based on the data analysis results. Using a generative AI model, the server inputs the analysis results as prompt sentences to generate investment advice that is easy for users to understand.

[0104] Examples:

[0105] The server analyzes that the average price of the Model Y has increased by 20% over the past six months, while sales have declined.

[0106] The server uses the generative AI model to generate investment advice such as "Model Y will become more valuable in the future."

[0107] Implementation of the delivery of investment advice

[0108] The generated investment advice is delivered to the user's device via push notification, email, etc. The user can check the delivered notification and obtain detailed investment advice.

[0109] Examples:

[0110] The server sends push notifications using a notification service such as Firebase.

[0111] The device receives a notification, and the user taps on it to open the application, which displays detailed information about the investment advice.

[0112] Users receive investment advice notifications about the Model Z, open the app to review the information, and make an investment decision.

[0113] Example prompt sentence:

[0114] "Collect and analyze sneaker market data from online marketplace A, generate investment advice based on the results, and send it to the user's device via push notification."

[0115] The system automatically collects market data, analyzes the data, and generates and distributes investment advice, enabling users to obtain accurate information in real time and make optimal investment decisions.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] System program processing flow

[0118] The program of this system is executed in the following processing steps.

[0119] Step 1: Data collection

[0120] A server collects sneaker market data from online marketplaces, auction sites, and social networking services.

[0121] Specific behavior:

[0122] Input: List of data source URLs

[0123] Processing: The server sends an HTTP request to each data source to retrieve an HTML page, which it then parses with an HTML parsing library such as Beautiful Soup.

[0124] Output: A list of sneaker models, release dates, and prices

[0125] Examples:

[0126] The server accesses "Online Marketplace A" and retrieves the HTML of the product list page (e.g., URL: https: / / example.com / products).

[0127] The server uses Beautiful Soup to parse the HTML and extract the following information: model "Model X", sale date "2023-09-15", and sale price "$300".

[0128] Step 2: Save data

[0129] The server organizes and stores the extracted market data in a database.

[0130] Specific behavior:

[0131] Input: Data extracted in step 1

[0132] Processing: The server connects to the database and inserts new data into the sneaker information table.

[0133] Output: Data stored in the database

[0134] Examples:

[0135] The server connects to the database and saves the data of model name "Model X", release date "2023-09-15", and sale price "$300" in the sneaker information table.

[0136] Step 3: Data analysis

[0137] The server runs algorithms that analyze the stored data.

[0138] Specific behavior:

[0139] Input: Sneaker market data stored in a database

[0140] Processing: The server uses Python's Scikit-learn and Pandas libraries to analyze historical sales data and calculate price trends, average prices, and scarcity scores.

[0141] Output: Analysis results (price trends, average price, scarcity score, etc.)

[0142] Examples:

[0143] The server retrieves sales data for the Model Y for the past 12 months from the database and calculates price trends.

[0144] The server assigns a high scarcity score based on the declining number of sales and rising prices.

[0145] Step 4: Investment advice generation

[0146] The server generates investment advice based on the analysis results.

[0147] Specific behavior:

[0148] Input: Analysis results (price trends, average price, scarcity score, etc.)

[0149] Processing: The server inputs the analysis results into the generative AI model as prompt sentences to generate investment advice that is easy for the user to understand.

[0150] Output: Generated investment advice

[0151] Examples:

[0152] The server generates investment advice based on the fact that the price of the Model Y has risen 20% over the past six months and sales have declined, stating that the Model Y will become more valuable in the future.

[0153] Step 5: Providing investment advice

[0154] The server distributes the generated investment advice to the information terminal.

[0155] Specific behavior:

[0156] Input: Generated investment advice

[0157] Processing: The server uses a notification service such as Firebase to deliver advice to the user's information device via push notification or email.

[0158] Output: Investment advice delivered to the user's information terminal

[0159] Examples:

[0160] The server generates investment advice on the Model Z and sends a push notification to the user's smartphone via Firebase.

[0161] The user receives a notification and opens the app to see more information.

[0162] Through this series of processing steps, users can obtain accurate investment information in real time, enabling them to make optimal investment decisions.

[0163] (Application example 1)

[0164] 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."

[0165] In today's sneaker market, where sneaker values ​​fluctuate rapidly, it is difficult for users to make appropriate investment decisions based on this information. Furthermore, if users do not have a way to directly purchase sneakers after receiving investment advice, they are unable to take prompt investment action. This can result in users missing out on advantageous investment opportunities.

[0166] 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.

[0167] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for delivering generated investment advice to a user terminal, and means for enabling the user to directly purchase the generated investment advice, thereby enabling the user to quickly receive reliable investment advice based on market data and immediately purchase sneakers.

[0168] "Data collection means" refers to the part that has the function of obtaining sneaker market data from online markets, auction sites, social networks, etc.

[0169] The "data organization means" is a part that organizes collected market data into a format suitable for analysis and stores it in a database or the like.

[0170] "Data storage means" refers to a database, storage system, or other part that stores organized market data efficiently and effectively.

[0171] The "data analysis means" refers to the part that uses algorithms and calculations to analyze sneaker rarity and price trends based on stored market data.

[0172] The "investment advice generation means" is a part that has the function of predicting future increases in the value of sneakers based on the analysis results and creating appropriate investment advice.

[0173] The "investment advice distribution means" is a part that includes a push notification system and an email system for notifying the user's terminal of the generated investment advice.

[0174] The "purchase means" is a function that allows the user to directly purchase sneakers based on the investment advice received.

[0175] This invention is a system that collects and analyzes sneaker market data, generates and distributes investment advice, and allows users to directly purchase sneakers based on that advice. The system consists of the following main components:

[0176] First, the server collects sneaker market data from multiple data sources, including online marketplaces, auction sites, and social networks. This involves sending an HTTP request to retrieve an HTML page containing sales information, parsing the HTML page to extract the required data, and then the server organizes this collected data and stores it in a database.

[0177] The server then analyzes the stored data. This data analysis uses algorithms to calculate the rarity and price trends of sneakers. For example, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. It also calculates a rarity score, which can be used to predict future value increases.

[0178] Based on the analysis results, the server generates investment advice based on factors that predict the future value of a particular sneaker (e.g., price appreciation rate and rarity score), and provides the advice in a format that is easy for users to understand.

[0179] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0180] Furthermore, users can directly purchase sneakers based on the advice. The server not only provides users with investment advice but also provides an interface for them to actually purchase the sneakers. This allows users to make quick investment decisions and execute them.

[0181] For example, if one day "Sneaker X" becomes particularly rare and its price rises, the user will be notified with the following advice:

[0182] "Sneaker X has increased in price by 25% over the past six months, and sales are declining. Consider investing in this sneaker as it is likely to continue to increase in value."

[0183] Examples of prompts for generative AI models include:

[0184] "Analyze the future value increase potential of Sneaker X based on the price fluctuation and sales data of the past six months. If the price increase rate is high, generate a message recommending investment to the user."

[0185] The above system can be a powerful tool for users to make efficient and accurate investment decisions in the sneaker market.

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] The server collects sneaker market data from online marketplaces, auction sites, and social networks using HTTP requests. The server retrieves HTML pages from each data source and parses them to extract data such as sneaker model name, sale date, and sale price. The input is the retrieved HTML data, and the output is the parsed sneaker market data.

[0189] Step 2:

[0190] The server then organizes the parsed sneaker market data appropriately and stores it in a database. The input is the parsed market data, and the output is the data stored in an organized format in the database. For example, information such as the model name "Sneaker A," the release date "2023-10-01," and the sale price "$120" is stored in the database.

[0191] Step 3:

[0192] The server runs an algorithm to analyze the stored data. Specifically, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. The input is market data stored in the database, and the output is the analysis results (e.g., average price, number of sales, rarity score).

[0193] Step 4:

[0194] The server generates investment advice based on the analysis results. This advice is based on factors such as price growth rate and scarcity score. The input is the analysis results, and the output is investment advice to be provided to the user. For example: "Sneaker B has increased in average price by 20% over the past six months and sales have decreased, so it is predicted to increase in value in the future."

[0195] Step 5:

[0196] The server delivers the generated investment advice to the user's device. Push notifications and emails are used as delivery methods. The input is the generated investment advice text, and the output is the notification sent to the user's device. Example: "Investment advice on sneaker C has been sent."

[0197] Step 6:

[0198] The user can confirm the investment advice and purchase the sneakers directly through the application. When the user presses the purchase button based on the advice received on the user's device, the server processes the purchase request and completes the transaction. The input is the user's purchase request, and the output is a purchase completion notification or a purchase rejection notification.

[0199] Through these steps, the system can efficiently collect and analyze sneaker market data, provide useful investment advice to users, and support quick purchases.

[0200] 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.

[0201] To put this invention into practice, a system is required that collects and analyzes sneaker market data and provides investment advice based on that data, and an emotion engine is also required that recognizes and analyzes user emotions. The specific configuration and operation of the system are described below.

[0202] Data collection implementation

[0203] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[0204] Data Storage Implementation

[0205] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[0206] Data Analysis Embodiments

[0207] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price history of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[0208] Embodiment of Emotion Engine

[0209] Next, the server uses an emotion engine to recognize and analyze the user's emotion data. This emotion engine infers emotions based on the user's input data and behavioral logs (e.g., clicks, browsing time, and purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[0210] Investment Advice Generation Embodiments

[0211] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the results of sneaker market data analysis. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice will be provided.

[0212] Implementation of the delivery of investment advice

[0213] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0214] As a concrete example, consider the following scenario:

[0215] The server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database.

[0216] At the same time, the emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X."

[0217] The server analyzes market data and user sentiment data for "Sneaker X" and determines that the value of the sneakers will increase in the future.

[0218] The advice generated by the server includes the content that now is the time to buy "Sneaker X" and is delivered to the user's device.

[0219] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[0220] The processing flow will be explained below.

[0221] Step 1:

[0222] The server collects sneaker market data from online marketplaces, auction sites, and social media sites. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[0223] Step 2:

[0224] The server organizes the extracted data and stores it in a database, specifically in a table with fields such as sneaker model name, release date, and sales price.

[0225] Step 3:

[0226] The server queries the database to retrieve the necessary information, such as sales data for a particular sneaker over the past year, and analyzes the sneaker's rarity and price trends based on this data.

[0227] Step 4:

[0228] The server runs algorithms to analyze the stored data, calculating declines in sales and price increases, and deriving a scarcity score. For example, it calculates the average price and number of sneakers sold and compares it with historical data.

[0229] Step 5:

[0230] The server launches an emotion engine to obtain user emotion data. The emotion engine estimates emotions based on the user's behavior log (e.g., clicks, browsing time, purchasing behavior) and input data. For example, if a user frequently views a particular sneaker model, it evaluates the user as having a high interest in that sneaker.

[0231] Step 6:

[0232] The server generates investment advice by combining the emotional data obtained by the emotion engine with the results of market data analysis. Specifically, the content of the investment advice is adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice is provided.

[0233] Step 7:

[0234] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[0235] Step 8:

[0236] Users receive investment advice delivered to their devices, open an app or email to view detailed information, and make optimal investment decisions based on that information. For example, they tap on an app notification to view detailed information about recommended sneakers and make a purchase decision based on that information.

[0237] The system allows users to receive accurate and personalized investment advice based on their emotional state and market data.

[0238] Example 2

[0239] 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."

[0240] In a system that collects and analyzes sneaker market data and provides investment advice based on that data, there is a challenge in generating and providing more appropriate and personalized advice by recognizing and analyzing user emotions. To solve this problem, it is necessary to accurately capture the user's emotional state and dynamically adjust investment advice based on that.

[0241] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0242] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for recognizing and analyzing user emotion data, means for generating investment advice based on the analysis results, and means for delivering the generated investment advice to the user terminal, thereby making it possible to provide personalized investment advice that takes into account the user's emotional state.

[0243] "Data" refers to information or figures collected from sources and used for analysis.

[0244] "Means of collection" refers to the methods and tools used to obtain data from online marketplaces, auction sites, social networking services, etc.

[0245] "Means of organizing and storing" refers to methods and tools for formatting collected data into a certain format and storing it safely and efficiently in storage such as a database.

[0246] "Means of analysis" refers to algorithms and tools that use stored data to analyze market trends and user behavior patterns.

[0247] "User emotional data" refers to information about the emotional state estimated based on the user's input data and behavioral log.

[0248] "Means of recognition and analysis" refers to the algorithms and tools used to collect and analyze user emotional data.

[0249] "Means for generating investment advice" refers to methods and tools for creating optimal investment advice based on data analysis results and user sentiment data.

[0250] "Means of delivery" refers to the methods and tools used to deliver the generated investment advice to the user's terminal.

[0251] "User terminal" refers to a device such as a smartphone or computer that a user uses to receive information or perform operations.

[0252] "Server" refers to a computer system for executing a series of processes such as data collection, analysis, storage, advice generation and distribution.

[0253] This invention is a system that collects and analyzes sneaker market data and user sentiment data, and provides investment advice. This system operates with the following configuration.

[0254] First, the server collects data. The server gathers sneaker data from multiple sources, including online marketplaces, auction sites, and social networking services. This data collection is done using HTTP requests and web scraping libraries such as BeautifulSoup and Scrapy. For example, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the Nike Air Max.

[0255] Next, the server organizes the collected data and stores it in a database. For this, it uses a relational database such as "PostgreSQL" or "MySQL (registered trademark)." The server converts the collected data into an appropriate format and inserts it into the database. Specifically, the server stores the Nike Air Max data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[0256] The server then performs analysis based on the stored data. This analysis uses machine learning libraries such as "pandas" and "scikit-learn" to calculate the price history and sales volume of a specific sneaker and calculate a rarity score. For example, based on the price of Nike Air Max over the past year, the server determines that the average price is $220 and the rarity score is 85.

