System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring sales data of real stores; means for acquiring online sales performance data; means for converting the sales data of the real stores and the online sales performance data into a common data format; means for detecting and correcting duplicate data and missing data; means for storing the converted data in a database; means for acquiring price information of the real stores and the online stores from the database; and means for displaying the acquired price information on 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] Conventional sales data management systems made it difficult to manage sales data from both physical and online stores in an integrated manner, making it impossible to set appropriate prices and manage inventory while maintaining consistency between the various data. Furthermore, they did not provide a way for consumers to easily compare price differences between physical and online stores. Furthermore, they lacked tools for businesses to estimate optimal sales prices and inventory levels, making them prone to problems such as stockouts and excess inventory. [Means for solving the problem]

[0005] The present invention provides a system that efficiently acquires sales data from brick-and-mortar stores and online sales performance data and stores them in an integrated database. It also provides a means for users to compare price information from brick-and-mortar stores and online stores when searching for a product. It also provides a system that includes a function for businesses to input sales history, inventory status, market trend data, etc. into an AI model, calculate appropriate sales prices and inventory quantities, and display them on a dashboard, thereby optimizing sales prices and properly managing inventory.

[0006] "Real store sales data" refers to sales information and related sales history data for products that occurred in actual physical stores.

[0007] "Online sales performance data" refers to sales information and related sales history data relating to product sales conducted over the Internet.

[0008] "Means for converting into a common data format" refers to a means for executing a process to convert sales data from physical stores and online sales performance data into a specific format in order to unify different data formats.

[0009] "Means for detecting and correcting duplicate and missing data" means means for identifying redundant or missing data within a dataset and implementing a process to remove, complete or correct it.

[0010] A "user terminal" refers to a device through which a user accesses and operates the system, and is typically an information processing device such as a computer, smartphone, or tablet.

[0011] "Means of input to AI models" refers to the means of carrying out a process to provide statistical data, historical data, etc. to artificial intelligence algorithms.

[0012] "Means for calculating the appropriate selling price and appropriate inventory quantity" refers to means for executing a process that uses an AI model to calculate the optimal price and effective inventory quantity for a product.

[0013] The "business dashboard" is a user interface that allows businesses to visually check sales data, inventory information, calculation results of AI models, and more.

[0014] "Scheduling means" refers to a time management mechanism for periodically acquiring and processing data, and is a means having the function of automatically starting a task at a specified time. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. This system includes a product price comparison service for users and a service that provides fair sales prices and inventory levels for businesses. Specific implementation methods for the system are described below.

[0037] 1. Data Acquisition

[0038] server:

[0039] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[0040] 2. Data formatting and cleansing

[0041] server:

[0042] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[0043] 3. Data Storage

[0044] server:

[0045] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0046] 4. Price comparison service for users

[0047] User device:

[0048] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0049] Specific examples

[0050] The user enters "laptop computer" in the product search box and presses the search button.

[0051] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[0052] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[0053] 5. Sales price and inventory information service for businesses

[0054] server:

[0055] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[0056] Operator terminal:

[0057] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[0058] Specific examples

[0059] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[0060] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[0061] The server displays the results on the operator's dashboard, where the operator can confirm them.

[0062] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, providing useful information to both users and businesses. This system brings great value to marketing strategies and sales management.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[0066] Step 2:

[0067] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[0068] Step 3:

[0069] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[0070] Step 4:

[0071] The server receives the response data from the online sales platform and stores it in a buffer as well.

[0072] Step 5:

[0073] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[0074] Step 6:

[0075] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[0076] Step 7:

[0077] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[0078] Step 8:

[0079] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[0080] Step 9:

[0081] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[0082] Step 10:

[0083] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[0084] Step 11:

[0085] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[0086] Step 12:

[0087] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[0088] Step 13:

[0089] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[0090] Step 14:

[0091] The server uses a scheduling means to set the task to start automatically in order to periodically execute the data acquisition and analysis processes.

[0092] Through the above steps, a system is built that integrates and manages sales data from physical and online stores and provides useful information to users and businesses.

[0093] Example 1

[0094] 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."

[0095] In today's retail industry, there is a need to integrate and efficiently manage sales data from both brick-and-mortar and online stores. However, building an integrated database is difficult because each sales channel uses a different data format, which can easily result in data duplication or omissions. There is also a lack of systems that allow users to easily compare product information, or tools that allow businesses to determine optimal sales prices and inventory levels. To solve this problem, a system that efficiently acquires and accurately integrates sales data is needed.

[0096] 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.

[0097] In this invention, the server includes means for acquiring sales data from real stores, means for acquiring online sales performance data, means for converting the sales data from real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate and missing data, means for storing the converted data in a database, means for a user to search for a product and acquire price information from real stores and online stores from the database, means for displaying the acquired price information on a user terminal, means for inputting sales history, inventory status, and market trend data into an AI model, means for calculating an appropriate sales price and an appropriate inventory quantity using the AI ​​model, means for displaying the calculation results on a dashboard for business operators, means for scheduling the periodic acquisition of sales data from real stores and online sales performance data, means for inputting prompt statements into the AI ​​model, and means for correcting and supplementing the acquired data. This makes it possible to efficiently integrate and manage sales data from real stores and online stores and provide useful information to users and business operators.

[0098] "Brick and mortar sales data" refers to data related to the sale of products in physical stores, including information such as transaction date and time, product name, price, and quantity.

[0099] "Online sales performance data" refers to data related to the sale of products via the Internet, including transaction dates and times, product names, prices, quantities, and delivery information.

[0100] A "common data format" refers to a standardized data representation that transforms data collected from different sources into a consistent format, facilitating uniform management of the data.

[0101] "Duplicate data" refers to the existence of two copies of the same data. Duplicate data can take up space in a database and can compromise data consistency.

[0102] "Missing data" refers to the absence of necessary information in a dataset, which can reduce the accuracy of data analysis and statistical models.

[0103] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data. There are various types, such as SQL and NoSQL.

[0104] "User terminal" refers to an electronic device used by a user to access the system, including a personal computer, smartphone, tablet, etc.

[0105] An "AI model" refers to an algorithm that uses artificial intelligence technology to extract meaningful information from data and make predictions or classifications for specific purposes.

[0106] A "prompt" is an input given to an AI model or natural language processing system, which controls the system's response and behavior.

[0107] "Scheduling means" refers to a mechanism that automatically executes specific processes or tasks at regular intervals, enabling regular data acquisition and updating.

[0108] The "business dashboard" refers to an interface that allows businesses to view and manage management data and analysis results in real time. This dashboard displays information such as sales analysis, inventory status, and optimal price proposals.

[0109] "Sales History" refers to a record of all past transactions, including details such as purchase date, product, quantity, and price.

[0110] "Inventory status" refers to information about the quantity and type of products currently in stock, which allows for effective inventory management.

[0111] "Market trend data" refers to information on consumer purchasing trends in the market, the actions of competitors, etc. This data plays an important role in sales strategies and pricing.

[0112] The system of the present invention efficiently integrates sales data from brick-and-mortar stores with online sales performance data, and provides useful information to users and businesses based on the integration. A specific implementation method of this system will now be described.

[0113] Data Acquisition

[0114] server

[0115] The server periodically sends an HTTP request to the POS system to retrieve sales data from the physical store. This request includes authentication information, and the POS system returns sales data in JSON format. Similarly, the server sends an HTTP request to the API of the online sales platform to retrieve online sales performance data. All retrieved data is stored in memory on the server.

[0116] Data transformation and cleansing

[0117] server

[0118] The acquired data is converted into a common data format. Specifically, different data formats (for example, JSON key names and value formats) are unified. Data cleansing is then performed to remove duplicate data and fill in missing data.

[0119] Data storage

[0120] server

[0121] After cleansing and unifying the data, it is stored in a database using a database connection library such as SQLAlchemy. This database manages data from both physical stores and online sales in an integrated manner.

[0122] Price comparison service for users

[0123] User terminal

[0124] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0125] Specific examples

[0126] The user enters "laptop" in the product search box and presses the search button. The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this on the user's screen.

[0127] Sales price and inventory information service for businesses

[0128] server

[0129] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity.

[0130] Operator terminal

[0131] When a business accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[0132] Specific examples

[0133] The server inputs the sales history of "notebook_pc" for the past six months, the current inventory, and market trends into the AI ​​model. The AI ​​model calculates an optimal selling price of 90,000 yen and an inventory of 20 units. The server displays the results on the business's dashboard, where the business can confirm them.

[0134] The implementation of this system will enable integrated management of sales data from brick-and-mortar and online stores, providing useful information for users and businesses. In addition, the use of generative AI models will enable highly accurate predictions and analysis using prompt sentences.

[0135] Examples of prompt statements

[0136] "Please tell me the best selling price and stock quantity for laptops."

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1:

[0139] Acquiring sales data from real stores

[0140] The server periodically sends an HTTP request to the POS system. This request includes authentication information such as an API key. The POS system responds with sales data in JSON format. The response data is stored in memory.

[0141] Input: HTTP request sent by the server to the POS system

[0142] Output: Sales data returned from the POS system (JSON format)

[0143] Specific operation: The server retrieves the data using requests.get('https: / / api.pos-system.com / data', headers={'Authorization': 'Bearer YOUR_API_KEY'}).

[0144] Step 2:

[0145] Acquisition of online sales performance data

[0146] The server sends an HTTP request to the API of the online sales platform. This request includes authentication information, and the sales platform responds with sales performance data in JSON format. The response data is stored in memory.

[0147] Input: HTTP request sent by the server to the online sales platform

[0148] Output: Sales performance data (JSON format) returned from the online sales platform

[0149] Specific behavior: The server retrieves the data using requests.get('https: / / api.ecommerce-platform.com / sales-data', headers={'Authorization': 'Bearer YOUR_API_KEY'}) .

[0150] Step 3:

[0151] Standardized data format

[0152] The server uses the Python pandas library to convert the retrieved data into a common data format, unifying different data formats (for example, JSON key names and value formats).

[0153] Input: Data obtained from POS systems and online sales platforms (JSON format)

[0154] Output: Data converted into a common data format

[0155] Specific behavior: The server converts the data as follows: data = pd.DataFrame(json_data).rename(columns={'shop_id': 'store_id', 'item_price': 'price'}) .

[0156] Step 4:

[0157] Data Cleansing

[0158] The server performs data cleansing, removing duplicate data and filling in missing data. Missing data is filled in based on historical data, average values, etc.

[0159] Input: Data converted into a common data format

[0160] Output: Cleansed data

[0161] Specific behavior: The server performs data cleansing as in data.drop_duplicates(inplace=True) or data.fillna(method='ffill', inplace=True).

[0162] Step 5:

[0163] Storing data in a database

[0164] The cleansed and unified formatted data is stored in a database using a database connection library such as SQLAlchemy.

[0165] Input: Cleansed data

[0166] Output: Data stored in a database

[0167] Specific operation: The server stores data in the database using engine = create_engine('mysql+pymysql: / / user:password@host / dbname') or data.to_sql('sales_data', con=engine, if_exists='replace', index=False).

[0168] Step 6:

[0169] Price comparison service processing for users

[0170] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen.

[0171] Input: User search query

[0172] Output: Price information returned by the server (JSON format)

[0173] What happens: When a user searches for laptop, the query is sent as ' / search?query=laptop'. The server retrieves the data as result = pd.read_sql('SELECT FROM sales_data WHERE product_name="laptop"', con=engine).

[0174] Step 7:

[0175] Sales price and inventory quantity provision service processing for businesses

[0176] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. When a business owner accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[0177] Input: Sales history, inventory status, and market trend data

[0178] Output: Optimal selling price and inventory quantity calculated by the AI ​​model

[0179] Specific operation: The server prepares the data as follows: model_input = create_model_input(sales_history, inventory_data) , and calculates the optimal selling price as follows: predictions = ai_model.predict(model_input) .

[0180] This series of processes enables integrated management of sales data from brick-and-mortar stores and online stores. In addition, by using prompt statements, it becomes possible to efficiently input data into the AI ​​model and develop appropriate sales strategies.

[0181] (Application example 1)

[0182] 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."

[0183] With conventional systems, it was difficult to manage sales data from brick-and-mortar stores and online stores in an integrated manner, making it difficult for users to easily compare prices and for businesses to develop optimal sales strategies.In addition, the inability to compare prices or grasp inventory status in real time resulted in problems with the user's purchasing experience and the business's inventory management being inefficient.

[0184] 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.

[0185] In this invention, the server includes a means for acquiring sales data from brick-and-mortar stores, a means for acquiring online sales performance data, and a display device for acquiring product IDs by barcode scanning and displaying product prices and stock status corresponding to the product IDs. This allows users to compare prices and check stock status in real time, and enables businesses to calculate optimal sales prices and stock quantities, enabling efficient inventory management.

[0186] "Real store sales data" refers to data that includes sales information from physical stores.

[0187] "Online sales performance data" refers to data that includes sales information for products sold over the Internet.

[0188] A "common data format" is a data structure for converting multiple pieces of data in different formats into one unified format.

[0189] "Duplicate data" refers to data in which the same data exists multiple times.

[0190] "Missing data" refers to data that is missing data that should be present.

[0191] A "database" is a management system for systematically storing large amounts of data and using it efficiently.

[0192] "User terminal" is a general term for electronic devices that can be directly operated by a user.

[0193] "Price information" is data relating to the selling price of a particular product.

[0194] The "display device" is a device or software for visually displaying acquired data.

[0195] "Sales history" is a record of past sales information for a product.

[0196] "Stock status" refers to information about how much of a particular product is currently in stock.

[0197] "Market trend data" refers to data that indicates current market trends and tendencies.

[0198] A "generative AI model" is an artificial intelligence model used to predict appropriate selling prices and inventory levels based on data.

[0199] A "business dashboard" is an interface that allows businesses to view and manage their business data.

[0200] "Barcode scanning" is a method of obtaining a product ID by reading a barcode.

[0201] The "prompt sentence generation means" is a function that automatically generates the required prompt sentences according to instructions from the system.

[0202] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. Specifically, this system includes a product price comparison service for users and a service that provides fair sales prices and inventory numbers for businesses. An embodiment of this system is described below.

[0203] 1. Data Acquisition

[0204] The server periodically sends an HTTP request to the POS system to obtain sales data for the physical store. This request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data, and the response data is returned to the server.