[0257] Furthermore, the server uses an emotion engine to recognize and analyze user emotion data. When a user browses a page, their behavioral log (clicks, browsing time, purchasing behavior) is collected and their emotion is estimated using natural language processing engines such as "TENSORFLOW (registered trademark)" and "IBM Watson (registered trademark)." For example, if a user frequently browses a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[0258] The server then combines the sentiment data and market data to generate investment advice. The server integrates the analysis results with the sentiment data and inputs a prompt statement into the generative AI model. For example, the server might input "If the user is highly interested in Nike Air Max, please generate investment advice," and the model would generate the advice "Now is the time to buy Nike Air Max."

[0259] Finally, the server delivers the generated investment advice to the user's device. This delivery can be done using methods such as push notification or email. The user receives the notification or email, checks the content, and then makes an investment decision. For example, the user's device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[0260] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[0261] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0262] Step 1:

[0263] The server collects sneaker market data from online marketplaces, auction sites, and social networking services. It lists the URLs of each data source as input and sends HTTP requests based on them. It obtains an HTML page as output, parses the page using the "BeautifulSoup" library, and extracts information such as the sneaker model name, release date, and sale price. Specifically, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the "Nike Air Max" on that page.

[0264] Step 2:

[0265] The server organizes the acquired data and saves it in a database. It formats the information extracted as input, such as the sneaker model name, release date, and sales price, connects to the "PostgreSQL" database, and inserts it into the database. The organized data is saved in the database as output. Specifically, the server saves the "Nike Air Max" data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[0266] Step 3:

[0267] The server performs analysis based on the stored data. It retrieves past sales data from the database as input using a query and processes the data using the "pandas" library. It then runs an algorithm to calculate the rarity score using "scikit-learn." The output is the price history of the sneakers, the average price, the number of sales, and the rarity score. Specifically, the server calculates that the average price is $220 and the rarity score is 85 based on the prices of "Nike Air Max" over the past year.

[0268] Step 4:

[0269] The server uses an emotion engine to recognize and analyze user emotion data. As input, it collects behavioral logs such as user clicks, browsing time, and purchasing behavior. It then uses TensorFlow and IBM Watson to run the emotion engine and estimate the user's emotions. The output is an evaluation of the user's emotional state. Specifically, the server assesses that the user has a high level of interest and anticipation based on the long time they spent browsing the Nike Air Max page.

[0270] Step 5:

[0271] The server combines the sentiment data and market data to generate investment advice. As input, it integrates the analyzed market data and sentiment data and inputs a prompt statement into the generative AI model. As output, the investment advice obtained from the generative AI model is generated. Specifically, the prompt statement is input as "If the user shows a high interest in Nike Air Max, please generate investment advice," and the model generates the advice "Now is the time to buy Nike Air Max."

[0272] Step 6:

[0273] The server delivers the generated investment advice to the user's device. Using the generated investment advice as input, it delivers it to the user's device via push notification or email. The investment advice is sent to the user's device as output, and the user confirms it. Specifically, the device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[0274] (Application example 2)

[0275] 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."

[0276] Conventional investment advice systems only analyze market data for investment targets, making it impossible to provide appropriate advice that takes into account the user's emotional state. It is also difficult to generate personalized advice based on the user's behavior and emotions. As a result, the advice users receive is general and does not fully address their individual needs and emotions.

[0277] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for analyzing user emotion data, means for generating investment advice based on the analysis results and the emotion data, and means for delivering the generated investment advice to the user terminal. This makes it possible to provide specific and personalized investment advice based on the user's individual emotional state and market data.

[0278] "Data collection means" refers to mechanisms for obtaining sneaker market data from online marketplaces, auction sites, and social media.

[0279] "Means for organizing and storing collected data" refers to a mechanism for structuring acquired data and storing it in a database.

[0280] The "means for analyzing stored data" refers to a mechanism that includes algorithms for calculating sneaker rarity and price trends based on collected market data.

[0281] The "means for analyzing user emotion data" is a mechanism including an emotion engine for estimating an emotional state using a user's behavior log and input data.

[0282] The "means for generating investment advice based on the analysis results and emotional data" is a mechanism for combining the analyzed market data with the user's emotional data to generate optimal investment advice.

[0283] The "means for delivering the generated investment advice to the user terminal" is a mechanism for sending the generated investment advice to the user's smartphone or computer via push notification or email.

[0284] The following describes an embodiment of the present invention. The system implements a series of functions including data collection, organization and storage, data analysis, sentiment analysis, investment advice generation, and distribution. This makes it possible to provide investment advice that takes into account the user's sentiment.

[0285] Data collection implementation

[0286] The server collects sneaker market data from online marketplaces, auction sites, and social media, sending HTTP requests to the URLs of each data source, retrieving HTML pages and parsing them to extract information such as sneaker model name, sale date, and sale price.

[0287] Data Storage Implementation

[0288] The collected data is organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price, allowing for efficient data storage and retrieval.

[0289] Data Analysis Embodiments

[0290] The server runs algorithms to analyze the stored market data. This analysis uses historical sales data to calculate sneaker rarity and price trends. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[0291] Embodiment of Emotion Engine

[0292] The server uses an emotion engine to recognize and analyze user emotion data. The emotion engine infers emotions based on user input data and behavioral logs (clicks, browsing time, purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, it infers that the user has a high level of interest and anticipation for that sneaker.

[0293] Investment Advice Generation Embodiments

[0294] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the sneaker market data analysis results. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, the server will provide low-risk investment advice, and if the user is in a positive emotional state, the server will provide risky but high-reward investment advice.

[0295] Implementation of the delivery of investment advice

[0296] The generated investment advice is delivered to the user's device via push notifications to their smartphone or email. Users can receive these notifications, check the content, and make appropriate investment decisions.

[0297] Specific examples

[0298] As an example, a server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database. The emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X." The server analyzes the market data for "Sneaker X" and the user's emotion data and determines that the value of these sneakers will increase in the future. The advice generated by the server, including the content that now is the time to buy "Sneaker X," is delivered to the user's device.

[0299] Prompt Sentence Examples

[0300] By inputting the following prompt sentences into the generative AI model, the information necessary to generate investment advice can be obtained.

[0301] "Please provide detailed steps to build an application that collects and analyzes sneaker market data from an online marketplace and combines it with user sentiment data to generate investment advice. Please include the following elements:

[0302] 1. Specific methods of data collection and storage

[0303] 2. How to analyze market data and user sentiment data

[0304] 3. Algorithm for generating investment advice

[0305] 4. How to deliver advice to user devices

[0306] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0307] Step 1:

[0308] The server collects sneaker market data from online marketplaces, auction sites, and social media. Specifically, it sends HTTP requests to the URLs of each data source and parses the resulting HTML pages. It extracts information such as the sneaker model name, release date, and sale price from the parsed results. The input is the data source URL, and the output is the parsed market data.

[0309] Step 2:

[0310] The server organizes the collected market data and stores it in a database. The data is divided into fields such as sneaker model name, release date, and sales price. The input is the organized market data, and the output is the data stored in the database. Specifically, the server inserts data into the database using SQL queries.

[0311] Step 3:

[0312] The server analyzes market data stored in a database. It runs an algorithm to calculate the rarity and price trends of sneakers based on past sales data. The input is the market data in the database, and the output is the analyzed price trends and rarity score. Specific operations include calculating the average price and tallying the number of sales.

[0313] Step 4:

[0314] The server analyzes the user's emotional data. The emotion engine uses the user's behavior log (clicks, browsing time, purchasing behavior) to estimate the emotional state. The input is the user's behavior data, and the output is an emotion score. Specifically, the emotion engine is used to analyze the user log and calculate the emotion score.

[0315] Step 5:

[0316] The server generates investment advice based on the analysis results and sentiment data. It combines the market data analysis results with sentiment scores to create optimal investment advice. The inputs are price trends, scarcity scores, and sentiment scores, and the output is investment advice. Specifically, it adjusts the content and wording of the advice to generate investment advice statements.

[0317] Step 6:

[0318] The server distributes the generated investment advice to the user's device. The distribution method is push notification or email. The input is the generated investment advice, and the output is a notification to the user's device. Specifically, the server uses a notification service to send the advice to the user's smartphone or computer.

[0319] 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.

[0320] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0321] 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.

[0322] [Second embodiment]

[0323] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0324] 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.

[0325] 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).

[0326] 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.

[0327] 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.

[0328] 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).

[0329] 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.

[0330] 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.

[0331] 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.

[0332] 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.

[0333] 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.

[0334] 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."

[0335] To put this invention into practice, a system is constructed that collects and analyzes sneaker market data and provides investment advice based on that data. The specific configuration and operation of the system are described below.

[0336] Data collection implementation

[0337] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. This involves sending HTTP requests to each data source to retrieve HTML pages containing sales information. The HTML pages are then parsed to extract necessary data such as the sneaker model name, sale date, and sale price.

[0338] For example, if a server were to collect data from "Online Marketplace A," the following steps would be taken: The server would access the product listing page of "Online Marketplace A" and retrieve the HTML. Using an HTML parsing library, it would extract information such as the sneaker name, price, and sale date.

[0339] Data Storage Implementation

[0340] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[0341] For example, if the server collects data on "Sneaker B," it will be stored in a database table as follows:

[0342] Model Name: Sneakers B

[0343] Sale date: 2023-09-15

[0344] Sale price: 300

[0345] Data Analysis Embodiments

[0346] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price and number of sales. A rarity score is also calculated, which can be used to predict future value increases.

[0347] As a specific example, the server analyzes data for "Sneaker C" and calculates the average price based on the sales history for the past 12 months. Based on this information, it determines that the scarcity score is high because sales are declining but the price is rising.

[0348] Investment Advice Generation Embodiments

[0349] The server generates investment advice based on the analysis results. This advice is based on factors that predict the future value of a particular sneaker (for example, price appreciation rate or rarity score). The advice is provided to the user in an easy-to-understand format.

[0350] For example, if the average price of "Sneaker D" has increased by 20% over the past six months and the number of sales has decreased, the server will generate a recommendation that "Sneaker D" will become more valuable in the future.

[0351] Implementation of the delivery of investment advice

[0352] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0353] For example, if a user receives an investment advice notification about "Sneaker E" on their smartphone, they can open the app to check the detailed information and make an investment based on that information.

[0354] In this way, the present invention provides a system that automatically processes everything from collecting sneaker market data to analyzing it, generating investment advice, and finally distributing it, allowing users to efficiently obtain accurate information and make optimal investment decisions.

[0355] The processing flow will be explained below.

[0356] Step 1:

[0357] The server accesses online marketplaces, auction sites, and social networking sites on the Internet to collect sneaker sales data. Specifically, it sends an HTTP request to the URL of each data source and retrieves the HTML page.

[0358] Step 2:

[0359] The server parses the HTML page and extracts information such as the sneaker model name, release date, and sale price. For example, an HTML parsing library is used to extract the necessary data from specific tags.

[0360] Step 3:

[0361] The server temporarily organizes the extracted data into a data structure such as a list or dictionary, then establishes a connection to the database and stores the data in the appropriate tables.

[0362] Step 4:

[0363] To analyze the stored data, the server queries the database to retrieve the necessary information, for example, sales data for a particular sneaker for the past year.

[0364] Step 5:

[0365] The server uses the acquired data to analyze sneaker rarity and price trends, calculating declines in sales and increases in price to calculate a rarity score.

[0366] Step 6:

[0367] The server generates investment advice based on the analysis results. For example, if it predicts that a particular pair of sneakers is likely to increase in value in the future, it generates a recommendation for that sneaker.

[0368] Step 7:

[0369] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[0370] Step 8:

[0371] Users receive investment advice delivered to their devices, then open an app or email to check detailed information, and use that information to make optimal investment decisions.

[0372] Example 1

[0373] 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."

[0374] In conventional market analysis systems, the collection, organization, and analysis of market data, as well as the generation and distribution of investment advice, were all carried out separately, resulting in complex processes and making it difficult to update data and make investment decisions in real time.In addition, the limited scope of data collection meant that data coverage and analytical accuracy were low.

[0375] 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.

[0376] In this invention, the server includes a means for collecting market data, a means for organizing and storing the collected market data, and a means for analyzing the stored market data. This automates the entire process of data collection, analysis, and investment advice generation and distribution in the sneaker market, enabling real-time data updates and efficient investment decisions.

[0377] "Market data" refers to data including sales information, price information, sales dates, number of transactions, etc., of products traded in the market.

[0378] "Online marketplace" refers to a platform for buying and selling goods over the Internet.

[0379] "Auction Site" means a website where bidding and auctioning of items takes place online.

[0380] "Social networking service" refers to a service on the Internet that enables users to share content and communicate with each other.

[0381] An "information terminal" is a device that a user uses to receive information, and includes a smartphone, a computer, etc.

[0382] "Database" refers to a management system for efficiently storing and retrieving data.

[0383] "Analysis" refers to the process of analyzing collected data to find specific patterns or trends.

[0384] "Investment advice" refers to information that recommends appropriate investment actions based on the results of data analysis.

[0385] This invention is a system that collects and analyzes sneaker market data and provides investment advice based on that data. This system automatically performs a series of processes: collecting necessary information from various data sources, analyzing the data, generating investment advice, and distributing it to users.

[0386] Data collection implementation

[0387] The server collects market data from online marketplaces, auction sites, and social networking services. Specifically, it sends HTTP requests and parses the HTML pages it retrieves to extract information such as sneaker model name, release date, and sale price. It uses an HTML parsing library such as Beautiful Soup to parse the HTML.

[0388] Examples:

[0389] The server periodically accesses "Online Market A" and retrieves the HTML of the product list page.

[0390] The server uses Beautiful Soup to parse the HTML and extract data such as the name of the sneaker "Model X," the release date "2023-09-15," and the sale price "$300."

[0391] Data Storage Implementation

[0392] The extracted market data is organized and stored in a database on the server, which includes fields such as sneaker model name, release date, and sales price.

[0393] Examples:

[0394] The server connects to the database and inserts the newly extracted "Model X" data into the sneaker information table.

[0395] The database stores the following information: model name "Model X," sales date "2023-09-15," and sales price "$300."

[0396] Data Analysis Embodiments

[0397] The server runs an algorithm that analyzes the stored data. This involves calculating sneaker rarity and price trends based on past sales data. The data is analyzed using Python's Scikit-learn and Pandas libraries to calculate average prices, sales numbers, and rarity scores.

[0398] Examples:

[0399] The server calculates price trends using Model Y sales data from the past 12 months.

[0400] The server calculates the average price and number of sales, and if it sees that the number of sales is decreasing and the price is increasing, it gives a high scarcity score.

[0401] Investment Advice Generation Embodiments

[0402] The server generates investment advice based on the data analysis results. Using a generative AI model, the server inputs the analysis results as prompt sentences to generate investment advice that is easy for users to understand.

[0403] Examples:

[0404] The server analyzes that the average price of the Model Y has increased by 20% over the past six months, while sales have declined.

[0405] The server uses the generative AI model to generate investment advice such as "Model Y will become more valuable in the future."

[0406] Implementation of the delivery of investment advice

[0407] The generated investment advice is delivered to the user's device via push notification, email, etc. The user can check the delivered notification and obtain detailed investment advice.

[0408] Examples:

[0409] The server sends push notifications using a notification service such as Firebase.

[0410] The device receives a notification, and the user taps on it to open the application, which displays detailed information about the investment advice.

[0411] Users receive investment advice notifications about the Model Z, open the app to review the information, and make an investment decision.

[0412] Example prompt sentence:

[0413] "Collect and analyze sneaker market data from online marketplace A, generate investment advice based on the results, and send it to the user's device via push notification."

[0414] The system automatically collects market data, analyzes the data, and generates and distributes investment advice, enabling users to obtain accurate information in real time and make optimal investment decisions.

[0415] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0416] System program processing flow

[0417] The program of this system is executed in the following processing steps.

[0418] Step 1: Data collection

[0419] A server collects sneaker market data from online marketplaces, auction sites, and social networking services.

[0420] Specific behavior:

[0421] Input: List of data source URLs

[0422] Processing: The server sends an HTTP request to each data source to retrieve an HTML page, which it then parses with an HTML parsing library such as Beautiful Soup.

[0423] Output: A list of sneaker models, release dates, and prices

[0424] Examples:

[0425] The server accesses "Online Marketplace A" and retrieves the HTML of the product list page (e.g., URL: https: / / example.com / products).

[0426] The server uses Beautiful Soup to parse the HTML and extract the following information: model "Model X", sale date "2023-09-15", and sale price "$300".

[0427] Step 2: Save data

[0428] The server organizes and stores the extracted market data in a database.

[0429] Specific behavior:

[0430] Input: Data extracted in step 1

[0431] Processing: The server connects to the database and inserts new data into the sneaker information table.

[0432] Output: Data stored in the database

[0433] Examples:

[0434] The server connects to the database and saves the data of model name "Model X", release date "2023-09-15", and sale price "$300" in the sneaker information table.

[0435] Step 3: Data analysis

[0436] The server runs algorithms that analyze the stored data.

[0437] Specific behavior:

[0438] Input: Sneaker market data stored in a database

[0439] Processing: The server uses Python's Scikit-learn and Pandas libraries to analyze historical sales data and calculate price trends, average prices, and scarcity scores.

[0440] Output: Analysis results (price trends, average price, scarcity score, etc.)

[0441] Examples:

[0442] The server retrieves sales data for the Model Y for the past 12 months from the database and calculates price trends.

[0443] The server assigns a high scarcity score based on the declining number of sales and rising prices.

[0444] Step 4: Investment advice generation

[0445] The server generates investment advice based on the analysis results.

[0446] Specific behavior:

[0447] Input: Analysis results (price trends, average price, scarcity score, etc.)

[0448] Processing: The server inputs the analysis results into the generative AI model as prompt sentences to generate investment advice that is easy for the user to understand.

[0449] Output: Generated investment advice

[0450] Examples:

[0451] The server generates investment advice based on the fact that the price of the Model Y has risen 20% over the past six months and sales have declined, stating that the Model Y will become more valuable in the future.

[0452] Step 5: Providing investment advice

[0453] The server distributes the generated investment advice to the information terminal.

[0454] Specific behavior:

[0455] Input: Generated investment advice

[0456] Processing: The server uses a notification service such as Firebase to deliver advice to the user's information device via push notification or email.

[0457] Output: Investment advice delivered to the user's information terminal

[0458] Examples:

[0459] The server generates investment advice on the Model Z and sends a push notification to the user's smartphone via Firebase.

[0460] The user receives a notification and opens the app to see more information.

[0461] Through this series of processing steps, users can obtain accurate investment information in real time, enabling them to make optimal investment decisions.

[0462] (Application example 1)

[0463] 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."

[0464] In today's sneaker market, where sneaker values ​​fluctuate rapidly, it is difficult for users to make appropriate investment decisions based on this information. Furthermore, if users do not have a way to directly purchase sneakers after receiving investment advice, they are unable to take prompt investment action. This can result in users missing out on advantageous investment opportunities.

[0465] 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.

[0466] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for delivering generated investment advice to a user terminal, and means for enabling the user to directly purchase the generated investment advice, thereby enabling the user to quickly receive reliable investment advice based on market data and immediately purchase sneakers.

[0467] "Data collection means" refers to the part that has the function of obtaining sneaker market data from online markets, auction sites, social networks, etc.

[0468] The "data organization means" is a part that organizes collected market data into a format suitable for analysis and stores it in a database or the like.

[0469] "Data storage means" refers to a database, storage system, or other part that stores organized market data efficiently and effectively.

[0470] The "data analysis means" refers to the part that uses algorithms and calculations to analyze sneaker rarity and price trends based on stored market data.

[0471] The "investment advice generation means" is a part that has the function of predicting future increases in the value of sneakers based on the analysis results and creating appropriate investment advice.

[0472] The "investment advice distribution means" is a part that includes a push notification system and an email system for notifying the user's terminal of the generated investment advice.

[0473] The "purchase means" is a function that allows the user to directly purchase sneakers based on the investment advice received.

[0474] This invention is a system that collects and analyzes sneaker market data, generates and distributes investment advice, and allows users to directly purchase sneakers based on that advice. The system consists of the following main components:

[0475] First, the server collects sneaker market data from multiple data sources, including online marketplaces, auction sites, and social networks. This involves sending an HTTP request to retrieve an HTML page containing sales information, parsing the HTML page to extract the required data, and then the server organizes this collected data and stores it in a database.

[0476] The server then analyzes the stored data. This data analysis uses algorithms to calculate the rarity and price trends of sneakers. For example, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. It also calculates a rarity score, which can be used to predict future value increases.

[0477] Based on the analysis results, the server generates investment advice based on factors that predict the future value of a particular sneaker (e.g., price appreciation rate and rarity score), and provides the advice in a format that is easy for users to understand.

[0478] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0479] Furthermore, users can directly purchase sneakers based on the advice. The server not only provides users with investment advice but also provides an interface for them to actually purchase the sneakers. This allows users to make quick investment decisions and execute them.

[0480] For example, if one day "Sneaker X" becomes particularly rare and its price rises, the user will be notified with the following advice:

[0481] "Sneaker X has increased in price by 25% over the past six months, and sales are declining. Consider investing in this sneaker as it is likely to continue to increase in value."

[0482] Examples of prompts for generative AI models include:

[0483] "Analyze the future value increase potential of Sneaker X based on the price fluctuation and sales data of the past six months. If the price increase rate is high, generate a message recommending investment to the user."

[0484] The above system can be a powerful tool for users to make efficient and accurate investment decisions in the sneaker market.

[0485] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0486] Step 1:

[0487] The server collects sneaker market data from online marketplaces, auction sites, and social networks using HTTP requests. The server retrieves HTML pages from each data source and parses them to extract data such as sneaker model name, sale date, and sale price. The input is the retrieved HTML data, and the output is the parsed sneaker market data.

[0488] Step 2:

[0489] The server then organizes the parsed sneaker market data appropriately and stores it in a database. The input is the parsed market data, and the output is the data stored in an organized format in the database. For example, information such as the model name "Sneaker A," the release date "2023-10-01," and the sale price "$120" is stored in the database.

[0490] Step 3:

[0491] The server runs an algorithm to analyze the stored data. Specifically, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. The input is market data stored in the database, and the output is the analysis results (e.g., average price, number of sales, rarity score).

[0492] Step 4:

[0493] The server generates investment advice based on the analysis results. This advice is based on factors such as price growth rate and scarcity score. The input is the analysis results, and the output is investment advice to be provided to the user. For example: "Sneaker B has increased in average price by 20% over the past six months and sales have decreased, so it is predicted to increase in value in the future."

[0494] Step 5:

[0495] The server delivers the generated investment advice to the user's device. Push notifications and emails are used as delivery methods. The input is the generated investment advice text, and the output is the notification sent to the user's device. Example: "Investment advice on sneaker C has been sent."

[0496] Step 6:

[0497] The user can confirm the investment advice and purchase the sneakers directly through the application. When the user presses the purchase button based on the advice received on the user's device, the server processes the purchase request and completes the transaction. The input is the user's purchase request, and the output is a purchase completion notification or a purchase rejection notification.

[0498] Through these steps, the system can efficiently collect and analyze sneaker market data, provide useful investment advice to users, and support quick purchases.

[0499] 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.

[0500] To put this invention into practice, a system is required that collects and analyzes sneaker market data and provides investment advice based on that data, and an emotion engine is also required that recognizes and analyzes user emotions. The specific configuration and operation of the system are described below.

[0501] Data collection implementation

[0502] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[0503] Data Storage Implementation

[0504] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[0505] Data Analysis Embodiments

[0506] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price history of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[0507] Embodiment of Emotion Engine

[0508] Next, the server uses an emotion engine to recognize and analyze the user's emotion data. This emotion engine infers emotions based on the user's input data and behavioral logs (e.g., clicks, browsing time, and purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[0509] Investment Advice Generation Embodiments

[0510] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the results of sneaker market data analysis. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice will be provided.

[0511] Implementation of the delivery of investment advice

[0512] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0513] As a concrete example, consider the following scenario:

[0514] The server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database.

[0515] At the same time, the emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X."

[0516] The server analyzes market data and user sentiment data for "Sneaker X" and determines that the value of the sneakers will increase in the future.

[0517] The advice generated by the server includes the content that now is the time to buy "Sneaker X" and is delivered to the user's device.

[0518] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[0519] The processing flow will be explained below.

[0520] Step 1:

[0521] The server collects sneaker market data from online marketplaces, auction sites, and social media sites. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[0522] Step 2:

[0523] The server organizes the extracted data and stores it in a database, specifically in a table with fields such as sneaker model name, release date, and sales price.

[0524] Step 3:

[0525] The server queries the database to retrieve the necessary information, such as sales data for a particular sneaker over the past year, and analyzes the sneaker's rarity and price trends based on this data.

[0526] Step 4:

[0527] The server runs algorithms to analyze the stored data, calculating declines in sales and price increases, and deriving a scarcity score. For example, it calculates the average price and number of sneakers sold and compares it with historical data.

[0528] Step 5:

[0529] The server launches an emotion engine to obtain user emotion data. The emotion engine estimates emotions based on the user's behavior log (e.g., clicks, browsing time, purchasing behavior) and input data. For example, if a user frequently views a particular sneaker model, it evaluates the user as having a high interest in that sneaker.

[0530] Step 6:

[0531] The server generates investment advice by combining the emotional data obtained by the emotion engine with the results of market data analysis. Specifically, the content of the investment advice is adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice is provided.

[0532] Step 7:

[0533] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[0534] Step 8:

[0535] Users receive investment advice delivered to their devices, open an app or email to view detailed information, and make optimal investment decisions based on that information. For example, they tap on an app notification to view detailed information about recommended sneakers and make a purchase decision based on that information.

[0536] The system allows users to receive accurate and personalized investment advice based on their emotional state and market data.

[0537] Example 2

[0538] 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."

[0539] In a system that collects and analyzes sneaker market data and provides investment advice based on that data, there is a challenge in generating and providing more appropriate and personalized advice by recognizing and analyzing user emotions. To solve this problem, it is necessary to accurately capture the user's emotional state and dynamically adjust investment advice based on that.

[0540] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0541] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for recognizing and analyzing user emotion data, means for generating investment advice based on the analysis results, and means for delivering the generated investment advice to the user terminal, thereby making it possible to provide personalized investment advice that takes into account the user's emotional state.

[0542] "Data" refers to information or figures collected from sources and used for analysis.

[0543] "Means of collection" refers to the methods and tools used to obtain data from online marketplaces, auction sites, social networking services, etc.

[0544] "Means of organizing and storing" refers to methods and tools for formatting collected data into a certain format and storing it safely and efficiently in storage such as a database.

[0545] "Means of analysis" refers to algorithms and tools that use stored data to analyze market trends and user behavior patterns.

[0546] "User emotional data" refers to information about the emotional state estimated based on the user's input data and behavioral log.

[0547] "Means of recognition and analysis" refers to the algorithms and tools used to collect and analyze user emotional data.

[0548] "Means for generating investment advice" refers to methods and tools for creating optimal investment advice based on data analysis results and user sentiment data.

[0549] "Means of delivery" refers to the methods and tools used to deliver the generated investment advice to the user's terminal.

[0550] "User terminal" refers to a device such as a smartphone or computer that a user uses to receive information or perform operations.

[0551] "Server" refers to a computer system for executing a series of processes such as data collection, analysis, storage, advice generation and distribution.

[0552] This invention is a system that collects and analyzes sneaker market data and user sentiment data, and provides investment advice. This system operates with the following configuration.

[0553] First, the server collects data. The server gathers sneaker data from multiple sources, including online marketplaces, auction sites, and social networking services. This data collection is done using HTTP requests and web scraping libraries such as BeautifulSoup and Scrapy. For example, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the Nike Air Max.

[0554] Next, the server organizes the collected data and stores it in a database. For this, it uses a relational database such as "PostgreSQL" or "MySQL." The server formats the collected data appropriately and inserts it into the database. Specifically, the server stores the Nike Air Max data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[0555] The server then performs analysis based on the stored data. This analysis uses machine learning libraries such as "pandas" and "scikit-learn" to calculate the price history and sales volume of a specific sneaker and calculate a rarity score. For example, based on the price of Nike Air Max over the past year, the server determines that the average price is $220 and the rarity score is 85.