[0205] 2. Data formatting and cleansing

[0206] The server converts the retrieved data into a common data format. This conversion unifies different data formats (for example, JSON key names and value formats). Next, it performs data cleansing to detect and correct duplicates and missing data. Duplicates are removed and missing data is filled in.

[0207] 3. Data Storage

[0208] The server stores the cleansed and unified data in a database, which is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0209] 4. Price comparison service for users

[0210] A user device (e.g., smart glasses or a smartphone) obtains a product ID by scanning a barcode. When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from a database and returns the results to the user device. The user device displays the retrieved price information, allowing the user to easily compare prices.

[0211] Specific examples

[0212] The user scans the barcode and obtains the product ID "1234567890." The server receives the request " / search?query=1234567890" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store (¥1000) and the price in the online store (¥950), and displays this information on the screen of the smart glasses.

[0213] 5. Sales price and inventory information service for businesses

[0214] The server inputs data such as sales history, inventory status, and market trends into a generative AI model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on a dashboard for business owners.

[0215] Businesses can access this dashboard from their terminals and check the optimal prices and inventory levels estimated by the generative AI model.

[0216] Specific examples

[0217] The server inputs the past six months' sales history of "laptop computers," current inventory levels, and market trends into the generative AI model. The generative AI model calculates the optimal selling price of 90,000 yen and inventory level of 20 units, and displays the results on the business dashboard.

[0218] Prompt Sentence Examples

[0219] User: Uses smart glasses to get information about product ID 1234567890.

[0220] Generative AI models: Obtain price and availability information from brick-and-mortar and online stores.

[0221] This allows users to compare prices and check stock status in real time, enabling businesses to efficiently manage inventory and set optimal sales prices.

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] Obtaining product IDs by scanning barcodes

[0225] The user scans a product using the smart glasses' barcode scanner. The input is the product barcode, and the output is the product ID. Specifically, the user activates the glasses' scanning function, reads the barcode, and sends the product ID to the glasses' internal system.

[0226] Step 2:

[0227] Sending a database search request based on product ID

[0228] The smart glasses user device sends an HTTP request to the server using the acquired product ID. The product ID is required as input, and the device waits for a response from the server as output. Specifically, the device sends an HTTP GET request to the server with a URL such as " / search?query=productID".

[0229] Step 3:

[0230] Acquiring in-store and online sales data

[0231] Based on the received product ID, the server sends an HTTP request to the physical store's POS system and the online sales platform API. The product ID is required as input, and sales data and inventory data are obtained from each system as output. Specifically, the server retrieves data in JSON format from the POS system and online platform.

[0232] Step 4:

[0233] Data formatting and cleansing

[0234] The server converts the acquired store and online sales data into a common data format and performs data cleansing. Various acquired data is required as input, and unified data is obtained as output. Specifically, the server performs tasks such as unifying JSON keys, deleting duplicate data, and filling in missing data.

[0235] Step 5:

[0236] Unified data storage in a database

[0237] The server stores the formatted and cleansed data in a database. The cleansed data is required as input and saved in the database as output. Specifically, the server inserts data into the database using SQL queries.

[0238] Step 6:

[0239] Consolidating and sending price information to user devices

[0240] The server integrates price information from brick-and-mortar stores and online stores based on the unified data and returns it to the user's device. Product IDs and unified data are required as input, and price information is obtained as output. Specifically, the server extracts relevant information from the database and sends it to the user's device in JSON format.

[0241] Step 7:

[0242] View pricing information

[0243] The user device displays the price information received from the server on the screen. The price information from the server is required as input, and is visually displayed to the user as output. Specifically, the smart glasses display shows the prices in real stores and online stores, allowing the user to compare them.

[0244] These steps will enable users to compare prices and check stock availability in real time, allowing businesses to develop optimal sales strategies based on the data.

[0245] 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.

[0246] This invention combines an emotion engine with a system that integrates sales data from brick-and-mortar stores and online sales performance data to provide services to users and businesses. This system recognizes user emotions and can recommend products and set prices based on those emotions. Specific implementation methods for the system are described below.

[0247] 1. Data Acquisition

[0248] server:

[0249] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[0250] 2. Data formatting and cleansing

[0251] server:

[0252] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[0253] 3. Data Storage

[0254] server:

[0255] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0256] 4. Price comparison service for users

[0257] User device:

[0258] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0259] Specific examples

[0260] The user enters "laptop computer" in the product search box and presses the search button.

[0261] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[0262] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[0263] 5. Sales price and inventory information service for businesses

[0264] server:

[0265] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[0266] Operator terminal:

[0267] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[0268] Specific examples

[0269] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[0270] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[0271] The server displays the results on the operator's dashboard, where the operator can confirm them.

[0272] 6. Introducing the Emotion Engine

[0273] server:

[0274] The emotion engine recognizes a user's emotions based on their search and purchase history. Specifically, it analyzes emotions from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it.

[0275] 7. Product recommendation

[0276] server:

[0277] Based on the user's emotions, the server recommends related products to the user, and the recommendation information is sent to the user's terminal and displayed on the screen.

[0278] Specific examples

[0279] If a user searches for "laptop" multiple times but doesn't end up buying it, the emotion engine will recognize that the user is undecided.

[0280] The server generates a request " / recommendations?user_id=12345" to recommend related products and discounts.

[0281] Recommendation information such as "Special discount laptop: \85,000" is displayed on the user's device.

[0282] 8. Individual User Pricing

[0283] server:

[0284] By integrating user sentiment and sales history data, we can optimize pricing for each individual user, providing them with a customized price that increases their motivation to buy.

[0285] Specific examples

[0286] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[0287] The server sets a special price for the user, for example, offering a "limited price of 80,000 yen."

[0288] Display "Special price for you: \80,000" on the user terminal.

[0289] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, and can utilize user emotions to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[0290] The processing flow will be explained below.

[0291] 1. Data Acquisition

[0292] Step 1:

[0293] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[0294] Step 2:

[0295] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[0296] Step 3:

[0297] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[0298] Step 4:

[0299] The server receives the response data from the online sales platform and stores it in a buffer as well.

[0300] 2. Data formatting and cleansing

[0301] Step 5:

[0302] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[0303] Step 6:

[0304] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[0305] 3. Data Storage

[0306] Step 7:

[0307] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[0308] 4. Price comparison service for users

[0309] Step 8:

[0310] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[0311] Step 9:

[0312] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[0313] Step 10:

[0314] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[0315] Specific examples

[0316] The user types "laptop" into the search box and presses the search button.

[0317] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[0318] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[0319] 5. Sales price and inventory information service for businesses

[0320] Step 11:

[0321] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[0322] Step 12:

[0323] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[0324] Step 13:

[0325] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[0326] Specific examples

[0327] The server inputs data on sales history, inventory status, and market trends for "notebook_pc" into the AI ​​model.

[0328] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[0329] The server displays the results on the operator's dashboard, where the operator can confirm them.

[0330] 6. Introducing the Emotion Engine

[0331] Step 14:

[0332] The server analyzes the user's search history and purchase history, and based on that, utilizes an emotion engine to recognize the user's emotions.

[0333] Step 15:

[0334] The emotion engine analyzes user behavior patterns and identifies emotions related to interests and purchasing intent.

[0335] 7. Product recommendation

[0336] Step 16:

[0337] The server recommends corresponding products based on the recognized user's emotions, and the recommendation information is sent to the user terminal.

[0338] Step 17:

[0339] The user terminal displays the received recommendation information on the screen and makes effective product suggestions to the user.

[0340] Specific examples

[0341] If a user searches for "laptop" multiple times but doesn't buy it, the sentiment engine will recognize that the user is undecided.

[0342] The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information.

[0343] The user terminal displays recommendation information such as "Special discount laptop: \85,000."

[0344] 8. Individual User Pricing

[0345] Step 18:

[0346] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[0347] Step 19:

[0348] The server transmits the customized price information to the user terminal, allowing the user to check the special price.

[0349] Specific examples

[0350] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[0351] The server sets a special price for the user and offers it as "Limited Price \80,000."

[0352] The user terminal displays "Special price for you: \80,000."

[0353] In this way, the system of the present invention integrates and manages sales data from brick-and-mortar stores and online stores, and by utilizing user emotions, it is possible to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[0354] Example 2

[0355] 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."

[0356] Many current sales management systems have the problem that sales data from brick-and-mortar stores and online stores is separated, making centralized management difficult. Furthermore, product recommendations and pricing rarely take user emotions into account, making it difficult to provide personalized services. It is also difficult to develop optimal sales strategies based on sales history and market trends. Therefore, there is a need for a system that integrates sales data from brick-and-mortar stores and online stores and takes user emotions into account.

[0357] 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.

[0358] In this invention, the server includes: means for acquiring sales data from brick-and-mortar stores; means for acquiring online sales performance data; means for converting the brick-and-mortar store sales data and the online sales performance data into a common data format; means for detecting and correcting duplicate and missing data; means for storing the converted data in a database; means for a user to search for products and acquire price information from brick-and-mortar stores and online stores from the database; means for displaying the acquired price information on a user terminal; means including an emotion engine for recognizing user emotions; means for recommending products based on the recognized emotions; means for setting optimal prices for individual users; means for inputting sales history, inventory status, and market trend data into an AI model; means for calculating appropriate sales prices and appropriate inventory quantities using the AI ​​model; means for displaying the calculation results on a business dashboard; and means for providing optimal prices based on user emotions and sales history data. This enables integrated data management of brick-and-mortar stores and online stores, enables product recommendations and pricing based on user emotions, and significantly improves the efficiency of marketing strategies and sales management.

[0359] "Real store sales data" refers to data that shows records of sales made at physical stores.

[0360] "Online sales performance data" refers to data showing a record of sales made via the Internet.

[0361] A "common data format" is a data format that unifies different data formats and expresses them in a consistent format.

[0362] "Duplicate data" refers to data in which the same information is recorded multiple times.

[0363] "Missing data" refers to data that lacks essential information.

[0364] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0365] A "user terminal" is an electronic device (e.g., a personal computer or smartphone) that a user uses to input information or display received information.

[0366] An "emotion engine" is a system that analyzes a user's behavioral data and recognizes their emotional state (e.g., interest, hesitation, motivation, etc.).

[0367] The "means for recommending products" is a system that suggests products suitable for a user based on the user's recognized emotions.

[0368] The "means for setting optimal prices for individual users" is a system that sets optimal prices by taking into account the emotions and purchase history of each user.

[0369] "Sales history" is data showing records of past sales activities.

[0370] "Stock status" is data that indicates the quantity and condition of products currently in stock.

[0371] "Market trend data" refers to data that shows current market demand, supply, price fluctuations, etc.

[0372] An "AI model" is an artificial intelligence algorithm that analyzes large amounts of data and creates certain patterns and predictions.

[0373] The "Business Dashboard" is an interface that allows businesses to check important information such as sales status and market trends.

[0374] This invention is a system that integrates and manages sales data from brick-and-mortar and online stores, and provides personalized services to users and businesses. This system recognizes users' emotions and recommends products and sets prices based on those emotions. Specific implementation methods for this system are described below.

[0375] First, the server obtains sales data from the physical store. To do this, the server periodically sends an HTTP request to the POS system. The request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This data is often returned in JSON format.

[0376] The acquired data is converted into a common data format by the server. When unifying data formats, for example, different data formats (JSON key names and value formats) are converted into a consistent format. Next, data cleansing is performed to detect and correct duplicate and missing data. Duplicate data is deleted and missing parts are filled in. This is often done using data processing tools such as the Python pandas library.

[0377] The cleansed and unified data is then stored in a database by the server. This database is used to manage data from both brick-and-mortar stores and online sales in an integrated manner. Specific databases used include MySQL and PostgreSQL.

[0378] Next, we will explain how a user searches for a product. The user searches for a product using a terminal. When a search query is sent to the server, the server retrieves price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's terminal. The user's terminal displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0379] For example, if a user types "laptop" into the search box and presses the search button, the server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. It returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this information on the user's device.

[0380] Next, we will explain the functions for businesses. The server inputs data such as sales history, inventory status, and market trends into the AI ​​model. This AI model is often implemented using a framework such as TensorFlow. The AI ​​model calculates the optimal selling price and appropriate inventory quantity, and displays the results on a dashboard for businesses. Businesses can access this dashboard and check the optimal price and inventory quantity estimated by the AI ​​model.

[0381] As a concrete example, when the server inputs the sales history of "notebook_pc" for the past six months, the current inventory quantity, and market trend data into the AI ​​model, the AI ​​model calculates the optimal selling price of 90,000 yen and the inventory quantity of 20 units. The server displays the results on the business operator's dashboard, where the business operator can confirm them.

[0382] We will also explain the introduction of an emotion engine. The server uses the emotion engine to recognize the user's emotions based on their search history and purchase history. Emotions are analyzed from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it. Emotion engines are often implemented using NLP (Natural Language Processing) models.

[0383] After recognizing the user's emotion, the server recommends related products. For example, if a user repeatedly searches for "laptop" but does not end up purchasing it, the emotion engine recognizes that the user is undecided. The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information to the user. Recommendation information such as "Special Discount Laptop: ¥85,000" is displayed on the user's device.

[0384] Finally, we will explain pricing for individual users. The server integrates the user's emotions and sales history data to set the optimal price for each individual user. If the emotion engine determines that the user is very interested in a particular product but is unsure about the price, the server will set a special price for that user. For example, it will offer a "limited price of ¥80,000." The message "Special price for you: ¥80,000" will be displayed on the user's terminal.

[0385] This system will integrate and manage sales data from both brick-and-mortar and online stores, and will be able to provide personalized services by utilizing user emotions. As a result, the efficiency of marketing strategies and sales management will be greatly improved, and user satisfaction is expected to increase as well.

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1: Obtaining sales data from physical stores

[0388] The server sends an HTTP request to the POS system to obtain sales data from the physical store. The request includes authentication information, and the POS system returns response data.

[0389] Input: Request URL (https: / / pos-system / api / sales-data) and authentication information

[0390] Output: Sales data obtained from the POS system (JSON format)

[0391] Specific operation: The server periodically sends an HTTP GET request to the POS system to receive the latest sales data.

[0392] Step 2: Obtaining online sales performance data

[0393] The server sends an HTTP request to the API of the online sales platform to obtain online sales performance data.

[0394] Input: Request URL (https: / / online-platform / api / sales-data) and OAuth token

[0395] Output: Sales data obtained from online sales platforms (JSON format)

[0396] Specific operation: The server sends an HTTP GET request specifying a URL, and the online platform returns sales data.

[0397] Step 3: Standardize data formats

[0398] The server converts the retrieved data into a common data format, converting different key names and value formats into a consistent format.

[0399] Input: Raw data (JSON format) obtained from POS systems and online platforms

[0400] Output: Data converted to a common data format (JSON format)

[0401] Specific operation: The server runs a program that unifies data formats and performs operations such as converting "item_code" to "product_id."

[0402] Step 4: Data cleansing

[0403] The server detects and corrects duplicate and missing data.

[0404] Input: Data converted into a common data format

[0405] Output: Clean, cleansed data

[0406] Specific operation: Create a data frame using Python's pandas library, remove duplicate rows, and impute missing values.

[0407] Step 5: Store the data in a database

[0408] The server stores the cleansed and formatted data in a database.

[0409] Input: Clean, cleaned data

[0410] Output: Data stored in the database

[0411] Specific operation: The server establishes a database connection and executes an SQL query (INSERT INTO ...) to store the data.

[0412] Step 6: Receiving a user's search query

[0413] The user enters a search query into the search box and sends it to the server.

[0414] Input: The search query entered by the user (e.g., "laptop")

[0415] Output: The search query sent to the server

[0416] Specific behavior: A user enters a search query in a web interface and presses the search button, which sends a request to the server.

[0417] Step 7: Retrieving pricing information from the database

[0418] The server retrieves the price information of the relevant product from the database and returns it to the user terminal.

[0419] Input: The search query sent to the server

[0420] Output: Price information of the relevant product (prices in physical stores and online stores)

[0421] Specific operation: The server executes an SQL query (SELECT ...) to retrieve price information from the database and returns the results in JSON format to the user device.

[0422] Step 8: View pricing information

[0423] The price information acquired by the user terminal is displayed on the screen and provided to the user.

[0424] Input: Price information sent from the server

[0425] Output: Price information displayed on the user's device

[0426] What it does: Parse the JSON data using client-side JavaScript and display the price information on a web page.

[0427] Step 9: Data analysis for businesses

[0428] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model for analysis.

[0429] Input: Sales history, inventory status, market trend data

[0430] Output: Optimal selling price and appropriate inventory quantity generated by the AI ​​model

[0431] How it works: The server feeds data into the AI ​​model and performs analysis using TensorFlow or other frameworks.

[0432] Step 10: Displaying results on a dashboard

[0433] The server displays the analysis results of the AI ​​model on a dashboard for businesses so that they can check them.

[0434] Input: Analysis results of the AI ​​model

[0435] Output: Optimal selling price and appropriate inventory quantity displayed on the business dashboard

[0436] Specific operation: The server sends the result data to the dashboard web page so that it can be displayed on the operator's terminal.

[0437] Step 11: Emotion Recognition with the Emotion Engine

[0438] The server uses an emotion engine to recognize the user's emotions based on the user's search history and purchase history.

[0439] Input: User search and purchase history

[0440] Output: User's emotional state

[0441] Specific operation: Analyze the user's activity data using an NLP model to determine their emotional state.

[0442] Step 12: Product Recommendation

[0443] The server recommends relevant products based on the user's emotional state.

[0444] Input: User's emotional state

[0445] Output: A list of recommended products

[0446] Specific operation: The server executes the recommendation algorithm, calculates related products, and displays them on the user's device.

[0447] Step 13: Pricing for Individual Users

[0448] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[0449] Input: User sentiment and sales history data

[0450] Output: Special pricing set for individual users

[0451] Specific operation: The server sets a special price and displays it on the user's terminal as "Special price for you."

[0452] Through these steps, the system can integrate and manage sales data from brick-and-mortar and online stores, and utilize user emotions to provide personalized services, significantly improving the efficiency of marketing strategies and sales management.

[0453] (Application example 2)

[0454] 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."

[0455] In today's retail industry, there is a demand for integrating online and offline sales data and utilizing it effectively. However, rather than simply integrating data, it is expected that recognizing user emotions and providing personalized services will further increase purchasing motivation. Conventional systems have had difficulty analyzing user emotions to recommend products or set individual prices. Therefore, the present invention aims to provide a sales data management system with emotion recognition functionality and improve the user's purchasing experience.

[0456] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data of real stores, means for acquiring online sales performance data, means for converting the sales data of the real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate data and missing data, means for storing the converted data in a database, means for a user to search for products and acquire price information of real stores and online stores from the database, means for displaying the acquired price information on a user terminal, means for recognizing a user's emotion, means for recommending products based on the recognized emotion, and means for setting prices customized for individual users. This allows users to have a more personalized purchasing experience through product recommendations and special prices according to their emotions.

[0457] "Real store sales data" refers to data relating to the sale of products in actual physical stores.

[0458] "Online sales performance data" refers to data relating to the sale of products through online platforms.

[0459] A "common data format" refers to data obtained from different data sources that has been converted into a format that can be processed consistently.

[0460] "Duplicate data" is data in which the same information is recorded multiple times.

[0461] "Missing data" is data in which required information is incomplete or missing.

[0462] A "database" is a system for efficiently storing, searching, and managing organized information.

[0463] "User terminal" refers to a device that a user uses to search for and view information, such as a smartphone or tablet.

[0464] "Means for recognizing emotions" refers to a system or device for detecting and identifying a user's emotions.

[0465] A "means for recommending products" is a system for suggesting appropriate products based on the user's interests and emotions.

[0466] "Means for setting customized prices for individual users" is a system that presents appropriate prices taking into account the emotions and purchasing history of specific users.

[0467] An "AI model" is a mathematical model that uses artificial intelligence technology to perform data analysis and predictions.

[0468] "Market trend data" refers to data relating to fluctuations in supply and demand, price trends, etc. in a particular market.

[0469] A "business dashboard" is an interface that allows businesses to visually check and analyze management information.

[0470] This invention combines an emotion engine with a system that integrates sales data from brick-and-mortar stores and online sales performance data to provide services to users and businesses. This system recognizes user emotions and can recommend products and set prices based on those emotions. Specific implementation methods for the system are described below.

[0471] 1. Data Acquisition

[0472] The server periodically sends HTTP requests to the POS system to obtain sales data from the physical store. These requests include appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends HTTP requests to the online sales platform's API to obtain online sales performance data. These response data are also returned to the server.

[0473] 2. Data formatting and cleansing

[0474] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[0475] 3. Data Storage

[0476] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0477] 4. User-friendly product search and pricing information display

[0478] When a user searches for a product, the search query is sent to the server. The server retrieves price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device displays the retrieved price information on the screen, allowing the user to easily compare prices. For example, if a user enters "laptop computer" in the product search box and presses the search button, the server retrieves price information for the corresponding product and displays it on the user's device.

[0479] 5. Sales price and inventory information service for businesses

[0480] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model. This AI model calculates the optimal selling price and appropriate inventory quantity. The results are displayed on a dashboard for business operators. Business operators access this dashboard and check the optimal price and inventory quantity estimated by the AI ​​model. For example, the sales history of "notebook_pc" for the past six months, the current inventory quantity, and market trends are input into the AI ​​model to calculate the optimal selling price and inventory quantity.

[0481] 6. User Emotion Recognition

[0482] The server uses an emotion engine to recognize a user's emotions based on their search and purchase history. Specifically, the server analyzes emotions based on patterns such as when a user frequently searches for a particular product or does not end up purchasing it. For example, if a user searches for "laptop computer" multiple times but does not end up purchasing it, the emotion engine recognizes the user's hesitation.

[0483] 7. Product Recommendations and Personalized Pricing

[0484] Based on the user's emotions, the server recommends related products to the user. This recommendation information is sent to the user's device and displayed on the screen. Furthermore, the server integrates the user's emotions and sales history data to determine optimal pricing for each individual user. For example, if the emotion engine determines that a user is very interested in a particular product but is unsure about the price, it will set a special price for that user and display it on the user's device as a "special price just for you."

[0485] Specific examples

[0486] If a user repeatedly searches for "laptop" but does not end up purchasing it, the server will use its emotion engine to recognize that the user is undecided. The server will then generate a request " / recommendations?user_id=12345" to recommend related products and special discount prices. Recommendations such as "Special Discount Laptop: ¥85,000" will be displayed on the user's device.

[0487] Prompt Sentence Examples

[0488] Possible prompts include:

[0489] "Users frequently search for the product 'laptop' but don't end up purchasing it. Can you give me a Python example that uses the DeepFace library to recognize user emotions and then set a limited-time discount price based on those emotions?"

[0490] In this way, the system of the present invention can integrate and manage sales data from real stores and online stores, and further utilize user emotions to provide more personalized services to users and businesses.

[0491] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0492] Step 1:

[0493] The server obtains sales data from the physical store. To do this, the server periodically sends an HTTP request to the POS system. The HTTP request as input includes authentication information, and the response data from the POS system is returned to the server as output. This data includes the ID, price, quantity, transaction date and time of the sold item, etc.

[0494] Step 2:

[0495] The server obtains online sales performance data. It sends an HTTP request to the API of the online sales platform, and the request, including authentication information, is input. The online sales data is returned to the server as output in response to this request. This data includes information such as the user ID, product ID, purchase date and time, and purchase price.

[0496] Step 3:

[0497] The server converts the acquired data from brick-and-mortar stores and online sales into a common data format. The input data is in different formats, and data mapping is performed to unify the JSON or XML format. The output is unified data in a common data format.

[0498] Step 4:

[0499] The server then performs data cleansing on the converted data. Specifically, it detects and corrects duplicates and missing data. The input is data converted to a common data format, and the output is clean data with duplicates removed and missing data filled in.

[0500] Step 5:

[0501] The server stores the cleansed data in a database. The input is the cleansed unified format data, and the output is the data stored in the database. This database manages data from both brick-and-mortar stores and online sales in an integrated manner.

[0502] Step 6:

[0503] When a user searches for a product, the user device sends a search query to the server. The input is the search query entered by the user, such as a keyword like "laptop." The server receives this, retrieves price information for the corresponding product (both in physical stores and online stores) from the database, and returns it to the user device as output.

[0504] Step 7:

[0505] The user device displays the acquired price information on the screen. The input is price information from the server, and the output is a screen display in a format that the user can check. This display allows the user to easily compare prices between physical stores and online stores.

[0506] Step 8:

[0507] The server inputs sales history, inventory status, and market trend data into the AI ​​model. The input data includes this information, and the AI ​​model calculates the optimal selling price and appropriate inventory quantity. The output is a recommended optimized price and inventory quantity, which are displayed on the business's dashboard.

[0508] Step 9:

[0509] Businesses can check the optimal selling price and inventory quantity calculated by the AI ​​model through a dashboard. The input is the calculation result from the AI ​​model, and the output is data that businesses can visually check on the dashboard.

[0510] Step 10:

[0511] The server uses an emotion engine to recognize the user's emotions. The input is the user's search history and purchase history, which the emotion engine analyzes. The output is the user's emotional state (e.g., uncertainty, interest, satisfaction, etc.).

[0512] Step 11:

[0513] The server recommends products based on the user's emotions. The input is the output of the emotion engine and related product data. The server recommends the most suitable product and sends the recommendation information to the user's device as output. The user's device displays the recommendation information, such as "Special discount laptop: 85,000 yen."

[0514] Step 12:

[0515] The server integrates the user's emotions and sales history to set a customized price for each individual user. The input is the emotional state and sales history data, the server calculates the individual price, and the special price is displayed on the user's terminal as the output.

[0516] Prompt Sentence Examples

[0517] "Users frequently search for the product 'laptop' but don't end up purchasing it. Can you give me a Python example that uses the DeepFace library to recognize user emotions and then set a limited-time discount price based on those emotions?"

[0518] 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.

[0519] 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.

[0520] 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.

[0521] [Second embodiment]

[0522] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0523] 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.

[0524] 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).

[0525] 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.

[0526] 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.

[0527] 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).

[0528] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0529] 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.

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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."

[0534] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. This system includes a product price comparison service for users and a service that provides fair sales prices and inventory levels for businesses. Specific implementation methods for the system are described below.

[0535] 1. Data Acquisition

[0536] server:

[0537] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[0538] 2. Data formatting and cleansing

[0539] server:

[0540] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[0541] 3. Data Storage

[0542] server:

[0543] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0544] 4. Price comparison service for users

[0545] User device:

[0546] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0547] Specific examples

[0548] The user enters "laptop computer" in the product search box and presses the search button.

[0549] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[0550] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[0551] 5. Sales price and inventory information service for businesses

[0552] server:

[0553] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[0554] Operator terminal:

[0555] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[0556] Specific examples

[0557] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[0558] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[0559] The server displays the results on the operator's dashboard, where the operator can confirm them.

[0560] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, providing useful information to both users and businesses. This system brings great value to marketing strategies and sales management.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[0564] Step 2:

[0565] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[0566] Step 3:

[0567] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[0568] Step 4:

[0569] The server receives the response data from the online sales platform and stores it in a buffer as well.

[0570] Step 5:

[0571] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[0572] Step 6:

[0573] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[0574] Step 7:

[0575] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[0576] Step 8:

[0577] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[0578] Step 9:

[0579] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[0580] Step 10:

[0581] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[0582] Step 11:

[0583] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[0584] Step 12:

[0585] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[0586] Step 13:

[0587] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[0588] Step 14:

[0589] The server uses a scheduling means to set the task to start automatically in order to periodically execute the data acquisition and analysis processes.

[0590] Through the above steps, a system is built that integrates and manages sales data from physical and online stores and provides useful information to users and businesses.

[0591] Example 1

[0592] 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."

[0593] In today's retail industry, there is a need to integrate and efficiently manage sales data from both brick-and-mortar and online stores. However, building an integrated database is difficult because each sales channel uses a different data format, which can easily result in data duplication or omissions. There is also a lack of systems that allow users to easily compare product information, or tools that allow businesses to determine optimal sales prices and inventory levels. To solve this problem, a system that efficiently acquires and accurately integrates sales data is needed.

[0594] 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.

[0595] In this invention, the server includes means for acquiring sales data from real stores, means for acquiring online sales performance data, means for converting the sales data from real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate and missing data, means for storing the converted data in a database, means for a user to search for a product and acquire price information from real stores and online stores from the database, means for displaying the acquired price information on a user terminal, means for inputting sales history, inventory status, and market trend data into an AI model, means for calculating an appropriate sales price and an appropriate inventory quantity using the AI ​​model, means for displaying the calculation results on a dashboard for business operators, means for scheduling the periodic acquisition of sales data from real stores and online sales performance data, means for inputting prompt statements into the AI ​​model, and means for correcting and supplementing the acquired data. This makes it possible to efficiently integrate and manage sales data from real stores and online stores and provide useful information to users and business operators.