[0556] Furthermore, the server uses an emotion engine to recognize and analyze user emotion data. When a user browses a page, their behavioral logs (clicks, browsing time, purchasing behavior) are collected and their emotions are estimated using natural language processing engines such as TensorFlow and IBM Watson. For example, if a user frequently browses a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[0557] The server then combines the sentiment data and market data to generate investment advice. The server integrates the analysis results with the sentiment data and inputs a prompt statement into the generative AI model. For example, the server might input "If the user is highly interested in Nike Air Max, please generate investment advice," and the model would generate the advice "Now is the time to buy Nike Air Max."

[0558] Finally, the server delivers the generated investment advice to the user's device. This delivery can be done using methods such as push notification or email. The user receives the notification or email, checks the content, and then makes an investment decision. For example, the user's device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[0559] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[0560] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0561] Step 1:

[0562] The server collects sneaker market data from online marketplaces, auction sites, and social networking services. It lists the URLs of each data source as input and sends HTTP requests based on them. It obtains an HTML page as output, parses the page using the "BeautifulSoup" library, and extracts information such as the sneaker model name, release date, and sale price. Specifically, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the "Nike Air Max" on that page.

[0563] Step 2:

[0564] The server organizes the acquired data and saves it in a database. It formats the information extracted as input, such as the sneaker model name, release date, and sales price, connects to the "PostgreSQL" database, and inserts it into the database. The organized data is saved in the database as output. Specifically, the server saves the "Nike Air Max" data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[0565] Step 3:

[0566] The server performs analysis based on the stored data. It retrieves past sales data from the database as input using a query and processes the data using the "pandas" library. It then runs an algorithm to calculate the rarity score using "scikit-learn." The output is the price history of the sneakers, the average price, the number of sales, and the rarity score. Specifically, the server calculates that the average price is $220 and the rarity score is 85 based on the prices of "Nike Air Max" over the past year.

[0567] Step 4:

[0568] The server uses an emotion engine to recognize and analyze user emotion data. As input, it collects behavioral logs such as user clicks, browsing time, and purchasing behavior. It then uses TensorFlow and IBM Watson to run the emotion engine and estimate the user's emotions. The output is an evaluation of the user's emotional state. Specifically, the server assesses that the user has a high level of interest and anticipation based on the long time they spent browsing the Nike Air Max page.

[0569] Step 5:

[0570] The server combines the sentiment data and market data to generate investment advice. As input, it integrates the analyzed market data and sentiment data and inputs a prompt statement into the generative AI model. As output, the investment advice obtained from the generative AI model is generated. Specifically, the prompt statement is input as "If the user shows a high interest in Nike Air Max, please generate investment advice," and the model generates the advice "Now is the time to buy Nike Air Max."

[0571] Step 6:

[0572] The server delivers the generated investment advice to the user's device. Using the generated investment advice as input, it delivers it to the user's device via push notification or email. The investment advice is sent to the user's device as output, and the user confirms it. Specifically, the device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[0573] (Application example 2)

[0574] 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."

[0575] Conventional investment advice systems only analyze market data for investment targets, making it impossible to provide appropriate advice that takes into account the user's emotional state. It is also difficult to generate personalized advice based on the user's behavior and emotions. As a result, the advice users receive is general and does not fully address their individual needs and emotions.

[0576] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for analyzing user emotion data, means for generating investment advice based on the analysis results and the emotion data, and means for delivering the generated investment advice to the user terminal. This makes it possible to provide specific and personalized investment advice based on the user's individual emotional state and market data.

[0577] "Data collection means" refers to mechanisms for obtaining sneaker market data from online marketplaces, auction sites, and social media.

[0578] "Means for organizing and storing collected data" refers to a mechanism for structuring acquired data and storing it in a database.

[0579] The "means for analyzing stored data" refers to a mechanism that includes algorithms for calculating sneaker rarity and price trends based on collected market data.

[0580] The "means for analyzing user emotion data" is a mechanism including an emotion engine for estimating an emotional state using a user's behavior log and input data.

[0581] The "means for generating investment advice based on the analysis results and emotional data" is a mechanism for combining the analyzed market data with the user's emotional data to generate optimal investment advice.

[0582] The "means for delivering the generated investment advice to the user terminal" is a mechanism for sending the generated investment advice to the user's smartphone or computer via push notification or email.

[0583] The following describes an embodiment of the present invention. The system implements a series of functions including data collection, organization and storage, data analysis, sentiment analysis, investment advice generation, and distribution. This makes it possible to provide investment advice that takes into account the user's sentiment.

[0584] Data collection implementation

[0585] The server collects sneaker market data from online marketplaces, auction sites, and social media, sending HTTP requests to the URLs of each data source, retrieving HTML pages and parsing them to extract information such as sneaker model name, sale date, and sale price.

[0586] Data Storage Implementation

[0587] The collected data is organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price, allowing for efficient data storage and retrieval.

[0588] Data Analysis Embodiments

[0589] The server runs algorithms to analyze the stored market data. This analysis uses historical sales data to calculate sneaker rarity and price trends. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[0590] Embodiment of Emotion Engine

[0591] The server uses an emotion engine to recognize and analyze user emotion data. The emotion engine infers emotions based on user input data and behavioral logs (clicks, browsing time, purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, it infers that the user has a high level of interest and anticipation for that sneaker.

[0592] Investment Advice Generation Embodiments

[0593] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the sneaker market data analysis results. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, the server will provide low-risk investment advice, and if the user is in a positive emotional state, the server will provide risky but high-reward investment advice.

[0594] Implementation of the delivery of investment advice

[0595] The generated investment advice is delivered to the user's device via push notifications to their smartphone or email. Users can receive these notifications, check the content, and make appropriate investment decisions.

[0596] Specific examples

[0597] As an example, a server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database. The emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X." The server analyzes the market data for "Sneaker X" and the user's emotion data and determines that the value of these sneakers will increase in the future. The advice generated by the server, including the content that now is the time to buy "Sneaker X," is delivered to the user's device.

[0598] Prompt Sentence Examples

[0599] By inputting the following prompt sentences into the generative AI model, the information necessary to generate investment advice can be obtained.

[0600] "Please provide detailed steps to build an application that collects and analyzes sneaker market data from an online marketplace and combines it with user sentiment data to generate investment advice. Please include the following elements:

[0601] 1. Specific methods of data collection and storage

[0602] 2. How to analyze market data and user sentiment data

[0603] 3. Algorithm for generating investment advice

[0604] 4. How to deliver advice to user devices

[0605] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0606] Step 1:

[0607] The server collects sneaker market data from online marketplaces, auction sites, and social media. Specifically, it sends HTTP requests to the URLs of each data source and parses the resulting HTML pages. It extracts information such as the sneaker model name, release date, and sale price from the parsed results. The input is the data source URL, and the output is the parsed market data.

[0608] Step 2:

[0609] The server organizes the collected market data and stores it in a database. The data is divided into fields such as sneaker model name, release date, and sales price. The input is the organized market data, and the output is the data stored in the database. Specifically, the server inserts data into the database using SQL queries.

[0610] Step 3:

[0611] The server analyzes market data stored in a database. It runs an algorithm to calculate the rarity and price trends of sneakers based on past sales data. The input is the market data in the database, and the output is the analyzed price trends and rarity score. Specific operations include calculating the average price and tallying the number of sales.

[0612] Step 4:

[0613] The server analyzes the user's emotional data. The emotion engine uses the user's behavior log (clicks, browsing time, purchasing behavior) to estimate the emotional state. The input is the user's behavior data, and the output is an emotion score. Specifically, the emotion engine is used to analyze the user log and calculate the emotion score.

[0614] Step 5:

[0615] The server generates investment advice based on the analysis results and sentiment data. It combines the market data analysis results with sentiment scores to create optimal investment advice. The inputs are price trends, scarcity scores, and sentiment scores, and the output is investment advice. Specifically, it adjusts the content and wording of the advice to generate investment advice statements.

[0616] Step 6:

[0617] The server distributes the generated investment advice to the user's device. The distribution method is push notification or email. The input is the generated investment advice, and the output is a notification to the user's device. Specifically, the server uses a notification service to send the advice to the user's smartphone or computer.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] [Third embodiment]

[0622] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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."

[0634] To put this invention into practice, a system is constructed that collects and analyzes sneaker market data and provides investment advice based on that data. The specific configuration and operation of the system are described below.

[0635] Data collection implementation

[0636] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. This involves sending HTTP requests to each data source to retrieve HTML pages containing sales information. The HTML pages are then parsed to extract necessary data such as the sneaker model name, sale date, and sale price.

[0637] For example, if a server were to collect data from "Online Marketplace A," the following steps would be taken: The server would access the product listing page of "Online Marketplace A" and retrieve the HTML. Using an HTML parsing library, it would extract information such as the sneaker name, price, and sale date.

[0638] Data Storage Implementation

[0639] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[0640] For example, if the server collects data on "Sneaker B," it will be stored in a database table as follows:

[0641] Model Name: Sneakers B

[0642] Sale date: 2023-09-15

[0643] Sale price: 300

[0644] Data Analysis Embodiments

[0645] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price and number of sales. A rarity score is also calculated, which can be used to predict future value increases.

[0646] As a specific example, the server analyzes data for "Sneaker C" and calculates the average price based on the sales history for the past 12 months. Based on this information, it determines that the scarcity score is high because sales are declining but the price is rising.

[0647] Investment Advice Generation Embodiments

[0648] The server generates investment advice based on the analysis results. This advice is based on factors that predict the future value of a particular sneaker (for example, price appreciation rate or rarity score). The advice is provided to the user in an easy-to-understand format.

[0649] For example, if the average price of "Sneaker D" has increased by 20% over the past six months and the number of sales has decreased, the server will generate a recommendation that "Sneaker D" will become more valuable in the future.

[0650] Implementation of the delivery of investment advice

[0651] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0652] For example, if a user receives an investment advice notification about "Sneaker E" on their smartphone, they can open the app to check the detailed information and make an investment based on that information.

[0653] In this way, the present invention provides a system that automatically processes everything from collecting sneaker market data to analyzing it, generating investment advice, and finally distributing it, allowing users to efficiently obtain accurate information and make optimal investment decisions.

[0654] The processing flow will be explained below.

[0655] Step 1:

[0656] The server accesses online marketplaces, auction sites, and social networking sites on the Internet to collect sneaker sales data. Specifically, it sends an HTTP request to the URL of each data source and retrieves the HTML page.

[0657] Step 2:

[0658] The server parses the HTML page and extracts information such as the sneaker model name, release date, and sale price. For example, an HTML parsing library is used to extract the necessary data from specific tags.

[0659] Step 3:

[0660] The server temporarily organizes the extracted data into a data structure such as a list or dictionary, then establishes a connection to the database and stores the data in the appropriate tables.

[0661] Step 4:

[0662] To analyze the stored data, the server queries the database to retrieve the necessary information, for example, sales data for a particular sneaker for the past year.

[0663] Step 5:

[0664] The server uses the acquired data to analyze sneaker rarity and price trends, calculating declines in sales and increases in price to calculate a rarity score.

[0665] Step 6:

[0666] The server generates investment advice based on the analysis results. For example, if it predicts that a particular pair of sneakers is likely to increase in value in the future, it generates a recommendation for that sneaker.

[0667] Step 7:

[0668] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[0669] Step 8:

[0670] Users receive investment advice delivered to their devices, then open an app or email to check detailed information, and use that information to make optimal investment decisions.

[0671] Example 1

[0672] 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."

[0673] In conventional market analysis systems, the collection, organization, and analysis of market data, as well as the generation and distribution of investment advice, were all carried out separately, resulting in complex processes and making it difficult to update data and make investment decisions in real time.In addition, the limited scope of data collection meant that data coverage and analytical accuracy were low.

[0674] 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.

[0675] In this invention, the server includes a means for collecting market data, a means for organizing and storing the collected market data, and a means for analyzing the stored market data. This automates the entire process of data collection, analysis, and investment advice generation and distribution in the sneaker market, enabling real-time data updates and efficient investment decisions.

[0676] "Market data" refers to data including sales information, price information, sales dates, number of transactions, etc., of products traded in the market.

[0677] "Online marketplace" refers to a platform for buying and selling goods over the Internet.

[0678] "Auction Site" means a website where bidding and auctioning of items takes place online.

[0679] "Social networking service" refers to a service on the Internet that enables users to share content and communicate with each other.

[0680] An "information terminal" is a device that a user uses to receive information, and includes a smartphone, a computer, etc.

[0681] "Database" refers to a management system for efficiently storing and retrieving data.

[0682] "Analysis" refers to the process of analyzing collected data to find specific patterns or trends.

[0683] "Investment advice" refers to information that recommends appropriate investment actions based on the results of data analysis.

[0684] This invention is a system that collects and analyzes sneaker market data and provides investment advice based on that data. This system automatically performs a series of processes: collecting necessary information from various data sources, analyzing the data, generating investment advice, and distributing it to users.

[0685] Data collection implementation

[0686] The server collects market data from online marketplaces, auction sites, and social networking services. Specifically, it sends HTTP requests and parses the HTML pages it retrieves to extract information such as sneaker model name, release date, and sale price. It uses an HTML parsing library such as Beautiful Soup to parse the HTML.

[0687] Examples:

[0688] The server periodically accesses "Online Market A" and retrieves the HTML of the product list page.

[0689] The server uses Beautiful Soup to parse the HTML and extract data such as the name of the sneaker "Model X," the release date "2023-09-15," and the sale price "$300."

[0690] Data Storage Implementation

[0691] The extracted market data is organized and stored in a database on the server, which includes fields such as sneaker model name, release date, and sales price.

[0692] Examples:

[0693] The server connects to the database and inserts the newly extracted "Model X" data into the sneaker information table.

[0694] The database stores the following information: model name "Model X," sales date "2023-09-15," and sales price "$300."