[0596] "Brick and mortar sales data" refers to data related to the sale of products in physical stores, including information such as transaction date and time, product name, price, and quantity.

[0597] "Online sales performance data" refers to data related to the sale of products via the Internet, including transaction dates and times, product names, prices, quantities, and delivery information.

[0598] A "common data format" refers to a standardized data representation that transforms data collected from different sources into a consistent format, facilitating uniform management of the data.

[0599] "Duplicate data" refers to the existence of two copies of the same data. Duplicate data can take up space in a database and can compromise data consistency.

[0600] "Missing data" refers to the absence of necessary information in a dataset, which can reduce the accuracy of data analysis and statistical models.

[0601] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data. There are various types, such as SQL and NoSQL.

[0602] "User terminal" refers to an electronic device used by a user to access the system, including a personal computer, smartphone, tablet, etc.

[0603] An "AI model" refers to an algorithm that uses artificial intelligence technology to extract meaningful information from data and make predictions or classifications for specific purposes.

[0604] A "prompt" is an input given to an AI model or natural language processing system, which controls the system's response and behavior.

[0605] "Scheduling means" refers to a mechanism that automatically executes specific processes or tasks at regular intervals, enabling regular data acquisition and updating.

[0606] The "business dashboard" refers to an interface that allows businesses to view and manage management data and analysis results in real time. This dashboard displays information such as sales analysis, inventory status, and optimal price proposals.

[0607] "Sales History" refers to a record of all past transactions, including details such as purchase date, product, quantity, and price.

[0608] "Inventory status" refers to information about the quantity and type of products currently in stock, which allows for effective inventory management.

[0609] "Market trend data" refers to information on consumer purchasing trends in the market, the actions of competitors, etc. This data plays an important role in sales strategies and pricing.

[0610] The system of the present invention efficiently integrates sales data from brick-and-mortar stores with online sales performance data, and provides useful information to users and businesses based on the integration. A specific implementation method of this system will now be described.

[0611] Data Acquisition

[0612] server

[0613] The server periodically sends an HTTP request to the POS system to retrieve sales data from the physical store. This request includes authentication information, and the POS system returns sales data in JSON format. Similarly, the server sends an HTTP request to the API of the online sales platform to retrieve online sales performance data. All retrieved data is stored in memory on the server.

[0614] Data transformation and cleansing

[0615] server

[0616] The acquired data is converted into a common data format. Specifically, different data formats (for example, JSON key names and value formats) are unified. Data cleansing is then performed to remove duplicate data and fill in missing data.

[0617] Data storage

[0618] server

[0619] After cleansing and unifying the data, it is stored in a database using a database connection library such as SQLAlchemy. This database manages data from both physical stores and online sales in an integrated manner.

[0620] Price comparison service for users

[0621] User terminal

[0622] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0623] Specific examples

[0624] The user enters "laptop" in the product search box and presses the search button. The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this on the user's screen.

[0625] Sales price and inventory information service for businesses

[0626] server

[0627] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity.

[0628] Operator terminal

[0629] When a business accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[0630] Specific examples

[0631] The server inputs the sales history of "notebook_pc" for the past six months, the current inventory, and market trends into the AI ​​model. The AI ​​model calculates an optimal selling price of 90,000 yen and an inventory of 20 units. The server displays the results on the business's dashboard, where the business can confirm them.

[0632] The implementation of this system will enable integrated management of sales data from brick-and-mortar and online stores, providing useful information for users and businesses. In addition, the use of generative AI models will enable highly accurate predictions and analysis using prompt sentences.

[0633] Examples of prompt statements

[0634] "Please tell me the best selling price and stock quantity for laptops."

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Step 1:

[0637] Acquiring sales data from real stores

[0638] The server periodically sends an HTTP request to the POS system. This request includes authentication information such as an API key. The POS system responds with sales data in JSON format. The response data is stored in memory.

[0639] Input: HTTP request sent by the server to the POS system

[0640] Output: Sales data returned from the POS system (JSON format)

[0641] Specific operation: The server retrieves the data using requests.get('https: / / api.pos-system.com / data', headers={'Authorization': 'Bearer YOUR_API_KEY'}).

[0642] Step 2:

[0643] Acquisition of online sales performance data

[0644] The server sends an HTTP request to the API of the online sales platform. This request includes authentication information, and the sales platform responds with sales performance data in JSON format. The response data is stored in memory.

[0645] Input: HTTP request sent by the server to the online sales platform

[0646] Output: Sales performance data (JSON format) returned from the online sales platform

[0647] Specific behavior: The server retrieves the data using requests.get('https: / / api.ecommerce-platform.com / sales-data', headers={'Authorization': 'Bearer YOUR_API_KEY'}) .

[0648] Step 3:

[0649] Standardized data format

[0650] The server uses the Python pandas library to convert the retrieved data into a common data format, unifying different data formats (for example, JSON key names and value formats).

[0651] Input: Data obtained from POS systems and online sales platforms (JSON format)

[0652] Output: Data converted into a common data format

[0653] Specific behavior: The server converts the data as follows: data = pd.DataFrame(json_data).rename(columns={'shop_id': 'store_id', 'item_price': 'price'}) .

[0654] Step 4:

[0655] Data Cleansing

[0656] The server performs data cleansing, removing duplicate data and filling in missing data. Missing data is filled in based on historical data, average values, etc.

[0657] Input: Data converted into a common data format

[0658] Output: Cleansed data

[0659] Specific behavior: The server performs data cleansing as in data.drop_duplicates(inplace=True) or data.fillna(method='ffill', inplace=True).

[0660] Step 5:

[0661] Storing data in a database

[0662] The cleansed and unified formatted data is stored in a database using a database connection library such as SQLAlchemy.

[0663] Input: Cleansed data

[0664] Output: Data stored in a database

[0665] Specific operation: The server stores data in the database using engine = create_engine('mysql+pymysql: / / user:password@host / dbname') or data.to_sql('sales_data', con=engine, if_exists='replace', index=False).

[0666] Step 6:

[0667] Price comparison service processing for users

[0668] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen.

[0669] Input: User search query

[0670] Output: Price information returned by the server (JSON format)

[0671] What happens: When a user searches for laptop, the query is sent as ' / search?query=laptop'. The server retrieves the data as result = pd.read_sql('SELECT FROM sales_data WHERE product_name="laptop"', con=engine).

[0672] Step 7:

[0673] Sales price and inventory quantity provision service processing for businesses

[0674] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. When a business owner accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[0675] Input: Sales history, inventory status, and market trend data

[0676] Output: Optimal selling price and inventory quantity calculated by the AI ​​model

[0677] Specific operation: The server prepares the data as follows: model_input = create_model_input(sales_history, inventory_data) , and calculates the optimal selling price as follows: predictions = ai_model.predict(model_input) .

[0678] This series of processes enables integrated management of sales data from brick-and-mortar stores and online stores. In addition, by using prompt statements, it becomes possible to efficiently input data into the AI ​​model and develop appropriate sales strategies.

[0679] (Application example 1)

[0680] 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."

[0681] With conventional systems, it was difficult to manage sales data from brick-and-mortar stores and online stores in an integrated manner, making it difficult for users to easily compare prices and for businesses to develop optimal sales strategies.In addition, the inability to compare prices or grasp inventory status in real time resulted in problems with the user's purchasing experience and the business's inventory management being inefficient.

[0682] 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.

[0683] In this invention, the server includes a means for acquiring sales data from brick-and-mortar stores, a means for acquiring online sales performance data, and a display device for acquiring product IDs by barcode scanning and displaying product prices and stock status corresponding to the product IDs. This allows users to compare prices and check stock status in real time, and enables businesses to calculate optimal sales prices and stock quantities, enabling efficient inventory management.

[0684] "Real store sales data" refers to data that includes sales information from physical stores.

[0685] "Online sales performance data" refers to data that includes sales information for products sold over the Internet.

[0686] A "common data format" is a data structure for converting multiple pieces of data in different formats into one unified format.

[0687] "Duplicate data" refers to data in which the same data exists multiple times.

[0688] "Missing data" refers to data that is missing data that should be present.

[0689] A "database" is a management system for systematically storing large amounts of data and using it efficiently.

[0690] "User terminal" is a general term for electronic devices that can be directly operated by a user.

[0691] "Price information" is data relating to the selling price of a particular product.

[0692] The "display device" is a device or software for visually displaying acquired data.

[0693] "Sales history" is a record of past sales information for a product.

[0694] "Stock status" refers to information about how much of a particular product is currently in stock.

[0695] "Market trend data" refers to data that indicates current market trends and tendencies.

[0696] A "generative AI model" is an artificial intelligence model used to predict appropriate selling prices and inventory levels based on data.

[0697] A "business dashboard" is an interface that allows businesses to view and manage their business data.

[0698] "Barcode scanning" is a method of obtaining a product ID by reading a barcode.

[0699] The "prompt sentence generation means" is a function that automatically generates the required prompt sentences according to instructions from the system.

[0700] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. Specifically, this system includes a product price comparison service for users and a service that provides fair sales prices and inventory numbers for businesses. An embodiment of this system is described below.

[0701] 1. Data Acquisition

[0702] The server periodically sends an HTTP request to the POS system to obtain sales data for the physical store. This request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data, and the response data is returned to the server.

[0703] 2. Data formatting and cleansing

[0704] The server converts the retrieved data into a common data format. This conversion unifies different data formats (for example, JSON key names and value formats). Next, it performs data cleansing to detect and correct duplicates and missing data. Duplicates are removed and missing data is filled in.

[0705] 3. Data Storage

[0706] The server stores the cleansed and unified data in a database, which is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0707] 4. Price comparison service for users

[0708] A user device (e.g., smart glasses or a smartphone) obtains a product ID by scanning a barcode. When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from a database and returns the results to the user device. The user device displays the retrieved price information, allowing the user to easily compare prices.

[0709] Specific examples

[0710] The user scans the barcode and obtains the product ID "1234567890." The server receives the request " / search?query=1234567890" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store (¥1000) and the price in the online store (¥950), and displays this information on the screen of the smart glasses.

[0711] 5. Sales price and inventory information service for businesses

[0712] The server inputs data such as sales history, inventory status, and market trends into a generative AI model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on a dashboard for business owners.

[0713] Businesses can access this dashboard from their terminals and check the optimal prices and inventory levels estimated by the generative AI model.

[0714] Specific examples

[0715] The server inputs the past six months' sales history of "laptop computers," current inventory levels, and market trends into the generative AI model. The generative AI model calculates the optimal selling price of 90,000 yen and inventory level of 20 units, and displays the results on the business dashboard.

[0716] Prompt Sentence Examples

[0717] User: Uses smart glasses to get information about product ID 1234567890.

[0718] Generative AI models: Obtain price and availability information from brick-and-mortar and online stores.

[0719] This allows users to compare prices and check stock status in real time, enabling businesses to efficiently manage inventory and set optimal sales prices.

[0720] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0721] Step 1:

[0722] Obtaining product IDs by scanning barcodes

[0723] The user scans a product using the smart glasses' barcode scanner. The input is the product barcode, and the output is the product ID. Specifically, the user activates the glasses' scanning function, reads the barcode, and sends the product ID to the glasses' internal system.

[0724] Step 2:

[0725] Sending a database search request based on product ID

[0726] The smart glasses user device sends an HTTP request to the server using the acquired product ID. The product ID is required as input, and the device waits for a response from the server as output. Specifically, the device sends an HTTP GET request to the server with a URL such as " / search?query=productID".

[0727] Step 3:

[0728] Acquiring in-store and online sales data

[0729] Based on the received product ID, the server sends an HTTP request to the physical store's POS system and the online sales platform API. The product ID is required as input, and sales data and inventory data are obtained from each system as output. Specifically, the server retrieves data in JSON format from the POS system and online platform.

[0730] Step 4:

[0731] Data formatting and cleansing

[0732] The server converts the acquired store and online sales data into a common data format and performs data cleansing. Various acquired data is required as input, and unified data is obtained as output. Specifically, the server performs tasks such as unifying JSON keys, deleting duplicate data, and filling in missing data.

[0733] Step 5:

[0734] Unified data storage in a database

[0735] The server stores the formatted and cleansed data in a database. The cleansed data is required as input and saved in the database as output. Specifically, the server inserts data into the database using SQL queries.

[0736] Step 6:

[0737] Consolidating and sending price information to user devices

[0738] The server integrates price information from brick-and-mortar stores and online stores based on the unified data and returns it to the user's device. Product IDs and unified data are required as input, and price information is obtained as output. Specifically, the server extracts relevant information from the database and sends it to the user's device in JSON format.

[0739] Step 7:

[0740] View pricing information

[0741] The user device displays the price information received from the server on the screen. The price information from the server is required as input, and is visually displayed to the user as output. Specifically, the smart glasses display shows the prices in real stores and online stores, allowing the user to compare them.

[0742] These steps will enable users to compare prices and check stock availability in real time, allowing businesses to develop optimal sales strategies based on the data.

[0743] 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.

[0744] This invention combines an emotion engine with a system that integrates sales data from brick-and-mortar stores and online sales performance data to provide services to users and businesses. This system recognizes user emotions and can recommend products and set prices based on those emotions. Specific implementation methods for the system are described below.

[0745] 1. Data Acquisition

[0746] server:

[0747] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[0748] 2. Data formatting and cleansing

[0749] server:

[0750] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[0751] 3. Data Storage

[0752] server:

[0753] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0754] 4. Price comparison service for users

[0755] User device:

[0756] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0757] Specific examples

[0758] The user enters "laptop computer" in the product search box and presses the search button.

[0759] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[0760] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[0761] 5. Sales price and inventory information service for businesses

[0762] server:

[0763] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[0764] Operator terminal:

[0765] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[0766] Specific examples

[0767] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[0768] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[0769] The server displays the results on the operator's dashboard, where the operator can confirm them.

[0770] 6. Introducing the Emotion Engine

[0771] server:

[0772] The emotion engine recognizes a user's emotions based on their search and purchase history. Specifically, it analyzes emotions from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it.

[0773] 7. Product recommendation

[0774] server:

[0775] Based on the user's emotions, the server recommends related products to the user, and the recommendation information is sent to the user's terminal and displayed on the screen.

[0776] Specific examples

[0777] If a user searches for "laptop" multiple times but doesn't end up buying it, the emotion engine will recognize that the user is undecided.

[0778] The server generates a request " / recommendations?user_id=12345" to recommend related products and discounts.

[0779] Recommendation information such as "Special discount laptop: \85,000" is displayed on the user's device.

[0780] 8. Individual User Pricing

[0781] server:

[0782] By integrating user sentiment and sales history data, we can optimize pricing for each individual user, providing them with a customized price that increases their motivation to buy.

[0783] Specific examples

[0784] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[0785] The server sets a special price for the user, for example, offering a "limited price of 80,000 yen."

[0786] Display "Special price for you: \80,000" on the user terminal.

[0787] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, and can utilize user emotions to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[0788] The processing flow will be explained below.

[0789] 1. Data Acquisition

[0790] Step 1:

[0791] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[0792] Step 2:

[0793] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[0794] Step 3:

[0795] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[0796] Step 4:

[0797] The server receives the response data from the online sales platform and stores it in a buffer as well.

[0798] 2. Data formatting and cleansing

[0799] Step 5:

[0800] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[0801] Step 6:

[0802] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[0803] 3. Data Storage

[0804] Step 7:

[0805] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[0806] 4. Price comparison service for users

[0807] Step 8:

[0808] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[0809] Step 9:

[0810] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[0811] Step 10:

[0812] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[0813] Specific examples

[0814] The user types "laptop" into the search box and presses the search button.

[0815] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[0816] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[0817] 5. Sales price and inventory information service for businesses

[0818] Step 11:

[0819] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[0820] Step 12:

[0821] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[0822] Step 13:

[0823] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[0824] Specific examples

[0825] The server inputs data on sales history, inventory status, and market trends for "notebook_pc" into the AI ​​model.

[0826] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[0827] The server displays the results on the operator's dashboard, where the operator can confirm them.

[0828] 6. Introducing the Emotion Engine

[0829] Step 14:

[0830] The server analyzes the user's search history and purchase history, and based on that, utilizes an emotion engine to recognize the user's emotions.

[0831] Step 15:

[0832] The emotion engine analyzes user behavior patterns and identifies emotions related to interests and purchasing intent.

[0833] 7. Product recommendation

[0834] Step 16:

[0835] The server recommends corresponding products based on the recognized user's emotions, and the recommendation information is sent to the user terminal.

[0836] Step 17:

[0837] The user terminal displays the received recommendation information on the screen and makes effective product suggestions to the user.

[0838] Specific examples

[0839] If a user searches for "laptop" multiple times but doesn't buy it, the sentiment engine will recognize that the user is undecided.

[0840] The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information.

[0841] The user terminal displays recommendation information such as "Special discount laptop: \85,000."

[0842] 8. Individual User Pricing

[0843] Step 18:

[0844] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[0845] Step 19:

[0846] The server transmits the customized price information to the user terminal, allowing the user to check the special price.

[0847] Specific examples

[0848] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[0849] The server sets a special price for the user and offers it as "Limited Price \80,000."

[0850] The user terminal displays "Special price for you: \80,000."

[0851] In this way, the system of the present invention integrates and manages sales data from brick-and-mortar stores and online stores, and by utilizing user emotions, it is possible to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[0852] Example 2

[0853] 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."

[0854] Many current sales management systems have the problem that sales data from brick-and-mortar stores and online stores is separated, making centralized management difficult. Furthermore, product recommendations and pricing rarely take user emotions into account, making it difficult to provide personalized services. It is also difficult to develop optimal sales strategies based on sales history and market trends. Therefore, there is a need for a system that integrates sales data from brick-and-mortar stores and online stores and takes user emotions into account.

[0855] 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.

[0856] In this invention, the server includes: means for acquiring sales data from brick-and-mortar stores; means for acquiring online sales performance data; means for converting the brick-and-mortar store sales data and the online sales performance data into a common data format; means for detecting and correcting duplicate and missing data; means for storing the converted data in a database; means for a user to search for products and acquire price information from brick-and-mortar stores and online stores from the database; means for displaying the acquired price information on a user terminal; means including an emotion engine for recognizing user emotions; means for recommending products based on the recognized emotions; means for setting optimal prices for individual users; means for inputting sales history, inventory status, and market trend data into an AI model; means for calculating appropriate sales prices and appropriate inventory quantities using the AI ​​model; means for displaying the calculation results on a business dashboard; and means for providing optimal prices based on user emotions and sales history data. This enables integrated data management of brick-and-mortar stores and online stores, enables product recommendations and pricing based on user emotions, and significantly improves the efficiency of marketing strategies and sales management.

[0857] "Real store sales data" refers to data that shows records of sales made at physical stores.

[0858] "Online sales performance data" refers to data showing a record of sales made via the Internet.

[0859] A "common data format" is a data format that unifies different data formats and expresses them in a consistent format.

[0860] "Duplicate data" refers to data in which the same information is recorded multiple times.

[0861] "Missing data" refers to data that lacks essential information.

[0862] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0863] A "user terminal" is an electronic device (e.g., a personal computer or smartphone) that a user uses to input information or display received information.

[0864] An "emotion engine" is a system that analyzes a user's behavioral data and recognizes their emotional state (e.g., interest, hesitation, motivation, etc.).

[0865] The "means for recommending products" is a system that suggests products suitable for a user based on the user's recognized emotions.

[0866] The "means for setting optimal prices for individual users" is a system that sets optimal prices by taking into account the emotions and purchase history of each user.

[0867] "Sales history" is data showing records of past sales activities.

[0868] "Stock status" is data that indicates the quantity and condition of products currently in stock.

[0869] "Market trend data" refers to data that shows current market demand, supply, price fluctuations, etc.

[0870] An "AI model" is an artificial intelligence algorithm that analyzes large amounts of data and creates certain patterns and predictions.

[0871] The "Business Dashboard" is an interface that allows businesses to check important information such as sales status and market trends.

[0872] This invention is a system that integrates and manages sales data from brick-and-mortar and online stores, and provides personalized services to users and businesses. This system recognizes users' emotions and recommends products and sets prices based on those emotions. Specific implementation methods for this system are described below.

[0873] First, the server obtains sales data from the physical store. To do this, the server periodically sends an HTTP request to the POS system. The request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This data is often returned in JSON format.

[0874] The acquired data is converted into a common data format by the server. When unifying data formats, for example, different data formats (JSON key names and value formats) are converted into a consistent format. Next, data cleansing is performed to detect and correct duplicate and missing data. Duplicate data is deleted and missing parts are filled in. This is often done using data processing tools such as the Python pandas library.

[0875] The cleansed and unified data is then stored in a database by the server. This database is used to manage data from both brick-and-mortar stores and online sales in an integrated manner. Specific databases used include MySQL and PostgreSQL.

[0876] Next, we will explain how a user searches for a product. The user searches for a product using a terminal. When a search query is sent to the server, the server retrieves price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's terminal. The user's terminal displays the retrieved price information on the screen, allowing the user to easily compare prices.

[0877] For example, if a user types "laptop" into the search box and presses the search button, the server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. It returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this information on the user's device.

[0878] Next, we will explain the functions for businesses. The server inputs data such as sales history, inventory status, and market trends into the AI ​​model. This AI model is often implemented using a framework such as TensorFlow. The AI ​​model calculates the optimal selling price and appropriate inventory quantity, and displays the results on a dashboard for businesses. Businesses can access this dashboard and check the optimal price and inventory quantity estimated by the AI ​​model.

[0879] As a concrete example, when the server inputs the sales history of "notebook_pc" for the past six months, the current inventory quantity, and market trend data into the AI ​​model, the AI ​​model calculates the optimal selling price of 90,000 yen and the inventory quantity of 20 units. The server displays the results on the business operator's dashboard, where the business operator can confirm them.

[0880] We will also explain the introduction of an emotion engine. The server uses the emotion engine to recognize the user's emotions based on their search history and purchase history. Emotions are analyzed from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it. Emotion engines are often implemented using NLP (Natural Language Processing) models.

[0881] After recognizing the user's emotion, the server recommends related products. For example, if a user repeatedly searches for "laptop" but does not end up purchasing it, the emotion engine recognizes that the user is undecided. The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information to the user. Recommendation information such as "Special Discount Laptop: ¥85,000" is displayed on the user's device.

[0882] Finally, we will explain pricing for individual users. The server integrates the user's emotions and sales history data to set the optimal price for each individual user. If the emotion engine determines that the user is very interested in a particular product but is unsure about the price, the server will set a special price for that user. For example, it will offer a "limited price of ¥80,000." The message "Special price for you: ¥80,000" will be displayed on the user's terminal.

[0883] This system will integrate and manage sales data from both brick-and-mortar and online stores, and will be able to provide personalized services by utilizing user emotions. As a result, the efficiency of marketing strategies and sales management will be greatly improved, and user satisfaction is expected to increase as well.

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

[0885] Step 1: Obtaining sales data from physical stores

[0886] The server sends an HTTP request to the POS system to obtain sales data from the physical store. The request includes authentication information, and the POS system returns response data.

[0887] Input: Request URL (https: / / pos-system / api / sales-data) and authentication information

[0888] Output: Sales data obtained from the POS system (JSON format)

[0889] Specific operation: The server periodically sends an HTTP GET request to the POS system to receive the latest sales data.

[0890] Step 2: Obtaining online sales performance data

[0891] The server sends an HTTP request to the API of the online sales platform to obtain online sales performance data.

[0892] Input: Request URL (https: / / online-platform / api / sales-data) and OAuth token

[0893] Output: Sales data obtained from online sales platforms (JSON format)

[0894] Specific operation: The server sends an HTTP GET request specifying a URL, and the online platform returns sales data.

[0895] Step 3: Standardize data formats

[0896] The server converts the retrieved data into a common data format, converting different key names and value formats into a consistent format.

[0897] Input: Raw data (JSON format) obtained from POS systems and online platforms

[0898] Output: Data converted to a common data format (JSON format)

[0899] Specific operation: The server runs a program that unifies data formats and performs operations such as converting "item_code" to "product_id."

[0900] Step 4: Data cleansing

[0901] The server detects and corrects duplicate and missing data.

[0902] Input: Data converted into a common data format

[0903] Output: Clean, cleansed data

[0904] Specific operation: Create a data frame using Python's pandas library, remove duplicate rows, and impute missing values.

[0905] Step 5: Store the data in a database

[0906] The server stores the cleansed and formatted data in a database.

[0907] Input: Clean, cleaned data

[0908] Output: Data stored in the database

[0909] Specific operation: The server establishes a database connection and executes an SQL query (INSERT INTO ...) to store the data.

[0910] Step 6: Receiving a user's search query

[0911] The user enters a search query into the search box and sends it to the server.

[0912] Input: The search query entered by the user (e.g., "laptop")

[0913] Output: The search query sent to the server

[0914] Specific behavior: A user enters a search query in a web interface and presses the search button, which sends a request to the server.

[0915] Step 7: Retrieving pricing information from the database

[0916] The server retrieves the price information of the relevant product from the database and returns it to the user terminal.

[0917] Input: The search query sent to the server

[0918] Output: Price information of the relevant product (prices in physical stores and online stores)

[0919] Specific operation: The server executes an SQL query (SELECT ...) to retrieve price information from the database and returns the results in JSON format to the user device.

[0920] Step 8: View pricing information

[0921] The price information acquired by the user terminal is displayed on the screen and provided to the user.

[0922] Input: Price information sent from the server

[0923] Output: Price information displayed on the user's device

[0924] What it does: Parse the JSON data using client-side JavaScript and display the price information on a web page.

[0925] Step 9: Data analysis for businesses

[0926] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model for analysis.

[0927] Input: Sales history, inventory status, market trend data

[0928] Output: Optimal selling price and appropriate inventory quantity generated by the AI ​​model

[0929] How it works: The server feeds data into the AI ​​model and performs analysis using TensorFlow or other frameworks.

[0930] Step 10: Displaying results on a dashboard

[0931] The server displays the analysis results of the AI ​​model on a dashboard for businesses so that they can check them.

[0932] Input: Analysis results of the AI ​​model

[0933] Output: Optimal selling price and appropriate inventory quantity displayed on the business dashboard

[0934] Specific operation: The server sends the result data to the dashboard web page so that it can be displayed on the operator's terminal.

[0935] Step 11: Emotion Recognition with the Emotion Engine

[0936] The server uses an emotion engine to recognize the user's emotions based on the user's search history and purchase history.

[0937] Input: User search and purchase history

[0938] Output: User's emotional state

[0939] Specific operation: Analyze the user's activity data using an NLP model to determine their emotional state.

[0940] Step 12: Product Recommendation

[0941] The server recommends relevant products based on the user's emotional state.

[0942] Input: User's emotional state

[0943] Output: A list of recommended products

[0944] Specific operation: The server executes the recommendation algorithm, calculates related products, and displays them on the user's device.

[0945] Step 13: Pricing for Individual Users

[0946] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[0947] Input: User sentiment and sales history data

[0948] Output: Special pricing set for individual users

[0949] Specific operation: The server sets a special price and displays it on the user's terminal as "Special price for you."

[0950] Through these steps, the system can integrate and manage sales data from brick-and-mortar and online stores, and utilize user emotions to provide personalized services, significantly improving the efficiency of marketing strategies and sales management.

[0951] (Application example 2)

[0952] 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."

[0953] In today's retail industry, there is a demand for integrating online and offline sales data and utilizing it effectively. However, rather than simply integrating data, it is expected that recognizing user emotions and providing personalized services will further increase purchasing motivation. Conventional systems have had difficulty analyzing user emotions to recommend products or set individual prices. Therefore, the present invention aims to provide a sales data management system with emotion recognition functionality and improve the user's purchasing experience.

[0954] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data of real stores, means for acquiring online sales performance data, means for converting the sales data of the real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate data and missing data, means for storing the converted data in a database, means for a user to search for products and acquire price information of real stores and online stores from the database, means for displaying the acquired price information on a user terminal, means for recognizing a user's emotion, means for recommending products based on the recognized emotion, and means for setting prices customized for individual users. This allows users to have a more personalized purchasing experience through product recommendations and special prices according to their emotions.

[0955] "Real store sales data" refers to data relating to the sale of products in actual physical stores.

[0956] "Online sales performance data" refers to data relating to the sale of products through online platforms.

[0957] A "common data format" refers to data obtained from different data sources that has been converted into a format that can be processed consistently.