[0695] Data Analysis Embodiments

[0696] The server runs an algorithm that analyzes the stored data. This involves calculating sneaker rarity and price trends based on past sales data. The data is analyzed using Python's Scikit-learn and Pandas libraries to calculate average prices, sales numbers, and rarity scores.

[0697] Examples:

[0698] The server calculates price trends using Model Y sales data from the past 12 months.

[0699] The server calculates the average price and number of sales, and if it sees that the number of sales is decreasing and the price is increasing, it gives a high scarcity score.

[0700] Investment Advice Generation Embodiments

[0701] The server generates investment advice based on the data analysis results. Using a generative AI model, the server inputs the analysis results as prompt sentences to generate investment advice that is easy for users to understand.

[0702] Examples:

[0703] The server analyzes that the average price of the Model Y has increased by 20% over the past six months, while sales have declined.

[0704] The server uses the generative AI model to generate investment advice such as "Model Y will become more valuable in the future."

[0705] Implementation of the delivery of investment advice

[0706] The generated investment advice is delivered to the user's device via push notification, email, etc. The user can check the delivered notification and obtain detailed investment advice.

[0707] Examples:

[0708] The server sends push notifications using a notification service such as Firebase.

[0709] The device receives a notification, and the user taps on it to open the application, which displays detailed information about the investment advice.

[0710] Users receive investment advice notifications about the Model Z, open the app to review the information, and make an investment decision.

[0711] Example prompt sentence:

[0712] "Collect and analyze sneaker market data from online marketplace A, generate investment advice based on the results, and send it to the user's device via push notification."

[0713] The system automatically collects market data, analyzes the data, and generates and distributes investment advice, enabling users to obtain accurate information in real time and make optimal investment decisions.

[0714] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0715] System program processing flow

[0716] The program of this system is executed in the following processing steps.

[0717] Step 1: Data collection

[0718] A server collects sneaker market data from online marketplaces, auction sites, and social networking services.

[0719] Specific behavior:

[0720] Input: List of data source URLs

[0721] Processing: The server sends an HTTP request to each data source to retrieve an HTML page, which it then parses with an HTML parsing library such as Beautiful Soup.

[0722] Output: A list of sneaker models, release dates, and prices

[0723] Examples:

[0724] The server accesses "Online Marketplace A" and retrieves the HTML of the product list page (e.g., URL: https: / / example.com / products).

[0725] The server uses Beautiful Soup to parse the HTML and extract the following information: model "Model X", sale date "2023-09-15", and sale price "$300".

[0726] Step 2: Save data

[0727] The server organizes and stores the extracted market data in a database.

[0728] Specific behavior:

[0729] Input: Data extracted in step 1

[0730] Processing: The server connects to the database and inserts new data into the sneaker information table.

[0731] Output: Data stored in the database

[0732] Examples:

[0733] The server connects to the database and saves the data of model name "Model X", release date "2023-09-15", and sale price "$300" in the sneaker information table.

[0734] Step 3: Data analysis

[0735] The server runs algorithms that analyze the stored data.

[0736] Specific behavior:

[0737] Input: Sneaker market data stored in a database

[0738] Processing: The server uses Python's Scikit-learn and Pandas libraries to analyze historical sales data and calculate price trends, average prices, and scarcity scores.

[0739] Output: Analysis results (price trends, average price, scarcity score, etc.)

[0740] Examples:

[0741] The server retrieves sales data for the Model Y for the past 12 months from the database and calculates price trends.

[0742] The server assigns a high scarcity score based on the declining number of sales and rising prices.

[0743] Step 4: Investment advice generation

[0744] The server generates investment advice based on the analysis results.

[0745] Specific behavior:

[0746] Input: Analysis results (price trends, average price, scarcity score, etc.)

[0747] Processing: The server inputs the analysis results into the generative AI model as prompt sentences to generate investment advice that is easy for the user to understand.

[0748] Output: Generated investment advice

[0749] Examples:

[0750] The server generates investment advice based on the fact that the price of the Model Y has risen 20% over the past six months and sales have declined, stating that the Model Y will become more valuable in the future.

[0751] Step 5: Providing investment advice

[0752] The server distributes the generated investment advice to the information terminal.

[0753] Specific behavior:

[0754] Input: Generated investment advice

[0755] Processing: The server uses a notification service such as Firebase to deliver advice to the user's information device via push notification or email.

[0756] Output: Investment advice delivered to the user's information terminal

[0757] Examples:

[0758] The server generates investment advice on the Model Z and sends a push notification to the user's smartphone via Firebase.

[0759] The user receives a notification and opens the app to see more information.

[0760] Through this series of processing steps, users can obtain accurate investment information in real time, enabling them to make optimal investment decisions.

[0761] (Application example 1)

[0762] 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."

[0763] In today's sneaker market, where sneaker values ​​fluctuate rapidly, it is difficult for users to make appropriate investment decisions based on this information. Furthermore, if users do not have a way to directly purchase sneakers after receiving investment advice, they are unable to take prompt investment action. This can result in users missing out on advantageous investment opportunities.

[0764] 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.

[0765] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for delivering generated investment advice to a user terminal, and means for enabling the user to directly purchase the generated investment advice, thereby enabling the user to quickly receive reliable investment advice based on market data and immediately purchase sneakers.

[0766] "Data collection means" refers to the part that has the function of obtaining sneaker market data from online markets, auction sites, social networks, etc.

[0767] The "data organization means" is a part that organizes collected market data into a format suitable for analysis and stores it in a database or the like.

[0768] "Data storage means" refers to a database, storage system, or other part that stores organized market data efficiently and effectively.

[0769] The "data analysis means" refers to the part that uses algorithms and calculations to analyze sneaker rarity and price trends based on stored market data.

[0770] The "investment advice generation means" is a part that has the function of predicting future increases in the value of sneakers based on the analysis results and creating appropriate investment advice.

[0771] The "investment advice distribution means" is a part that includes a push notification system and an email system for notifying the user's terminal of the generated investment advice.

[0772] The "purchase means" is a function that allows the user to directly purchase sneakers based on the investment advice received.

[0773] This invention is a system that collects and analyzes sneaker market data, generates and distributes investment advice, and allows users to directly purchase sneakers based on that advice. The system consists of the following main components:

[0774] First, the server collects sneaker market data from multiple data sources, including online marketplaces, auction sites, and social networks. This involves sending an HTTP request to retrieve an HTML page containing sales information, parsing the HTML page to extract the required data, and then the server organizes this collected data and stores it in a database.

[0775] The server then analyzes the stored data. This data analysis uses algorithms to calculate the rarity and price trends of sneakers. For example, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. It also calculates a rarity score, which can be used to predict future value increases.

[0776] Based on the analysis results, the server generates investment advice based on factors that predict the future value of a particular sneaker (e.g., price appreciation rate and rarity score), and provides the advice in a format that is easy for users to understand.

[0777] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0778] Furthermore, users can directly purchase sneakers based on the advice. The server not only provides users with investment advice but also provides an interface for them to actually purchase the sneakers. This allows users to make quick investment decisions and execute them.

[0779] For example, if one day "Sneaker X" becomes particularly rare and its price rises, the user will be notified with the following advice:

[0780] "Sneaker X has increased in price by 25% over the past six months, and sales are declining. Consider investing in this sneaker as it is likely to continue to increase in value."

[0781] Examples of prompts for generative AI models include:

[0782] "Analyze the future value increase potential of Sneaker X based on the price fluctuation and sales data of the past six months. If the price increase rate is high, generate a message recommending investment to the user."

[0783] The above system can be a powerful tool for users to make efficient and accurate investment decisions in the sneaker market.

[0784] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0785] Step 1:

[0786] The server collects sneaker market data from online marketplaces, auction sites, and social networks using HTTP requests. The server retrieves HTML pages from each data source and parses them to extract data such as sneaker model name, sale date, and sale price. The input is the retrieved HTML data, and the output is the parsed sneaker market data.

[0787] Step 2:

[0788] The server then organizes the parsed sneaker market data appropriately and stores it in a database. The input is the parsed market data, and the output is the data stored in an organized format in the database. For example, information such as the model name "Sneaker A," the release date "2023-10-01," and the sale price "$120" is stored in the database.

[0789] Step 3:

[0790] The server runs an algorithm to analyze the stored data. Specifically, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. The input is market data stored in the database, and the output is the analysis results (e.g., average price, number of sales, rarity score).

[0791] Step 4:

[0792] The server generates investment advice based on the analysis results. This advice is based on factors such as price growth rate and scarcity score. The input is the analysis results, and the output is investment advice to be provided to the user. For example: "Sneaker B has increased in average price by 20% over the past six months and sales have decreased, so it is predicted to increase in value in the future."

[0793] Step 5:

[0794] The server delivers the generated investment advice to the user's device. Push notifications and emails are used as delivery methods. The input is the generated investment advice text, and the output is the notification sent to the user's device. Example: "Investment advice on sneaker C has been sent."

[0795] Step 6:

[0796] The user can confirm the investment advice and purchase the sneakers directly through the application. When the user presses the purchase button based on the advice received on the user's device, the server processes the purchase request and completes the transaction. The input is the user's purchase request, and the output is a purchase completion notification or a purchase rejection notification.

[0797] Through these steps, the system can efficiently collect and analyze sneaker market data, provide useful investment advice to users, and support quick purchases.

[0798] 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.

[0799] To put this invention into practice, a system is required that collects and analyzes sneaker market data and provides investment advice based on that data, and an emotion engine is also required that recognizes and analyzes user emotions. The specific configuration and operation of the system are described below.

[0800] Data collection implementation

[0801] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[0802] Data Storage Implementation

[0803] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[0804] Data Analysis Embodiments

[0805] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price history of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[0806] Embodiment of Emotion Engine

[0807] Next, the server uses an emotion engine to recognize and analyze the user's emotion data. This emotion engine infers emotions based on the user's input data and behavioral logs (e.g., clicks, browsing time, and purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[0808] Investment Advice Generation Embodiments

[0809] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the results of sneaker market data analysis. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice will be provided.

[0810] Implementation of the delivery of investment advice

[0811] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0812] As a concrete example, consider the following scenario:

[0813] The server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database.

[0814] At the same time, the emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X."

[0815] The server analyzes market data and user sentiment data for "Sneaker X" and determines that the value of the sneakers will increase in the future.

[0816] The advice generated by the server includes the content that now is the time to buy "Sneaker X" and is delivered to the user's device.

[0817] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[0818] The processing flow will be explained below.

[0819] Step 1:

[0820] The server collects sneaker market data from online marketplaces, auction sites, and social media sites. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[0821] Step 2:

[0822] The server organizes the extracted data and stores it in a database, specifically in a table with fields such as sneaker model name, release date, and sales price.

[0823] Step 3:

[0824] The server queries the database to retrieve the necessary information, such as sales data for a particular sneaker over the past year, and analyzes the sneaker's rarity and price trends based on this data.

[0825] Step 4:

[0826] The server runs algorithms to analyze the stored data, calculating declines in sales and price increases, and deriving a scarcity score. For example, it calculates the average price and number of sneakers sold and compares it with historical data.

[0827] Step 5:

[0828] The server launches an emotion engine to obtain user emotion data. The emotion engine estimates emotions based on the user's behavior log (e.g., clicks, browsing time, purchasing behavior) and input data. For example, if a user frequently views a particular sneaker model, it evaluates the user as having a high interest in that sneaker.

[0829] Step 6:

[0830] The server generates investment advice by combining the emotional data obtained by the emotion engine with the results of market data analysis. Specifically, the content of the investment advice is adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice is provided.

[0831] Step 7:

[0832] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[0833] Step 8:

[0834] Users receive investment advice delivered to their devices, open an app or email to view detailed information, and make optimal investment decisions based on that information. For example, they tap on an app notification to view detailed information about recommended sneakers and make a purchase decision based on that information.

[0835] The system allows users to receive accurate and personalized investment advice based on their emotional state and market data.

[0836] Example 2

[0837] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0838] In a system that collects and analyzes sneaker market data and provides investment advice based on that data, there is a challenge in generating and providing more appropriate and personalized advice by recognizing and analyzing user emotions. To solve this problem, it is necessary to accurately capture the user's emotional state and dynamically adjust investment advice based on that.

[0839] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0840] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for recognizing and analyzing user emotion data, means for generating investment advice based on the analysis results, and means for delivering the generated investment advice to the user terminal, thereby making it possible to provide personalized investment advice that takes into account the user's emotional state.

[0841] "Data" refers to information or figures collected from sources and used for analysis.

[0842] "Means of collection" refers to the methods and tools used to obtain data from online marketplaces, auction sites, social networking services, etc.

[0843] "Means of organizing and storing" refers to methods and tools for formatting collected data into a certain format and storing it safely and efficiently in storage such as a database.

[0844] "Means of analysis" refers to algorithms and tools that use stored data to analyze market trends and user behavior patterns.

[0845] "User emotional data" refers to information about the emotional state estimated based on the user's input data and behavioral log.

[0846] "Means of recognition and analysis" refers to the algorithms and tools used to collect and analyze user emotional data.

[0847] "Means for generating investment advice" refers to methods and tools for creating optimal investment advice based on data analysis results and user sentiment data.

[0848] "Means of delivery" refers to the methods and tools used to deliver the generated investment advice to the user's terminal.

[0849] "User terminal" refers to a device such as a smartphone or computer that a user uses to receive information or perform operations.

[0850] "Server" refers to a computer system for executing a series of processes such as data collection, analysis, storage, advice generation and distribution.

[0851] This invention is a system that collects and analyzes sneaker market data and user sentiment data, and provides investment advice. This system operates with the following configuration.

[0852] First, the server collects data. The server gathers sneaker data from multiple sources, including online marketplaces, auction sites, and social networking services. This data collection is done using HTTP requests and web scraping libraries such as BeautifulSoup and Scrapy. For example, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the Nike Air Max.