[0958] "Duplicate data" is data in which the same information is recorded multiple times.

[0959] "Missing data" is data in which required information is incomplete or missing.

[0960] A "database" is a system for efficiently storing, searching, and managing organized information.

[0961] "User terminal" refers to a device that a user uses to search for and view information, such as a smartphone or tablet.

[0962] "Means for recognizing emotions" refers to a system or device for detecting and identifying a user's emotions.

[0963] A "means for recommending products" is a system for suggesting appropriate products based on the user's interests and emotions.

[0964] "Means for setting customized prices for individual users" is a system that presents appropriate prices taking into account the emotions and purchasing history of specific users.

[0965] An "AI model" is a mathematical model that uses artificial intelligence technology to perform data analysis and predictions.

[0966] "Market trend data" refers to data relating to fluctuations in supply and demand, price trends, etc. in a particular market.

[0967] A "business dashboard" is an interface that allows businesses to visually check and analyze management information.

[0968] This invention combines an emotion engine with a system that integrates sales data from brick-and-mortar stores and online sales performance data to provide services to users and businesses. This system recognizes user emotions and can recommend products and set prices based on those emotions. Specific implementation methods for the system are described below.

[0969] 1. Data Acquisition

[0970] The server periodically sends HTTP requests to the POS system to obtain sales data from the physical store. These requests include appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends HTTP requests to the online sales platform's API to obtain online sales performance data. These response data are also returned to the server.

[0971] 2. Data formatting and cleansing

[0972] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[0973] 3. Data Storage

[0974] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[0975] 4. User-friendly product search and pricing information display

[0976] When a user searches for a product, the search query is sent to the server. The server retrieves price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device displays the retrieved price information on the screen, allowing the user to easily compare prices. For example, if a user enters "laptop computer" in the product search box and presses the search button, the server retrieves price information for the corresponding product and displays it on the user's device.

[0977] 5. Sales price and inventory information service for businesses

[0978] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model. This AI model calculates the optimal selling price and appropriate inventory quantity. The results are displayed on a dashboard for business operators. Business operators access this dashboard and check the optimal price and inventory quantity estimated by the AI ​​model. For example, the sales history of "notebook_pc" for the past six months, the current inventory quantity, and market trends are input into the AI ​​model to calculate the optimal selling price and inventory quantity.

[0979] 6. User Emotion Recognition

[0980] The server uses an emotion engine to recognize a user's emotions based on their search and purchase history. Specifically, the server analyzes emotions based on patterns such as when a user frequently searches for a particular product or does not end up purchasing it. For example, if a user searches for "laptop computer" multiple times but does not end up purchasing it, the emotion engine recognizes the user's hesitation.

[0981] 7. Product Recommendations and Personalized Pricing

[0982] Based on the user's emotions, the server recommends related products to the user. This recommendation information is sent to the user's device and displayed on the screen. Furthermore, the server integrates the user's emotions and sales history data to determine optimal pricing for each individual user. For example, if the emotion engine determines that a user is very interested in a particular product but is unsure about the price, it will set a special price for that user and display it on the user's device as a "special price just for you."

[0983] Specific examples

[0984] If a user repeatedly searches for "laptop" but does not end up purchasing it, the server will use its emotion engine to recognize that the user is undecided. The server will then generate a request " / recommendations?user_id=12345" to recommend related products and special discount prices. Recommendations such as "Special Discount Laptop: ¥85,000" will be displayed on the user's device.

[0985] Prompt Sentence Examples

[0986] Possible prompts include:

[0987] "Users frequently search for the product 'laptop' but don't end up purchasing it. Can you give me a Python example that uses the DeepFace library to recognize user emotions and then set a limited-time discount price based on those emotions?"

[0988] In this way, the system of the present invention can integrate and manage sales data from real stores and online stores, and further utilize user emotions to provide more personalized services to users and businesses.

[0989] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0990] Step 1:

[0991] The server obtains sales data from the physical store. To do this, the server periodically sends an HTTP request to the POS system. The HTTP request as input includes authentication information, and the response data from the POS system is returned to the server as output. This data includes the ID, price, quantity, transaction date and time of the sold item, etc.

[0992] Step 2:

[0993] The server obtains online sales performance data. It sends an HTTP request to the API of the online sales platform, and the request, including authentication information, is input. The online sales data is returned to the server as output in response to this request. This data includes information such as the user ID, product ID, purchase date and time, and purchase price.

[0994] Step 3:

[0995] The server converts the acquired data from brick-and-mortar stores and online sales into a common data format. The input data is in different formats, and data mapping is performed to unify the JSON or XML format. The output is unified data in a common data format.

[0996] Step 4:

[0997] The server then performs data cleansing on the converted data. Specifically, it detects and corrects duplicates and missing data. The input is data converted to a common data format, and the output is clean data with duplicates removed and missing data filled in.

[0998] Step 5:

[0999] The server stores the cleansed data in a database. The input is the cleansed unified format data, and the output is the data stored in the database. This database manages data from both brick-and-mortar stores and online sales in an integrated manner.

[1000] Step 6:

[1001] When a user searches for a product, the user device sends a search query to the server. The input is the search query entered by the user, such as a keyword like "laptop." The server receives this, retrieves price information for the corresponding product (both in physical stores and online stores) from the database, and returns it to the user device as output.

[1002] Step 7:

[1003] The user device displays the acquired price information on the screen. The input is price information from the server, and the output is a screen display in a format that the user can check. This display allows the user to easily compare prices between physical stores and online stores.

[1004] Step 8:

[1005] The server inputs sales history, inventory status, and market trend data into the AI ​​model. The input data includes this information, and the AI ​​model calculates the optimal selling price and appropriate inventory quantity. The output is a recommended optimized price and inventory quantity, which are displayed on the business's dashboard.

[1006] Step 9:

[1007] Businesses can check the optimal selling price and inventory quantity calculated by the AI ​​model through a dashboard. The input is the calculation result from the AI ​​model, and the output is data that businesses can visually check on the dashboard.

[1008] Step 10:

[1009] The server uses an emotion engine to recognize the user's emotions. The input is the user's search history and purchase history, which the emotion engine analyzes. The output is the user's emotional state (e.g., uncertainty, interest, satisfaction, etc.).

[1010] Step 11:

[1011] The server recommends products based on the user's emotions. The input is the output of the emotion engine and related product data. The server recommends the most suitable product and sends the recommendation information to the user's device as output. The user's device displays the recommendation information, such as "Special discount laptop: 85,000 yen."

[1012] Step 12:

[1013] The server integrates the user's emotions and sales history to set a customized price for each individual user. The input is the emotional state and sales history data, the server calculates the individual price, and the special price is displayed on the user's terminal as the output.

[1014] Prompt Sentence Examples

[1015] "Users frequently search for the product 'laptop' but don't end up purchasing it. Can you give me a Python example that uses the DeepFace library to recognize user emotions and then set a limited-time discount price based on those emotions?"

[1016] 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.

[1017] 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.

[1018] 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.

[1019] [Third embodiment]

[1020] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1021] 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.

[1022] 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).

[1023] 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.

[1024] 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.

[1025] 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).

[1026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1027] 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.

[1028] 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.

[1029] 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.

[1030] 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.

[1031] 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."

[1032] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. This system includes a product price comparison service for users and a service that provides fair sales prices and inventory levels for businesses. Specific implementation methods for the system are described below.

[1033] 1. Data Acquisition

[1034] server:

[1035] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[1036] 2. Data formatting and cleansing

[1037] server:

[1038] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[1039] 3. Data Storage

[1040] server:

[1041] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[1042] 4. Price comparison service for users

[1043] User device:

[1044] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1045] Specific examples

[1046] The user enters "laptop computer" in the product search box and presses the search button.

[1047] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[1048] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[1049] 5. Sales price and inventory information service for businesses

[1050] server:

[1051] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[1052] Operator terminal:

[1053] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[1054] Specific examples

[1055] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[1056] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[1057] The server displays the results on the operator's dashboard, where the operator can confirm them.

[1058] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, providing useful information to both users and businesses. This system brings great value to marketing strategies and sales management.

[1059] The processing flow will be explained below.

[1060] Step 1:

[1061] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[1062] Step 2:

[1063] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[1064] Step 3:

[1065] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[1066] Step 4:

[1067] The server receives the response data from the online sales platform and stores it in a buffer as well.

[1068] Step 5:

[1069] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[1070] Step 6:

[1071] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[1072] Step 7:

[1073] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[1074] Step 8:

[1075] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[1076] Step 9:

[1077] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[1078] Step 10:

[1079] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[1080] Step 11:

[1081] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[1082] Step 12:

[1083] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[1084] Step 13:

[1085] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[1086] Step 14:

[1087] The server uses a scheduling means to set the task to start automatically in order to periodically execute the data acquisition and analysis processes.

[1088] Through the above steps, a system is built that integrates and manages sales data from physical and online stores and provides useful information to users and businesses.

[1089] Example 1

[1090] 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."

[1091] In today's retail industry, there is a need to integrate and efficiently manage sales data from both brick-and-mortar and online stores. However, building an integrated database is difficult because each sales channel uses a different data format, which can easily result in data duplication or omissions. There is also a lack of systems that allow users to easily compare product information, or tools that allow businesses to determine optimal sales prices and inventory levels. To solve this problem, a system that efficiently acquires and accurately integrates sales data is needed.

[1092] 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.

[1093] In this invention, the server includes means for acquiring sales data from real stores, means for acquiring online sales performance data, means for converting the sales data from real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate and missing data, means for storing the converted data in a database, means for a user to search for a product and acquire price information from real stores and online stores from the database, means for displaying the acquired price information on a user terminal, means for inputting sales history, inventory status, and market trend data into an AI model, means for calculating an appropriate sales price and an appropriate inventory quantity using the AI ​​model, means for displaying the calculation results on a dashboard for business operators, means for scheduling the periodic acquisition of sales data from real stores and online sales performance data, means for inputting prompt statements into the AI ​​model, and means for correcting and supplementing the acquired data. This makes it possible to efficiently integrate and manage sales data from real stores and online stores and provide useful information to users and business operators.

[1094] "Brick and mortar sales data" refers to data related to the sale of products in physical stores, including information such as transaction date and time, product name, price, and quantity.

[1095] "Online sales performance data" refers to data related to the sale of products via the Internet, including transaction dates and times, product names, prices, quantities, and delivery information.

[1096] A "common data format" refers to a standardized data representation that transforms data collected from different sources into a consistent format, facilitating uniform management of the data.

[1097] "Duplicate data" refers to the existence of two copies of the same data. Duplicate data can take up space in a database and can compromise data consistency.

[1098] "Missing data" refers to the absence of necessary information in a dataset, which can reduce the accuracy of data analysis and statistical models.

[1099] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data. There are various types, such as SQL and NoSQL.

[1100] "User terminal" refers to an electronic device used by a user to access the system, including a personal computer, smartphone, tablet, etc.

[1101] An "AI model" refers to an algorithm that uses artificial intelligence technology to extract meaningful information from data and make predictions or classifications for specific purposes.

[1102] A "prompt" is an input given to an AI model or natural language processing system, which controls the system's response and behavior.

[1103] "Scheduling means" refers to a mechanism that automatically executes specific processes or tasks at regular intervals, enabling regular data acquisition and updating.

[1104] The "business dashboard" refers to an interface that allows businesses to view and manage management data and analysis results in real time. This dashboard displays information such as sales analysis, inventory status, and optimal price proposals.

[1105] "Sales History" refers to a record of all past transactions, including details such as purchase date, product, quantity, and price.

[1106] "Inventory status" refers to information about the quantity and type of products currently in stock, which allows for effective inventory management.

[1107] "Market trend data" refers to information on consumer purchasing trends in the market, the actions of competitors, etc. This data plays an important role in sales strategies and pricing.

[1108] The system of the present invention efficiently integrates sales data from brick-and-mortar stores with online sales performance data, and provides useful information to users and businesses based on the integration. A specific implementation method of this system will now be described.

[1109] Data Acquisition

[1110] server

[1111] The server periodically sends an HTTP request to the POS system to retrieve sales data from the physical store. This request includes authentication information, and the POS system returns sales data in JSON format. Similarly, the server sends an HTTP request to the API of the online sales platform to retrieve online sales performance data. All retrieved data is stored in memory on the server.

[1112] Data transformation and cleansing

[1113] server

[1114] The acquired data is converted into a common data format. Specifically, different data formats (for example, JSON key names and value formats) are unified. Data cleansing is then performed to remove duplicate data and fill in missing data.

[1115] Data storage

[1116] server

[1117] After cleansing and unifying the data, it is stored in a database using a database connection library such as SQLAlchemy. This database manages data from both physical stores and online sales in an integrated manner.

[1118] Price comparison service for users

[1119] User terminal

[1120] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1121] Specific examples

[1122] The user enters "laptop" in the product search box and presses the search button. The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this on the user's screen.

[1123] Sales price and inventory information service for businesses

[1124] server

[1125] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity.

[1126] Operator terminal

[1127] When a business accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[1128] Specific examples

[1129] The server inputs the sales history of "notebook_pc" for the past six months, the current inventory, and market trends into the AI ​​model. The AI ​​model calculates an optimal selling price of 90,000 yen and an inventory of 20 units. The server displays the results on the business's dashboard, where the business can confirm them.

[1130] The implementation of this system will enable integrated management of sales data from brick-and-mortar and online stores, providing useful information for users and businesses. In addition, the use of generative AI models will enable highly accurate predictions and analysis using prompt sentences.

[1131] Examples of prompt statements

[1132] "Please tell me the best selling price and stock quantity for laptops."

[1133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1134] Step 1:

[1135] Acquiring sales data from real stores

[1136] The server periodically sends an HTTP request to the POS system. This request includes authentication information such as an API key. The POS system responds with sales data in JSON format. The response data is stored in memory.

[1137] Input: HTTP request sent by the server to the POS system

[1138] Output: Sales data returned from the POS system (JSON format)

[1139] Specific operation: The server retrieves the data using requests.get('https: / / api.pos-system.com / data', headers={'Authorization': 'Bearer YOUR_API_KEY'}).

[1140] Step 2:

[1141] Acquisition of online sales performance data

[1142] The server sends an HTTP request to the API of the online sales platform. This request includes authentication information, and the sales platform responds with sales performance data in JSON format. The response data is stored in memory.

[1143] Input: HTTP request sent by the server to the online sales platform

[1144] Output: Sales performance data (JSON format) returned from the online sales platform

[1145] Specific behavior: The server retrieves the data using requests.get('https: / / api.ecommerce-platform.com / sales-data', headers={'Authorization': 'Bearer YOUR_API_KEY'}) .

[1146] Step 3:

[1147] Standardized data format

[1148] The server uses the Python pandas library to convert the retrieved data into a common data format, unifying different data formats (for example, JSON key names and value formats).

[1149] Input: Data obtained from POS systems and online sales platforms (JSON format)

[1150] Output: Data converted into a common data format

[1151] Specific behavior: The server converts the data as follows: data = pd.DataFrame(json_data).rename(columns={'shop_id': 'store_id', 'item_price': 'price'}) .

[1152] Step 4:

[1153] Data Cleansing

[1154] The server performs data cleansing, removing duplicate data and filling in missing data. Missing data is filled in based on historical data, average values, etc.

[1155] Input: Data converted into a common data format

[1156] Output: Cleansed data

[1157] Specific behavior: The server performs data cleansing as in data.drop_duplicates(inplace=True) or data.fillna(method='ffill', inplace=True).

[1158] Step 5:

[1159] Storing data in a database

[1160] The cleansed and unified formatted data is stored in a database using a database connection library such as SQLAlchemy.

[1161] Input: Cleansed data

[1162] Output: Data stored in a database

[1163] Specific operation: The server stores data in the database using engine = create_engine('mysql+pymysql: / / user:password@host / dbname') or data.to_sql('sales_data', con=engine, if_exists='replace', index=False).

[1164] Step 6:

[1165] Price comparison service processing for users

[1166] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen.

[1167] Input: User search query

[1168] Output: Price information returned by the server (JSON format)

[1169] What happens: When a user searches for laptop, the query is sent as ' / search?query=laptop'. The server retrieves the data as result = pd.read_sql('SELECT FROM sales_data WHERE product_name="laptop"', con=engine).

[1170] Step 7:

[1171] Sales price and inventory quantity provision service processing for businesses

[1172] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. When a business owner accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[1173] Input: Sales history, inventory status, and market trend data

[1174] Output: Optimal selling price and inventory quantity calculated by the AI ​​model

[1175] Specific operation: The server prepares the data as follows: model_input = create_model_input(sales_history, inventory_data) , and calculates the optimal selling price as follows: predictions = ai_model.predict(model_input) .

[1176] This series of processes enables integrated management of sales data from brick-and-mortar stores and online stores. In addition, by using prompt statements, it becomes possible to efficiently input data into the AI ​​model and develop appropriate sales strategies.

[1177] (Application example 1)

[1178] 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."

[1179] With conventional systems, it was difficult to manage sales data from brick-and-mortar stores and online stores in an integrated manner, making it difficult for users to easily compare prices and for businesses to develop optimal sales strategies.In addition, the inability to compare prices or grasp inventory status in real time resulted in problems with the user's purchasing experience and the business's inventory management being inefficient.

[1180] 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.

[1181] In this invention, the server includes a means for acquiring sales data from brick-and-mortar stores, a means for acquiring online sales performance data, and a display device for acquiring product IDs by barcode scanning and displaying product prices and stock status corresponding to the product IDs. This allows users to compare prices and check stock status in real time, and enables businesses to calculate optimal sales prices and stock quantities, enabling efficient inventory management.

[1182] "Real store sales data" refers to data that includes sales information from physical stores.

[1183] "Online sales performance data" refers to data that includes sales information for products sold over the Internet.

[1184] A "common data format" is a data structure for converting multiple pieces of data in different formats into one unified format.

[1185] "Duplicate data" refers to data in which the same data exists multiple times.

[1186] "Missing data" refers to data that is missing data that should be present.

[1187] A "database" is a management system for systematically storing large amounts of data and using it efficiently.

[1188] "User terminal" is a general term for electronic devices that can be directly operated by a user.

[1189] "Price information" is data relating to the selling price of a particular product.

[1190] The "display device" is a device or software for visually displaying acquired data.

[1191] "Sales history" is a record of past sales information for a product.

[1192] "Stock status" refers to information about how much of a particular product is currently in stock.

[1193] "Market trend data" refers to data that indicates current market trends and tendencies.

[1194] A "generative AI model" is an artificial intelligence model used to predict appropriate selling prices and inventory levels based on data.

[1195] A "business dashboard" is an interface that allows businesses to view and manage their business data.

[1196] "Barcode scanning" is a method of obtaining a product ID by reading a barcode.

[1197] The "prompt sentence generation means" is a function that automatically generates the required prompt sentences according to instructions from the system.

[1198] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. Specifically, this system includes a product price comparison service for users and a service that provides fair sales prices and inventory numbers for businesses. An embodiment of this system is described below.

[1199] 1. Data Acquisition

[1200] The server periodically sends an HTTP request to the POS system to obtain sales data for the physical store. This request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data, and the response data is returned to the server.

[1201] 2. Data formatting and cleansing

[1202] The server converts the retrieved data into a common data format. This conversion unifies different data formats (for example, JSON key names and value formats). Next, it performs data cleansing to detect and correct duplicates and missing data. Duplicates are removed and missing data is filled in.

[1203] 3. Data Storage

[1204] The server stores the cleansed and unified data in a database, which is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[1205] 4. Price comparison service for users

[1206] A user device (e.g., smart glasses or a smartphone) obtains a product ID by scanning a barcode. When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from a database and returns the results to the user device. The user device displays the retrieved price information, allowing the user to easily compare prices.

[1207] Specific examples

[1208] The user scans the barcode and obtains the product ID "1234567890." The server receives the request " / search?query=1234567890" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store (¥1000) and the price in the online store (¥950), and displays this information on the screen of the smart glasses.

[1209] 5. Sales price and inventory information service for businesses

[1210] The server inputs data such as sales history, inventory status, and market trends into a generative AI model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on a dashboard for business owners.

[1211] Businesses can access this dashboard from their terminals and check the optimal prices and inventory levels estimated by the generative AI model.

[1212] Specific examples

[1213] The server inputs the past six months' sales history of "laptop computers," current inventory levels, and market trends into the generative AI model. The generative AI model calculates the optimal selling price of 90,000 yen and inventory level of 20 units, and displays the results on the business dashboard.

[1214] Prompt Sentence Examples

[1215] User: Uses smart glasses to get information about product ID 1234567890.

[1216] Generative AI models: Obtain price and availability information from brick-and-mortar and online stores.

[1217] This allows users to compare prices and check stock status in real time, enabling businesses to efficiently manage inventory and set optimal sales prices.

[1218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1219] Step 1:

[1220] Obtaining product IDs by scanning barcodes

[1221] The user scans a product using the smart glasses' barcode scanner. The input is the product barcode, and the output is the product ID. Specifically, the user activates the glasses' scanning function, reads the barcode, and sends the product ID to the glasses' internal system.

[1222] Step 2:

[1223] Sending a database search request based on product ID

[1224] The smart glasses user device sends an HTTP request to the server using the acquired product ID. The product ID is required as input, and the device waits for a response from the server as output. Specifically, the device sends an HTTP GET request to the server with a URL such as " / search?query=productID".

[1225] Step 3:

[1226] Acquiring in-store and online sales data

[1227] Based on the received product ID, the server sends an HTTP request to the physical store's POS system and the online sales platform API. The product ID is required as input, and sales data and inventory data are obtained from each system as output. Specifically, the server retrieves data in JSON format from the POS system and online platform.

[1228] Step 4:

[1229] Data formatting and cleansing

[1230] The server converts the acquired store and online sales data into a common data format and performs data cleansing. Various acquired data is required as input, and unified data is obtained as output. Specifically, the server performs tasks such as unifying JSON keys, deleting duplicate data, and filling in missing data.

[1231] Step 5:

[1232] Unified data storage in a database

[1233] The server stores the formatted and cleansed data in a database. The cleansed data is required as input and saved in the database as output. Specifically, the server inserts data into the database using SQL queries.

[1234] Step 6:

[1235] Consolidating and sending price information to user devices

[1236] The server integrates price information from brick-and-mortar stores and online stores based on the unified data and returns it to the user's device. Product IDs and unified data are required as input, and price information is obtained as output. Specifically, the server extracts relevant information from the database and sends it to the user's device in JSON format.

[1237] Step 7:

[1238] View pricing information

[1239] The user device displays the price information received from the server on the screen. The price information from the server is required as input, and is visually displayed to the user as output. Specifically, the smart glasses display shows the prices in real stores and online stores, allowing the user to compare them.

[1240] These steps will enable users to compare prices and check stock availability in real time, allowing businesses to develop optimal sales strategies based on the data.

[1241] 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.

[1242] This invention combines an emotion engine with a system that integrates sales data from brick-and-mortar stores and online sales performance data to provide services to users and businesses. This system recognizes user emotions and can recommend products and set prices based on those emotions. Specific implementation methods for the system are described below.

[1243] 1. Data Acquisition

[1244] server:

[1245] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[1246] 2. Data formatting and cleansing

[1247] server:

[1248] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[1249] 3. Data Storage

[1250] server:

[1251] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[1252] 4. Price comparison service for users

[1253] User device:

[1254] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1255] Specific examples

[1256] The user enters "laptop computer" in the product search box and presses the search button.

[1257] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[1258] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[1259] 5. Sales price and inventory information service for businesses

[1260] server:

[1261] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[1262] Operator terminal:

[1263] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[1264] Specific examples

[1265] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[1266] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[1267] The server displays the results on the operator's dashboard, where the operator can confirm them.

[1268] 6. Introducing the Emotion Engine

[1269] server:

[1270] The emotion engine recognizes a user's emotions based on their search and purchase history. Specifically, it analyzes emotions from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it.

[1271] 7. Product recommendation

[1272] server:

[1273] Based on the user's emotions, the server recommends related products to the user, and the recommendation information is sent to the user's terminal and displayed on the screen.

[1274] Specific examples

[1275] If a user searches for "laptop" multiple times but doesn't end up buying it, the emotion engine will recognize that the user is undecided.

[1276] The server generates a request " / recommendations?user_id=12345" to recommend related products and discounts.

[1277] Recommendation information such as "Special discount laptop: \85,000" is displayed on the user's device.

[1278] 8. Individual User Pricing

[1279] server:

[1280] By integrating user sentiment and sales history data, we can optimize pricing for each individual user, providing them with a customized price that increases their motivation to buy.

[1281] Specific examples

[1282] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[1283] The server sets a special price for the user, for example, offering a "limited price of 80,000 yen."

[1284] Display "Special price for you: \80,000" on the user terminal.

[1285] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, and can utilize user emotions to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[1286] The processing flow will be explained below.

[1287] 1. Data Acquisition

[1288] Step 1:

[1289] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[1290] Step 2:

[1291] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[1292] Step 3:

[1293] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[1294] Step 4:

[1295] The server receives the response data from the online sales platform and stores it in a buffer as well.

[1296] 2. Data formatting and cleansing

[1297] Step 5:

[1298] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[1299] Step 6:

[1300] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[1301] 3. Data Storage

[1302] Step 7:

[1303] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[1304] 4. Price comparison service for users

[1305] Step 8:

[1306] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[1307] Step 9:

[1308] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[1309] Step 10:

[1310] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[1311] Specific examples

[1312] The user types "laptop" into the search box and presses the search button.

[1313] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[1314] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[1315] 5. Sales price and inventory information service for businesses

[1316] Step 11:

[1317] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[1318] Step 12:

[1319] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[1320] Step 13:

[1321] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[1322] Specific examples

[1323] The server inputs data on sales history, inventory status, and market trends for "notebook_pc" into the AI ​​model.

[1324] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[1325] The server displays the results on the operator's dashboard, where the operator can confirm them.

[1326] 6. Introducing the Emotion Engine

[1327] Step 14:

[1328] The server analyzes the user's search history and purchase history, and based on that, utilizes an emotion engine to recognize the user's emotions.

[1329] Step 15:

[1330] The emotion engine analyzes user behavior patterns and identifies emotions related to interests and purchasing intent.

[1331] 7. Product recommendation

[1332] Step 16:

[1333] The server recommends corresponding products based on the recognized user's emotions, and the recommendation information is sent to the user terminal.

[1334] Step 17:

[1335] The user terminal displays the received recommendation information on the screen and makes effective product suggestions to the user.

[1336] Specific examples

[1337] If a user searches for "laptop" multiple times but doesn't buy it, the sentiment engine will recognize that the user is undecided.

[1338] The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information.

[1339] The user terminal displays recommendation information such as "Special discount laptop: \85,000."

[1340] 8. Individual User Pricing

[1341] Step 18:

[1342] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[1343] Step 19:

[1344] The server transmits the customized price information to the user terminal, allowing the user to check the special price.

[1345] Specific examples

[1346] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[1347] The server sets a special price for the user and offers it as "Limited Price \80,000."

[1348] The user terminal displays "Special price for you: \80,000."

[1349] In this way, the system of the present invention integrates and manages sales data from brick-and-mortar stores and online stores, and by utilizing user emotions, it is possible to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[1350] Example 2

[1351] 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."

[1352] Many current sales management systems have the problem that sales data from brick-and-mortar stores and online stores is separated, making centralized management difficult. Furthermore, product recommendations and pricing rarely take user emotions into account, making it difficult to provide personalized services. It is also difficult to develop optimal sales strategies based on sales history and market trends. Therefore, there is a need for a system that integrates sales data from brick-and-mortar stores and online stores and takes user emotions into account.

[1353] 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.

[1354] In this invention, the server includes: means for acquiring sales data from brick-and-mortar stores; means for acquiring online sales performance data; means for converting the brick-and-mortar store sales data and the online sales performance data into a common data format; means for detecting and correcting duplicate and missing data; means for storing the converted data in a database; means for a user to search for products and acquire price information from brick-and-mortar stores and online stores from the database; means for displaying the acquired price information on a user terminal; means including an emotion engine for recognizing user emotions; means for recommending products based on the recognized emotions; means for setting optimal prices for individual users; means for inputting sales history, inventory status, and market trend data into an AI model; means for calculating appropriate sales prices and appropriate inventory quantities using the AI ​​model; means for displaying the calculation results on a business dashboard; and means for providing optimal prices based on user emotions and sales history data. This enables integrated data management of brick-and-mortar stores and online stores, enables product recommendations and pricing based on user emotions, and significantly improves the efficiency of marketing strategies and sales management.