[0853] Next, the server organizes the collected data and stores it in a database. For this, it uses a relational database such as "PostgreSQL" or "MySQL." The server formats the collected data appropriately and inserts it into the database. Specifically, the server stores the Nike Air Max data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[0854] The server then performs analysis based on the stored data. This analysis uses machine learning libraries such as "pandas" and "scikit-learn" to calculate the price history and sales volume of a specific sneaker and calculate a rarity score. For example, based on the price of Nike Air Max over the past year, the server determines that the average price is $220 and the rarity score is 85.

[0855] Furthermore, the server uses an emotion engine to recognize and analyze user emotion data. When a user browses a page, their behavioral logs (clicks, browsing time, purchasing behavior) are collected and their emotions are estimated using natural language processing engines such as TensorFlow and IBM Watson. For example, if a user frequently browses a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[0856] The server then combines the sentiment data and market data to generate investment advice. The server integrates the analysis results with the sentiment data and inputs a prompt statement into the generative AI model. For example, the server might input "If the user is highly interested in Nike Air Max, please generate investment advice," and the model would generate the advice "Now is the time to buy Nike Air Max."

[0857] Finally, the server delivers the generated investment advice to the user's device. This delivery can be done using methods such as push notification or email. The user receives the notification or email, checks the content, and then makes an investment decision. For example, the user's device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[0858] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[0859] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0860] Step 1:

[0861] The server collects sneaker market data from online marketplaces, auction sites, and social networking services. It lists the URLs of each data source as input and sends HTTP requests based on them. It obtains an HTML page as output, parses the page using the "BeautifulSoup" library, and extracts information such as the sneaker model name, release date, and sale price. Specifically, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the "Nike Air Max" on that page.

[0862] Step 2:

[0863] The server organizes the acquired data and saves it in a database. It formats the information extracted as input, such as the sneaker model name, release date, and sales price, connects to the "PostgreSQL" database, and inserts it into the database. The organized data is saved in the database as output. Specifically, the server saves the "Nike Air Max" data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[0864] Step 3:

[0865] The server performs analysis based on the stored data. It retrieves past sales data from the database as input using a query and processes the data using the "pandas" library. It then runs an algorithm to calculate the rarity score using "scikit-learn." The output is the price history of the sneakers, the average price, the number of sales, and the rarity score. Specifically, the server calculates that the average price is $220 and the rarity score is 85 based on the prices of "Nike Air Max" over the past year.

[0866] Step 4:

[0867] The server uses an emotion engine to recognize and analyze user emotion data. As input, it collects behavioral logs such as user clicks, browsing time, and purchasing behavior. It then uses TensorFlow and IBM Watson to run the emotion engine and estimate the user's emotions. The output is an evaluation of the user's emotional state. Specifically, the server assesses that the user has a high level of interest and anticipation based on the long time they spent browsing the Nike Air Max page.

[0868] Step 5:

[0869] The server combines the sentiment data and market data to generate investment advice. As input, it integrates the analyzed market data and sentiment data and inputs a prompt statement into the generative AI model. As output, the investment advice obtained from the generative AI model is generated. Specifically, the prompt statement is input as "If the user shows a high interest in Nike Air Max, please generate investment advice," and the model generates the advice "Now is the time to buy Nike Air Max."

[0870] Step 6:

[0871] The server delivers the generated investment advice to the user's device. Using the generated investment advice as input, it delivers it to the user's device via push notification or email. The investment advice is sent to the user's device as output, and the user confirms it. Specifically, the device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[0872] (Application example 2)

[0873] 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."

[0874] Conventional investment advice systems only analyze market data for investment targets, making it impossible to provide appropriate advice that takes into account the user's emotional state. It is also difficult to generate personalized advice based on the user's behavior and emotions. As a result, the advice users receive is general and does not fully address their individual needs and emotions.

[0875] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for analyzing user emotion data, means for generating investment advice based on the analysis results and the emotion data, and means for delivering the generated investment advice to the user terminal. This makes it possible to provide specific and personalized investment advice based on the user's individual emotional state and market data.

[0876] "Data collection means" refers to mechanisms for obtaining sneaker market data from online marketplaces, auction sites, and social media.

[0877] "Means for organizing and storing collected data" refers to a mechanism for structuring acquired data and storing it in a database.

[0878] The "means for analyzing stored data" refers to a mechanism that includes algorithms for calculating sneaker rarity and price trends based on collected market data.

[0879] The "means for analyzing user emotion data" is a mechanism including an emotion engine for estimating an emotional state using a user's behavior log and input data.

[0880] The "means for generating investment advice based on the analysis results and emotional data" is a mechanism for combining the analyzed market data with the user's emotional data to generate optimal investment advice.

[0881] The "means for delivering the generated investment advice to the user terminal" is a mechanism for sending the generated investment advice to the user's smartphone or computer via push notification or email.

[0882] The following describes an embodiment of the present invention. The system implements a series of functions including data collection, organization and storage, data analysis, sentiment analysis, investment advice generation, and distribution. This makes it possible to provide investment advice that takes into account the user's sentiment.

[0883] Data collection implementation

[0884] The server collects sneaker market data from online marketplaces, auction sites, and social media, sending HTTP requests to the URLs of each data source, retrieving HTML pages and parsing them to extract information such as sneaker model name, sale date, and sale price.

[0885] Data Storage Implementation

[0886] The collected data is organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price, allowing for efficient data storage and retrieval.

[0887] Data Analysis Embodiments

[0888] The server runs algorithms to analyze the stored market data. This analysis uses historical sales data to calculate sneaker rarity and price trends. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[0889] Embodiment of Emotion Engine

[0890] The server uses an emotion engine to recognize and analyze user emotion data. The emotion engine infers emotions based on user input data and behavioral logs (clicks, browsing time, purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, it infers that the user has a high level of interest and anticipation for that sneaker.

[0891] Investment Advice Generation Embodiments

[0892] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the sneaker market data analysis results. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, the server will provide low-risk investment advice, and if the user is in a positive emotional state, the server will provide risky but high-reward investment advice.

[0893] Implementation of the delivery of investment advice

[0894] The generated investment advice is delivered to the user's device via push notifications to their smartphone or email. Users can receive these notifications, check the content, and make appropriate investment decisions.

[0895] Specific examples

[0896] As an example, a server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database. The emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X." The server analyzes the market data for "Sneaker X" and the user's emotion data and determines that the value of these sneakers will increase in the future. The advice generated by the server, including the content that now is the time to buy "Sneaker X," is delivered to the user's device.

[0897] Prompt Sentence Examples

[0898] By inputting the following prompt sentences into the generative AI model, the information necessary to generate investment advice can be obtained.

[0899] "Please provide detailed steps to build an application that collects and analyzes sneaker market data from an online marketplace and combines it with user sentiment data to generate investment advice. Please include the following elements:

[0900] 1. Specific methods of data collection and storage

[0901] 2. How to analyze market data and user sentiment data

[0902] 3. Algorithm for generating investment advice

[0903] 4. How to deliver advice to user devices

[0904] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0905] Step 1:

[0906] The server collects sneaker market data from online marketplaces, auction sites, and social media. Specifically, it sends HTTP requests to the URLs of each data source and parses the resulting HTML pages. It extracts information such as the sneaker model name, release date, and sale price from the parsed results. The input is the data source URL, and the output is the parsed market data.

[0907] Step 2:

[0908] The server organizes the collected market data and stores it in a database. The data is divided into fields such as sneaker model name, release date, and sales price. The input is the organized market data, and the output is the data stored in the database. Specifically, the server inserts data into the database using SQL queries.

[0909] Step 3:

[0910] The server analyzes market data stored in a database. It runs an algorithm to calculate the rarity and price trends of sneakers based on past sales data. The input is the market data in the database, and the output is the analyzed price trends and rarity score. Specific operations include calculating the average price and tallying the number of sales.

[0911] Step 4:

[0912] The server analyzes the user's emotional data. The emotion engine uses the user's behavior log (clicks, browsing time, purchasing behavior) to estimate the emotional state. The input is the user's behavior data, and the output is an emotion score. Specifically, the emotion engine is used to analyze the user log and calculate the emotion score.

[0913] Step 5:

[0914] The server generates investment advice based on the analysis results and sentiment data. It combines the market data analysis results with sentiment scores to create optimal investment advice. The inputs are price trends, scarcity scores, and sentiment scores, and the output is investment advice. Specifically, it adjusts the content and wording of the advice to generate investment advice statements.

[0915] Step 6:

[0916] The server distributes the generated investment advice to the user's device. The distribution method is push notification or email. The input is the generated investment advice, and the output is a notification to the user's device. Specifically, the server uses a notification service to send the advice to the user's smartphone or computer.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] [Fourth embodiment]

[0921] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0922] 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.

[0923] 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).

[0924] 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.

[0925] 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.

[0926] 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).

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] 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."

[0934] To put this invention into practice, a system is constructed that collects and analyzes sneaker market data and provides investment advice based on that data. The specific configuration and operation of the system are described below.

[0935] Data collection implementation

[0936] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. This involves sending HTTP requests to each data source to retrieve HTML pages containing sales information. The HTML pages are then parsed to extract necessary data such as the sneaker model name, sale date, and sale price.

[0937] For example, if a server were to collect data from "Online Marketplace A," the following steps would be taken: The server would access the product listing page of "Online Marketplace A" and retrieve the HTML. Using an HTML parsing library, it would extract information such as the sneaker name, price, and sale date.

[0938] Data Storage Implementation

[0939] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[0940] For example, if the server collects data on "Sneaker B," it will be stored in a database table as follows:

[0941] Model Name: Sneakers B

[0942] Sale date: 2023-09-15

[0943] Sale price: 300

[0944] Data Analysis Embodiments

[0945] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price and number of sales. A rarity score is also calculated, which can be used to predict future value increases.

[0946] As a specific example, the server analyzes data for "Sneaker C" and calculates the average price based on the sales history for the past 12 months. Based on this information, it determines that the scarcity score is high because sales are declining but the price is rising.

[0947] Investment Advice Generation Embodiments

[0948] The server generates investment advice based on the analysis results. This advice is based on factors that predict the future value of a particular sneaker (for example, price appreciation rate or rarity score). The advice is provided to the user in an easy-to-understand format.

[0949] For example, if the average price of "Sneaker D" has increased by 20% over the past six months and the number of sales has decreased, the server will generate a recommendation that "Sneaker D" will become more valuable in the future.

[0950] Implementation of the delivery of investment advice

[0951] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[0952] For example, if a user receives an investment advice notification about "Sneaker E" on their smartphone, they can open the app to check the detailed information and make an investment based on that information.

[0953] In this way, the present invention provides a system that automatically processes everything from collecting sneaker market data to analyzing it, generating investment advice, and finally distributing it, allowing users to efficiently obtain accurate information and make optimal investment decisions.

[0954] The processing flow will be explained below.

[0955] Step 1:

[0956] The server accesses online marketplaces, auction sites, and social networking sites on the Internet to collect sneaker sales data. Specifically, it sends an HTTP request to the URL of each data source and retrieves the HTML page.

[0957] Step 2:

[0958] The server parses the HTML page and extracts information such as the sneaker model name, release date, and sale price. For example, an HTML parsing library is used to extract the necessary data from specific tags.

[0959] Step 3:

[0960] The server temporarily organizes the extracted data into a data structure such as a list or dictionary, then establishes a connection to the database and stores the data in the appropriate tables.

[0961] Step 4:

[0962] To analyze the stored data, the server queries the database to retrieve the necessary information, for example, sales data for a particular sneaker for the past year.

[0963] Step 5:

[0964] The server uses the acquired data to analyze sneaker rarity and price trends, calculating declines in sales and increases in price to calculate a rarity score.

[0965] Step 6:

[0966] The server generates investment advice based on the analysis results. For example, if it predicts that a particular pair of sneakers is likely to increase in value in the future, it generates a recommendation for that sneaker.

[0967] Step 7:

[0968] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[0969] Step 8:

[0970] Users receive investment advice delivered to their devices, then open an app or email to check detailed information, and use that information to make optimal investment decisions.

[0971] Example 1

[0972] 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."

[0973] In conventional market analysis systems, the collection, organization, and analysis of market data, as well as the generation and distribution of investment advice, were all carried out separately, resulting in complex processes and making it difficult to update data and make investment decisions in real time.In addition, the limited scope of data collection meant that data coverage and analytical accuracy were low.

[0974] 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.

[0975] In this invention, the server includes a means for collecting market data, a means for organizing and storing the collected market data, and a means for analyzing the stored market data. This automates the entire process of data collection, analysis, and investment advice generation and distribution in the sneaker market, enabling real-time data updates and efficient investment decisions.

[0976] "Market data" refers to data including sales information, price information, sales dates, number of transactions, etc., of products traded in the market.

[0977] "Online marketplace" refers to a platform for buying and selling goods over the Internet.

[0978] "Auction Site" means a website where bidding and auctioning of items takes place online.

[0979] "Social networking service" refers to a service on the Internet that enables users to share content and communicate with each other.

[0980] An "information terminal" is a device that a user uses to receive information, and includes a smartphone, a computer, etc.

[0981] "Database" refers to a management system for efficiently storing and retrieving data.

[0982] "Analysis" refers to the process of analyzing collected data to find specific patterns or trends.

[0983] "Investment advice" refers to information that recommends appropriate investment actions based on the results of data analysis.

[0984] This invention is a system that collects and analyzes sneaker market data and provides investment advice based on that data. This system automatically performs a series of processes: collecting necessary information from various data sources, analyzing the data, generating investment advice, and distributing it to users.

[0985] Data collection implementation

[0986] The server collects market data from online marketplaces, auction sites, and social networking services. Specifically, it sends HTTP requests and parses the HTML pages it retrieves to extract information such as sneaker model name, release date, and sale price. It uses an HTML parsing library such as Beautiful Soup to parse the HTML.

[0987] Examples:

[0988] The server periodically accesses "Online Market A" and retrieves the HTML of the product list page.

[0989] The server uses Beautiful Soup to parse the HTML and extract data such as the name of the sneaker "Model X," the release date "2023-09-15," and the sale price "$300."

[0990] Data Storage Implementation

[0991] The extracted market data is organized and stored in a database on the server, which includes fields such as sneaker model name, release date, and sales price.

[0992] Examples:

[0993] The server connects to the database and inserts the newly extracted "Model X" data into the sneaker information table.

[0994] The database stores the following information: model name "Model X," sales date "2023-09-15," and sales price "$300."

[0995] Data Analysis Embodiments

[0996] The server runs an algorithm that analyzes the stored data. This involves calculating sneaker rarity and price trends based on past sales data. The data is analyzed using Python's Scikit-learn and Pandas libraries to calculate average prices, sales numbers, and rarity scores.

[0997] Examples:

[0998] The server calculates price trends using Model Y sales data from the past 12 months.

[0999] The server calculates the average price and number of sales, and if it sees that the number of sales is decreasing and the price is increasing, it gives a high scarcity score.

[1000] Investment Advice Generation Embodiments

[1001] The server generates investment advice based on the data analysis results. Using a generative AI model, the server inputs the analysis results as prompt sentences to generate investment advice that is easy for users to understand.

[1002] Examples:

[1003] The server analyzes that the average price of the Model Y has increased by 20% over the past six months, while sales have declined.

[1004] The server uses the generative AI model to generate investment advice such as "Model Y will become more valuable in the future."

[1005] Implementation of the delivery of investment advice

[1006] The generated investment advice is delivered to the user's device via push notification, email, etc. The user can check the delivered notification and obtain detailed investment advice.

[1007] Examples:

[1008] The server sends push notifications using a notification service such as Firebase.

[1009] The device receives a notification, and the user taps on it to open the application, which displays detailed information about the investment advice.

[1010] Users receive investment advice notifications about the Model Z, open the app to review the information, and make an investment decision.

[1011] Example prompt sentence:

[1012] "Collect and analyze sneaker market data from online marketplace A, generate investment advice based on the results, and send it to the user's device via push notification."

[1013] The system automatically collects market data, analyzes the data, and generates and distributes investment advice, enabling users to obtain accurate information in real time and make optimal investment decisions.

[1014] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1015] System program processing flow

[1016] The program of this system is executed in the following processing steps.

[1017] Step 1: Data collection

[1018] A server collects sneaker market data from online marketplaces, auction sites, and social networking services.

[1019] Specific behavior:

[1020] Input: List of data source URLs

[1021] Processing: The server sends an HTTP request to each data source to retrieve an HTML page, which it then parses with an HTML parsing library such as Beautiful Soup.

[1022] Output: A list of sneaker models, release dates, and prices

[1023] Examples:

[1024] The server accesses "Online Marketplace A" and retrieves the HTML of the product list page (e.g., URL: https: / / example.com / products).

[1025] The server uses Beautiful Soup to parse the HTML and extract the following information: model "Model X", sale date "2023-09-15", and sale price "$300".

[1026] Step 2: Save data

[1027] The server organizes and stores the extracted market data in a database.

[1028] Specific behavior:

[1029] Input: Data extracted in step 1

[1030] Processing: The server connects to the database and inserts new data into the sneaker information table.

[1031] Output: Data stored in the database

[1032] Examples:

[1033] The server connects to the database and saves the data of model name "Model X", release date "2023-09-15", and sale price "$300" in the sneaker information table.

[1034] Step 3: Data analysis

[1035] The server runs algorithms that analyze the stored data.

[1036] Specific behavior:

[1037] Input: Sneaker market data stored in a database

[1038] Processing: The server uses Python's Scikit-learn and Pandas libraries to analyze historical sales data and calculate price trends, average prices, and scarcity scores.

[1039] Output: Analysis results (price trends, average price, scarcity score, etc.)

[1040] Examples:

[1041] The server retrieves sales data for the Model Y for the past 12 months from the database and calculates price trends.

[1042] The server assigns a high scarcity score based on the declining number of sales and rising prices.

[1043] Step 4: Investment advice generation

[1044] The server generates investment advice based on the analysis results.

[1045] Specific behavior:

[1046] Input: Analysis results (price trends, average price, scarcity score, etc.)

[1047] Processing: The server inputs the analysis results into the generative AI model as prompt sentences to generate investment advice that is easy for the user to understand.

[1048] Output: Generated investment advice

[1049] Examples:

[1050] The server generates investment advice based on the fact that the price of the Model Y has risen 20% over the past six months and sales have declined, stating that the Model Y will become more valuable in the future.

[1051] Step 5: Providing investment advice

[1052] The server distributes the generated investment advice to the information terminal.

[1053] Specific behavior:

[1054] Input: Generated investment advice

[1055] Processing: The server uses a notification service such as Firebase to deliver advice to the user's information device via push notification or email.

[1056] Output: Investment advice delivered to the user's information terminal

[1057] Examples:

[1058] The server generates investment advice on the Model Z and sends a push notification to the user's smartphone via Firebase.

[1059] The user receives a notification and opens the app to see more information.

[1060] Through this series of processing steps, users can obtain accurate investment information in real time, enabling them to make optimal investment decisions.

[1061] (Application example 1)

[1062] 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."

[1063] In today's sneaker market, where sneaker values ​​fluctuate rapidly, it is difficult for users to make appropriate investment decisions based on this information. Furthermore, if users do not have a way to directly purchase sneakers after receiving investment advice, they are unable to take prompt investment action. This can result in users missing out on advantageous investment opportunities.

[1064] 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.

[1065] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for delivering generated investment advice to a user terminal, and means for enabling the user to directly purchase the generated investment advice, thereby enabling the user to quickly receive reliable investment advice based on market data and immediately purchase sneakers.

[1066] "Data collection means" refers to the part that has the function of obtaining sneaker market data from online markets, auction sites, social networks, etc.

[1067] The "data organization means" is a part that organizes collected market data into a format suitable for analysis and stores it in a database or the like.

[1068] "Data storage means" refers to a database, storage system, or other part that stores organized market data efficiently and effectively.

[1069] The "data analysis means" refers to the part that uses algorithms and calculations to analyze sneaker rarity and price trends based on stored market data.

[1070] The "investment advice generation means" is a part that has the function of predicting future increases in the value of sneakers based on the analysis results and creating appropriate investment advice.

[1071] The "investment advice distribution means" is a part that includes a push notification system and an email system for notifying the user's terminal of the generated investment advice.

[1072] The "purchase means" is a function that allows the user to directly purchase sneakers based on the investment advice received.

[1073] This invention is a system that collects and analyzes sneaker market data, generates and distributes investment advice, and allows users to directly purchase sneakers based on that advice. The system consists of the following main components:

[1074] First, the server collects sneaker market data from multiple data sources, including online marketplaces, auction sites, and social networks. This involves sending an HTTP request to retrieve an HTML page containing sales information, parsing the HTML page to extract the required data, and then the server organizes this collected data and stores it in a database.

[1075] The server then analyzes the stored data. This data analysis uses algorithms to calculate the rarity and price trends of sneakers. For example, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. It also calculates a rarity score, which can be used to predict future value increases.

[1076] Based on the analysis results, the server generates investment advice based on factors that predict the future value of a particular sneaker (e.g., price appreciation rate and rarity score), and provides the advice in a format that is easy for users to understand.

[1077] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[1078] Furthermore, users can directly purchase sneakers based on the advice. The server not only provides users with investment advice but also provides an interface for them to actually purchase the sneakers. This allows users to make quick investment decisions and execute them.

[1079] For example, if one day "Sneaker X" becomes particularly rare and its price rises, the user will be notified with the following advice:

[1080] "Sneaker X has increased in price by 25% over the past six months, and sales are declining. Consider investing in this sneaker as it is likely to continue to increase in value."

[1081] Examples of prompts for generative AI models include:

[1082] "Analyze the future value increase potential of Sneaker X based on the price fluctuation and sales data of the past six months. If the price increase rate is high, generate a message recommending investment to the user."

[1083] The above system can be a powerful tool for users to make efficient and accurate investment decisions in the sneaker market.

[1084] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1085] Step 1:

[1086] The server collects sneaker market data from online marketplaces, auction sites, and social networks using HTTP requests. The server retrieves HTML pages from each data source and parses them to extract data such as sneaker model name, sale date, and sale price. The input is the retrieved HTML data, and the output is the parsed sneaker market data.

[1087] Step 2:

[1088] The server then organizes the parsed sneaker market data appropriately and stores it in a database. The input is the parsed market data, and the output is the data stored in an organized format in the database. For example, information such as the model name "Sneaker A," the release date "2023-10-01," and the sale price "$120" is stored in the database.

[1089] Step 3:

[1090] The server runs an algorithm to analyze the stored data. Specifically, it analyzes the price trends of a particular sneaker over the past year and calculates the average price and number of sales. The input is market data stored in the database, and the output is the analysis results (e.g., average price, number of sales, rarity score).

[1091] Step 4:

[1092] The server generates investment advice based on the analysis results. This advice is based on factors such as price growth rate and scarcity score. The input is the analysis results, and the output is investment advice to be provided to the user. For example: "Sneaker B has increased in average price by 20% over the past six months and sales have decreased, so it is predicted to increase in value in the future."

[1093] Step 5:

[1094] The server delivers the generated investment advice to the user's device. Push notifications and emails are used as delivery methods. The input is the generated investment advice text, and the output is the notification sent to the user's device. Example: "Investment advice on sneaker C has been sent."

[1095] Step 6:

[1096] The user can confirm the investment advice and purchase the sneakers directly through the application. When the user presses the purchase button based on the advice received on the user's device, the server processes the purchase request and completes the transaction. The input is the user's purchase request, and the output is a purchase completion notification or a purchase rejection notification.

[1097] Through these steps, the system can efficiently collect and analyze sneaker market data, provide useful investment advice to users, and support quick purchases.

[1098] 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.

[1099] To put this invention into practice, a system is required that collects and analyzes sneaker market data and provides investment advice based on that data, and an emotion engine is also required that recognizes and analyzes user emotions. The specific configuration and operation of the system are described below.

[1100] Data collection implementation

[1101] The server first collects sneaker market data from data sources such as online marketplaces, auction sites, and social media. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[1102] Data Storage Implementation

[1103] The extracted data is then organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price. This structure allows the server to store the data efficiently and make it easy to search later.

[1104] Data Analysis Embodiments

[1105] The server runs algorithms to analyze the stored data. This analysis uses historical sales data to calculate a sneaker's rarity and price trend. For example, it analyzes the price history of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[1106] Embodiment of Emotion Engine

[1107] Next, the server uses an emotion engine to recognize and analyze the user's emotion data. This emotion engine infers emotions based on the user's input data and behavioral logs (e.g., clicks, browsing time, and purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[1108] Investment Advice Generation Embodiments

[1109] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the results of sneaker market data analysis. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice will be provided.

[1110] Implementation of the delivery of investment advice

[1111] The generated investment advice is delivered to the user's device via push notification, email, or other means. The user receives the notification, checks the content, and makes an investment decision.

[1112] As a concrete example, consider the following scenario:

[1113] The server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database.

[1114] At the same time, the emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X."

[1115] The server analyzes market data and user sentiment data for "Sneaker X" and determines that the value of the sneakers will increase in the future.

[1116] The advice generated by the server includes the content that now is the time to buy "Sneaker X" and is delivered to the user's device.

[1117] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[1118] The processing flow will be explained below.

[1119] Step 1:

[1120] The server collects sneaker market data from online marketplaces, auction sites, and social media sites. Specifically, it sends an HTTP request to the URL of each data source to retrieve an HTML page. It then parses this HTML page to extract information such as the sneaker model name, release date, and sale price.

[1121] Step 2:

[1122] The server organizes the extracted data and stores it in a database, specifically in a table with fields such as sneaker model name, release date, and sales price.

[1123] Step 3:

[1124] The server queries the database to retrieve the necessary information, such as sales data for a particular sneaker over the past year, and analyzes the sneaker's rarity and price trends based on this data.

[1125] Step 4:

[1126] The server runs algorithms to analyze the stored data, calculating declines in sales and price increases, and deriving a scarcity score. For example, it calculates the average price and number of sneakers sold and compares it with historical data.

[1127] Step 5:

[1128] The server launches an emotion engine to obtain user emotion data. The emotion engine estimates emotions based on the user's behavior log (e.g., clicks, browsing time, purchasing behavior) and input data. For example, if a user frequently views a particular sneaker model, it evaluates the user as having a high interest in that sneaker.

[1129] Step 6:

[1130] The server generates investment advice by combining the emotional data obtained by the emotion engine with the results of market data analysis. Specifically, the content of the investment advice is adjusted according to the user's emotional state. For example, if the user is feeling stressed, low-risk investment advice is provided.

[1131] Step 7:

[1132] The server generates investment advice and delivers it to the user's device via push notifications, email, or a dedicated app.

[1133] Step 8:

[1134] Users receive investment advice delivered to their devices, open an app or email to view detailed information, and make optimal investment decisions based on that information. For example, they tap on an app notification to view detailed information about recommended sneakers and make a purchase decision based on that information.

[1135] The system allows users to receive accurate and personalized investment advice based on their emotional state and market data.

[1136] Example 2

[1137] 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."

[1138] In a system that collects and analyzes sneaker market data and provides investment advice based on that data, there is a challenge in generating and providing more appropriate and personalized advice by recognizing and analyzing user emotions. To solve this problem, it is necessary to accurately capture the user's emotional state and dynamically adjust investment advice based on that.

[1139] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1140] In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for recognizing and analyzing user emotion data, means for generating investment advice based on the analysis results, and means for delivering the generated investment advice to the user terminal, thereby making it possible to provide personalized investment advice that takes into account the user's emotional state.

[1141] "Data" refers to information or figures collected from sources and used for analysis.

[1142] "Means of collection" refers to the methods and tools used to obtain data from online marketplaces, auction sites, social networking services, etc.

[1143] "Means of organizing and storing" refers to methods and tools for formatting collected data into a certain format and storing it safely and efficiently in storage such as a database.

[1144] "Means of analysis" refers to algorithms and tools that use stored data to analyze market trends and user behavior patterns.

[1145] "User emotional data" refers to information about the emotional state estimated based on the user's input data and behavioral log.

[1146] "Means of recognition and analysis" refers to the algorithms and tools used to collect and analyze user emotional data.

[1147] "Means for generating investment advice" refers to methods and tools for creating optimal investment advice based on data analysis results and user sentiment data.

[1148] "Means of delivery" refers to the methods and tools used to deliver the generated investment advice to the user's terminal.

[1149] "User terminal" refers to a device such as a smartphone or computer that a user uses to receive information or perform operations.

[1150] "Server" refers to a computer system for executing a series of processes such as data collection, analysis, storage, advice generation and distribution.

[1151] This invention is a system that collects and analyzes sneaker market data and user sentiment data, and provides investment advice. This system operates with the following configuration.

[1152] First, the server collects data. The server gathers sneaker data from multiple sources, including online marketplaces, auction sites, and social networking services. This data collection is done using HTTP requests and web scraping libraries such as BeautifulSoup and Scrapy. For example, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the Nike Air Max.

[1153] Next, the server organizes the collected data and stores it in a database. For this, it uses a relational database such as "PostgreSQL" or "MySQL." The server formats the collected data appropriately and inserts it into the database. Specifically, the server stores the Nike Air Max data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[1154] The server then performs analysis based on the stored data. This analysis uses machine learning libraries such as "pandas" and "scikit-learn" to calculate the price history and sales volume of a specific sneaker and calculate a rarity score. For example, based on the price of Nike Air Max over the past year, the server determines that the average price is $220 and the rarity score is 85.

[1155] Furthermore, the server uses an emotion engine to recognize and analyze user emotion data. When a user browses a page, their behavioral logs (clicks, browsing time, purchasing behavior) are collected and their emotions are estimated using natural language processing engines such as TensorFlow and IBM Watson. For example, if a user frequently browses a particular sneaker model and stays on the page for a long time, the emotion engine will assess that the user has a high level of interest and anticipation for that sneaker.

[1156] The server then combines the sentiment data and market data to generate investment advice. The server integrates the analysis results with the sentiment data and inputs a prompt statement into the generative AI model. For example, the server might input "If the user is highly interested in Nike Air Max, please generate investment advice," and the model would generate the advice "Now is the time to buy Nike Air Max."

[1157] Finally, the server delivers the generated investment advice to the user's device. This delivery can be done using methods such as push notification or email. The user receives the notification or email, checks the content, and then makes an investment decision. For example, the user's device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[1158] This system allows users to efficiently receive optimal investment advice based on their emotional state and market data, enabling them to make investment decisions based on accurate and objective information, reducing investment risks and maximizing profits.

[1159] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1160] Step 1:

[1161] The server collects sneaker market data from online marketplaces, auction sites, and social networking services. It lists the URLs of each data source as input and sends HTTP requests based on them. It obtains an HTML page as output, parses the page using the "BeautifulSoup" library, and extracts information such as the sneaker model name, release date, and sale price. Specifically, the server retrieves the "https: / / example.com / sneakers" page and extracts the price and release date of the "Nike Air Max" on that page.

[1162] Step 2:

[1163] The server organizes the acquired data and saves it in a database. It formats the information extracted as input, such as the sneaker model name, release date, and sales price, connects to the "PostgreSQL" database, and inserts it into the database. The organized data is saved in the database as output. Specifically, the server saves the "Nike Air Max" data in the "sneakers_pricing" table as "2023-10-01, Nike Air Max, $200."

[1164] Step 3:

[1165] The server performs analysis based on the stored data. It retrieves past sales data from the database as input using a query and processes the data using the "pandas" library. It then runs an algorithm to calculate the rarity score using "scikit-learn." The output is the price history of the sneakers, the average price, the number of sales, and the rarity score. Specifically, the server calculates that the average price is $220 and the rarity score is 85 based on the prices of "Nike Air Max" over the past year.

[1166] Step 4:

[1167] The server uses an emotion engine to recognize and analyze user emotion data. As input, it collects behavioral logs such as user clicks, browsing time, and purchasing behavior. It then uses TensorFlow and IBM Watson to run the emotion engine and estimate the user's emotions. The output is an evaluation of the user's emotional state. Specifically, the server assesses that the user has a high level of interest and anticipation based on the long time they spent browsing the Nike Air Max page.

[1168] Step 5:

[1169] The server combines the sentiment data and market data to generate investment advice. As input, it integrates the analyzed market data and sentiment data and inputs a prompt statement into the generative AI model. As output, the investment advice obtained from the generative AI model is generated. Specifically, the prompt statement is input as "If the user shows a high interest in Nike Air Max, please generate investment advice," and the model generates the advice "Now is the time to buy Nike Air Max."

[1170] Step 6:

[1171] The server delivers the generated investment advice to the user's device. Using the generated investment advice as input, it delivers it to the user's device via push notification or email. The investment advice is sent to the user's device as output, and the user confirms it. Specifically, the device receives a notification saying, "The price of Nike Air Max is currently rising. Now is the time to buy!" and the user confirms it.

[1172] (Application example 2)

[1173] 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."

[1174] Conventional investment advice systems only analyze market data for investment targets, making it impossible to provide appropriate advice that takes into account the user's emotional state. It is also difficult to generate personalized advice based on the user's behavior and emotions. As a result, the advice users receive is general and does not fully address their individual needs and emotions.

[1175] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for organizing and storing the collected data, means for analyzing the stored data, means for analyzing user emotion data, means for generating investment advice based on the analysis results and the emotion data, and means for delivering the generated investment advice to the user terminal. This makes it possible to provide specific and personalized investment advice based on the user's individual emotional state and market data.

[1176] "Data collection means" refers to mechanisms for obtaining sneaker market data from online marketplaces, auction sites, and social media.

[1177] "Means for organizing and storing collected data" refers to a mechanism for structuring acquired data and storing it in a database.

[1178] The "means for analyzing stored data" refers to a mechanism that includes algorithms for calculating sneaker rarity and price trends based on collected market data.

[1179] The "means for analyzing user emotion data" is a mechanism including an emotion engine for estimating an emotional state using a user's behavior log and input data.

[1180] The "means for generating investment advice based on the analysis results and emotional data" is a mechanism for combining the analyzed market data with the user's emotional data to generate optimal investment advice.

[1181] The "means for delivering the generated investment advice to the user terminal" is a mechanism for sending the generated investment advice to the user's smartphone or computer via push notification or email.

[1182] The following describes an embodiment of the present invention. The system implements a series of functions including data collection, organization and storage, data analysis, sentiment analysis, investment advice generation, and distribution. This makes it possible to provide investment advice that takes into account the user's sentiment.

[1183] Data collection implementation

[1184] The server collects sneaker market data from online marketplaces, auction sites, and social media, sending HTTP requests to the URLs of each data source, retrieving HTML pages and parsing them to extract information such as sneaker model name, sale date, and sale price.

[1185] Data Storage Implementation

[1186] The collected data is organized and stored in a database on the server. The database consists of tables with fields such as sneaker model name, release date, and sale price, allowing for efficient data storage and retrieval.

[1187] Data Analysis Embodiments

[1188] The server runs algorithms to analyze the stored market data. This analysis uses historical sales data to calculate sneaker rarity and price trends. For example, it analyzes the price trends of a particular sneaker over the past year to calculate the average price, number of sales, and rarity score.

[1189] Embodiment of Emotion Engine

[1190] The server uses an emotion engine to recognize and analyze user emotion data. The emotion engine infers emotions based on user input data and behavioral logs (clicks, browsing time, purchasing behavior). For example, if a user frequently views a particular sneaker model and stays on the page for a long time, it infers that the user has a high level of interest and anticipation for that sneaker.

[1191] Investment Advice Generation Embodiments

[1192] The server generates investment advice by combining the emotional data analyzed by the emotion engine with the sneaker market data analysis results. Specifically, the content and presentation of the advice are adjusted according to the user's emotional state. For example, if the user is feeling stressed, the server will provide low-risk investment advice, and if the user is in a positive emotional state, the server will provide risky but high-reward investment advice.

[1193] Implementation of the delivery of investment advice

[1194] The generated investment advice is delivered to the user's device via push notifications to their smartphone or email. Users can receive these notifications, check the content, and make appropriate investment decisions.

[1195] Specific examples

[1196] As an example, a server collects data on "Sneaker X" from "Online Marketplace A" and stores it in a database. The emotion engine analyzes the user's behavioral log and recognizes that the user is highly interested in "Sneaker X." The server analyzes the market data for "Sneaker X" and the user's emotion data and determines that the value of these sneakers will increase in the future. The advice generated by the server, including the content that now is the time to buy "Sneaker X," is delivered to the user's device.

[1197] Prompt Sentence Examples

[1198] By inputting the following prompt sentences into the generative AI model, the information necessary to generate investment advice can be obtained.

[1199] "Please provide detailed steps to build an application that collects and analyzes sneaker market data from an online marketplace and combines it with user sentiment data to generate investment advice. Please include the following elements:

[1200] 1. Specific methods of data collection and storage

[1201] 2. How to analyze market data and user sentiment data

[1202] 3. Algorithm for generating investment advice

[1203] 4. How to deliver advice to user devices

[1204] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1205] Step 1:

[1206] The server collects sneaker market data from online marketplaces, auction sites, and social media. Specifically, it sends HTTP requests to the URLs of each data source and parses the resulting HTML pages. It extracts information such as the sneaker model name, release date, and sale price from the parsed results. The input is the data source URL, and the output is the parsed market data.

[1207] Step 2:

[1208] The server organizes the collected market data and stores it in a database. The data is divided into fields such as sneaker model name, release date, and sales price. The input is the organized market data, and the output is the data stored in the database. Specifically, the server inserts data into the database using SQL queries.

[1209] Step 3:

[1210] The server analyzes market data stored in a database. It runs an algorithm to calculate the rarity and price trends of sneakers based on past sales data. The input is the market data in the database, and the output is the analyzed price trends and rarity score. Specific operations include calculating the average price and tallying the number of sales.

[1211] Step 4:

[1212] The server analyzes the user's emotional data. The emotion engine uses the user's behavior log (clicks, browsing time, purchasing behavior) to estimate the emotional state. The input is the user's behavior data, and the output is an emotion score. Specifically, the emotion engine is used to analyze the user log and calculate the emotion score.

[1213] Step 5:

[1214] The server generates investment advice based on the analysis results and sentiment data. It combines the market data analysis results with sentiment scores to create optimal investment advice. The inputs are price trends, scarcity scores, and sentiment scores, and the output is investment advice. Specifically, it adjusts the content and wording of the advice to generate investment advice statements.

[1215] Step 6:

[1216] The server distributes the generated investment advice to the user's device. The distribution method is push notification or email. The input is the generated investment advice, and the output is a notification to the user's device. Specifically, the server uses a notification service to send the advice to the user's smartphone or computer.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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).

[1224] 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.

[1225] 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."

[1226] 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.

[1227] 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).

[1228] 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.

[1229] 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.

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] 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.

[1238] The following is further disclosed regarding the above embodiment.

[1239] (Claim 1)

[1240] a means of collecting data;

[1241] A means of organizing and storing the collected data;

[1242] means for analyzing the stored data;

[1243] means for generating investment advice based on the analysis results;

[1244] The system includes means for delivering the generated investment advice to a user terminal.

[1245] (Claim 2)

[1246] 10. The system of claim 1, wherein the system collects data from online marketplaces, auction sites, and social media.

[1247] (Claim 3)

[1248] The system of claim 1, wherein the collected data is stored in a database.

[1249] "Example 1"

[1250] (Claim 1)

[1251] a means of collecting market data;

[1252] A means of organizing and storing the collected market data;

[1253] means for analyzing the stored market data;

[1254] means for generating investment advice based on the analysis results;

[1255] The system includes a means for distributing the generated investment advice to an information terminal.

[1256] (Claim 2)

[1257] 10. The system of claim 1, wherein the system collects market data from online marketplaces, auction sites, and social networking services.

[1258] (Claim 3)

[1259] 10. The system of claim 1, wherein the database stores the market data.

[1260] "Application Example 1"

[1261] (Claim 1)

[1262] a means of collecting data;

[1263] A means of organizing and storing the collected data;

[1264] means for analyzing the stored data;

[1265] means for generating investment advice based on the analysis results;

[1266] means for delivering the generated investment advice to a user terminal;

[1267] The system includes a means for enabling a user to directly purchase the generated investment advice.

[1268] (Claim 2)

[1269] 10. The system of claim 1, wherein the system collects data from online marketplaces, auction sites, and social networks.

[1270] (Claim 3)

[1271] The system of claim 1, wherein the collected data is stored in a database.

[1272] "Example 2: Combining Emotion Engines"

[1273] (Claim 1)

[1274] a means of collecting data;

[1275] A means of organizing and storing the collected data;

[1276] means for analyzing the stored data;

[1277] A means for recognizing and analyzing user emotion data;

[1278] means for generating investment advice based on the analysis results;

[1279] The system includes means for delivering the generated investment advice to a user terminal.

[1280] (Claim 2)

[1281] 10. The system of claim 1, wherein the system collects data from online marketplaces, auction sites, and social networking services.

[1282] (Claim 3)

[1283] The system of claim 1, wherein the collected data is stored in a database.

[1284] "Application example 2 when combining emotion engines"

[1285] (Claim 1)

[1286] a means of collecting data;

[1287] A means of organizing and storing the collected data;

[1288] means for analyzing the stored data;

[1289] means for analyzing user emotion data;

[1290] means for generating investment advice based on the analytical results and sentiment data;

[1291] The system includes means for delivering the generated investment advice to a user terminal.

[1292] (Claim 2)

[1293] 10. The system of claim 1, wherein the system collects data from online marketplaces, auction sites, and social media.

[1294] (Claim 3)

[1295] The system of claim 1, wherein the collected data and emotion data are stored in a database. [Explanation of symbols]

[1296] 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 data; A means of organizing and storing the collected data; means for analyzing the stored data; means for generating investment advice based on the analysis results; The system includes means for delivering the generated investment advice to a user terminal.

2. The system of claim 1 , wherein the system collects data from online marketplaces, auction sites, and social media.

3. The system of claim 1, wherein the collected data is stored in a database.

Images