[1355] "Real store sales data" refers to data that shows records of sales made at physical stores.

[1356] "Online sales performance data" refers to data showing a record of sales made via the Internet.

[1357] A "common data format" is a data format that unifies different data formats and expresses them in a consistent format.

[1358] "Duplicate data" refers to data in which the same information is recorded multiple times.

[1359] "Missing data" refers to data that lacks essential information.

[1360] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1361] A "user terminal" is an electronic device (e.g., a personal computer or smartphone) that a user uses to input information or display received information.

[1362] An "emotion engine" is a system that analyzes a user's behavioral data and recognizes their emotional state (e.g., interest, hesitation, motivation, etc.).

[1363] The "means for recommending products" is a system that suggests products suitable for a user based on the user's recognized emotions.

[1364] The "means for setting optimal prices for individual users" is a system that sets optimal prices by taking into account the emotions and purchase history of each user.

[1365] "Sales history" is data showing records of past sales activities.

[1366] "Stock status" is data that indicates the quantity and condition of products currently in stock.

[1367] "Market trend data" refers to data that shows current market demand, supply, price fluctuations, etc.

[1368] An "AI model" is an artificial intelligence algorithm that analyzes large amounts of data and creates certain patterns and predictions.

[1369] The "Business Dashboard" is an interface that allows businesses to check important information such as sales status and market trends.

[1370] This invention is a system that integrates and manages sales data from brick-and-mortar and online stores, and provides personalized services to users and businesses. This system recognizes users' emotions and recommends products and sets prices based on those emotions. Specific implementation methods for this system are described below.

[1371] First, the server obtains sales data from the physical store. To do this, the server periodically sends an HTTP request to the POS system. The request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This data is often returned in JSON format.

[1372] The acquired data is converted into a common data format by the server. When unifying data formats, for example, different data formats (JSON key names and value formats) are converted into a consistent format. Next, data cleansing is performed to detect and correct duplicate and missing data. Duplicate data is deleted and missing parts are filled in. This is often done using data processing tools such as the Python pandas library.

[1373] The cleansed and unified data is then stored in a database by the server. This database is used to manage data from both brick-and-mortar stores and online sales in an integrated manner. Specific databases used include MySQL and PostgreSQL.

[1374] Next, we will explain how a user searches for a product. The user searches for a product using a terminal. When a search query is sent to the server, the server retrieves price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's terminal. The user's terminal displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1375] For example, if a user types "laptop" into the search box and presses the search button, the server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. It returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this information on the user's device.

[1376] Next, we will explain the functions for businesses. The server inputs data such as sales history, inventory status, and market trends into the AI ​​model. This AI model is often implemented using a framework such as TensorFlow. The AI ​​model calculates the optimal selling price and appropriate inventory quantity, and displays the results on a dashboard for businesses. Businesses can access this dashboard and check the optimal price and inventory quantity estimated by the AI ​​model.

[1377] As a concrete example, when the server inputs the sales history of "notebook_pc" for the past six months, the current inventory quantity, and market trend data into the AI ​​model, the AI ​​model calculates the optimal selling price of 90,000 yen and the inventory quantity of 20 units. The server displays the results on the business operator's dashboard, where the business operator can confirm them.

[1378] We will also explain the introduction of an emotion engine. The server uses the emotion engine to recognize the user's emotions based on their search history and purchase history. Emotions are analyzed from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it. Emotion engines are often implemented using NLP (Natural Language Processing) models.

[1379] After recognizing the user's emotion, the server recommends related products. For example, if a user repeatedly searches for "laptop" but does not end up purchasing it, the emotion engine recognizes that the user is undecided. The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information to the user. Recommendation information such as "Special Discount Laptop: ¥85,000" is displayed on the user's device.

[1380] Finally, we will explain pricing for individual users. The server integrates the user's emotions and sales history data to set the optimal price for each individual user. If the emotion engine determines that the user is very interested in a particular product but is unsure about the price, the server will set a special price for that user. For example, it will offer a "limited price of ¥80,000." The message "Special price for you: ¥80,000" will be displayed on the user's terminal.

[1381] This system will integrate and manage sales data from both brick-and-mortar and online stores, and will be able to provide personalized services by utilizing user emotions. As a result, the efficiency of marketing strategies and sales management will be greatly improved, and user satisfaction is expected to increase as well.

[1382] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1383] Step 1: Obtaining sales data from physical stores

[1384] The server sends an HTTP request to the POS system to obtain sales data from the physical store. The request includes authentication information, and the POS system returns response data.

[1385] Input: Request URL (https: / / pos-system / api / sales-data) and authentication information

[1386] Output: Sales data obtained from the POS system (JSON format)

[1387] Specific operation: The server periodically sends an HTTP GET request to the POS system to receive the latest sales data.

[1388] Step 2: Obtaining online sales performance data

[1389] The server sends an HTTP request to the API of the online sales platform to obtain online sales performance data.

[1390] Input: Request URL (https: / / online-platform / api / sales-data) and OAuth token

[1391] Output: Sales data obtained from online sales platforms (JSON format)

[1392] Specific operation: The server sends an HTTP GET request specifying a URL, and the online platform returns sales data.

[1393] Step 3: Standardize data formats

[1394] The server converts the retrieved data into a common data format, converting different key names and value formats into a consistent format.

[1395] Input: Raw data (JSON format) obtained from POS systems and online platforms

[1396] Output: Data converted to a common data format (JSON format)

[1397] Specific operation: The server runs a program that unifies data formats and performs operations such as converting "item_code" to "product_id."

[1398] Step 4: Data cleansing

[1399] The server detects and corrects duplicate and missing data.

[1400] Input: Data converted into a common data format

[1401] Output: Clean, cleansed data

[1402] Specific operation: Create a data frame using Python's pandas library, remove duplicate rows, and impute missing values.

[1403] Step 5: Store the data in a database

[1404] The server stores the cleansed and formatted data in a database.

[1405] Input: Clean, cleaned data

[1406] Output: Data stored in the database

[1407] Specific operation: The server establishes a database connection and executes an SQL query (INSERT INTO ...) to store the data.

[1408] Step 6: Receiving a user's search query

[1409] The user enters a search query into the search box and sends it to the server.

[1410] Input: The search query entered by the user (e.g., "laptop")

[1411] Output: The search query sent to the server

[1412] Specific behavior: A user enters a search query in a web interface and presses the search button, which sends a request to the server.

[1413] Step 7: Retrieving pricing information from the database

[1414] The server retrieves the price information of the relevant product from the database and returns it to the user terminal.

[1415] Input: The search query sent to the server

[1416] Output: Price information of the relevant product (prices in physical stores and online stores)

[1417] Specific operation: The server executes an SQL query (SELECT ...) to retrieve price information from the database and returns the results in JSON format to the user device.

[1418] Step 8: View pricing information

[1419] The price information acquired by the user terminal is displayed on the screen and provided to the user.

[1420] Input: Price information sent from the server

[1421] Output: Price information displayed on the user's device

[1422] What it does: Parse the JSON data using client-side JavaScript and display the price information on a web page.

[1423] Step 9: Data analysis for businesses

[1424] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model for analysis.

[1425] Input: Sales history, inventory status, market trend data

[1426] Output: Optimal selling price and appropriate inventory quantity generated by the AI ​​model

[1427] How it works: The server feeds data into the AI ​​model and performs analysis using TensorFlow or other frameworks.

[1428] Step 10: Displaying results on a dashboard

[1429] The server displays the analysis results of the AI ​​model on a dashboard for businesses so that they can check them.

[1430] Input: Analysis results of the AI ​​model

[1431] Output: Optimal selling price and appropriate inventory quantity displayed on the business dashboard

[1432] Specific operation: The server sends the result data to the dashboard web page so that it can be displayed on the operator's terminal.

[1433] Step 11: Emotion Recognition with the Emotion Engine

[1434] The server uses an emotion engine to recognize the user's emotions based on the user's search history and purchase history.

[1435] Input: User search and purchase history

[1436] Output: User's emotional state

[1437] Specific operation: Analyze the user's activity data using an NLP model to determine their emotional state.

[1438] Step 12: Product Recommendation

[1439] The server recommends relevant products based on the user's emotional state.

[1440] Input: User's emotional state

[1441] Output: A list of recommended products

[1442] Specific operation: The server executes the recommendation algorithm, calculates related products, and displays them on the user's device.

[1443] Step 13: Pricing for Individual Users

[1444] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[1445] Input: User sentiment and sales history data

[1446] Output: Special pricing set for individual users

[1447] Specific operation: The server sets a special price and displays it on the user's terminal as "Special price for you."

[1448] Through these steps, the system can integrate and manage sales data from brick-and-mortar and online stores, and utilize user emotions to provide personalized services, significantly improving the efficiency of marketing strategies and sales management.

[1449] (Application example 2)

[1450] 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."

[1451] In today's retail industry, there is a demand for integrating online and offline sales data and utilizing it effectively. However, rather than simply integrating data, it is expected that recognizing user emotions and providing personalized services will further increase purchasing motivation. Conventional systems have had difficulty analyzing user emotions to recommend products or set individual prices. Therefore, the present invention aims to provide a sales data management system with emotion recognition functionality and improve the user's purchasing experience.

[1452] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data of real stores, means for acquiring online sales performance data, means for converting the sales data of the real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate data and missing data, means for storing the converted data in a database, means for a user to search for products and acquire price information of real stores and online stores from the database, means for displaying the acquired price information on a user terminal, means for recognizing a user's emotion, means for recommending products based on the recognized emotion, and means for setting prices customized for individual users. This allows users to have a more personalized purchasing experience through product recommendations and special prices according to their emotions.

[1453] "Real store sales data" refers to data relating to the sale of products in actual physical stores.

[1454] "Online sales performance data" refers to data relating to the sale of products through online platforms.

[1455] A "common data format" refers to data obtained from different data sources that has been converted into a format that can be processed consistently.

[1456] "Duplicate data" is data in which the same information is recorded multiple times.

[1457] "Missing data" is data in which required information is incomplete or missing.

[1458] A "database" is a system for efficiently storing, searching, and managing organized information.

[1459] "User terminal" refers to a device that a user uses to search for and view information, such as a smartphone or tablet.

[1460] "Means for recognizing emotions" refers to a system or device for detecting and identifying a user's emotions.

[1461] A "means for recommending products" is a system for suggesting appropriate products based on the user's interests and emotions.

[1462] "Means for setting customized prices for individual users" is a system that presents appropriate prices taking into account the emotions and purchasing history of specific users.

[1463] An "AI model" is a mathematical model that uses artificial intelligence technology to perform data analysis and predictions.

[1464] "Market trend data" refers to data relating to fluctuations in supply and demand, price trends, etc. in a particular market.

[1465] A "business dashboard" is an interface that allows businesses to visually check and analyze management information.

[1466] This invention combines an emotion engine with a system that integrates sales data from brick-and-mortar stores and online sales performance data to provide services to users and businesses. This system recognizes user emotions and can recommend products and set prices based on those emotions. Specific implementation methods for the system are described below.

[1467] 1. Data Acquisition

[1468] The server periodically sends HTTP requests to the POS system to obtain sales data from the physical store. These requests include appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends HTTP requests to the online sales platform's API to obtain online sales performance data. These response data are also returned to the server.

[1469] 2. Data formatting and cleansing

[1470] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[1471] 3. Data Storage

[1472] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[1473] 4. User-friendly product search and pricing information display

[1474] When a user searches for a product, the search query is sent to the server. The server retrieves price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device displays the retrieved price information on the screen, allowing the user to easily compare prices. For example, if a user enters "laptop computer" in the product search box and presses the search button, the server retrieves price information for the corresponding product and displays it on the user's device.

[1475] 5. Sales price and inventory information service for businesses

[1476] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model. This AI model calculates the optimal selling price and appropriate inventory quantity. The results are displayed on a dashboard for business operators. Business operators access this dashboard and check the optimal price and inventory quantity estimated by the AI ​​model. For example, the sales history of "notebook_pc" for the past six months, the current inventory quantity, and market trends are input into the AI ​​model to calculate the optimal selling price and inventory quantity.

[1477] 6. User Emotion Recognition

[1478] The server uses an emotion engine to recognize a user's emotions based on their search and purchase history. Specifically, the server analyzes emotions based on patterns such as when a user frequently searches for a particular product or does not end up purchasing it. For example, if a user searches for "laptop computer" multiple times but does not end up purchasing it, the emotion engine recognizes the user's hesitation.

[1479] 7. Product Recommendations and Personalized Pricing

[1480] Based on the user's emotions, the server recommends related products to the user. This recommendation information is sent to the user's device and displayed on the screen. Furthermore, the server integrates the user's emotions and sales history data to determine optimal pricing for each individual user. For example, if the emotion engine determines that a user is very interested in a particular product but is unsure about the price, it will set a special price for that user and display it on the user's device as a "special price just for you."

[1481] Specific examples

[1482] If a user repeatedly searches for "laptop" but does not end up purchasing it, the server will use its emotion engine to recognize that the user is undecided. The server will then generate a request " / recommendations?user_id=12345" to recommend related products and special discount prices. Recommendations such as "Special Discount Laptop: ¥85,000" will be displayed on the user's device.

[1483] Prompt Sentence Examples

[1484] Possible prompts include:

[1485] "Users frequently search for the product 'laptop' but don't end up purchasing it. Can you give me a Python example that uses the DeepFace library to recognize user emotions and then set a limited-time discount price based on those emotions?"

[1486] In this way, the system of the present invention can integrate and manage sales data from real stores and online stores, and further utilize user emotions to provide more personalized services to users and businesses.

[1487] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1488] Step 1:

[1489] The server obtains sales data from the physical store. To do this, the server periodically sends an HTTP request to the POS system. The HTTP request as input includes authentication information, and the response data from the POS system is returned to the server as output. This data includes the ID, price, quantity, transaction date and time of the sold item, etc.

[1490] Step 2:

[1491] The server obtains online sales performance data. It sends an HTTP request to the API of the online sales platform, and the request, including authentication information, is input. The online sales data is returned to the server as output in response to this request. This data includes information such as the user ID, product ID, purchase date and time, and purchase price.

[1492] Step 3:

[1493] The server converts the acquired data from brick-and-mortar stores and online sales into a common data format. The input data is in different formats, and data mapping is performed to unify the JSON or XML format. The output is unified data in a common data format.

[1494] Step 4:

[1495] The server then performs data cleansing on the converted data. Specifically, it detects and corrects duplicates and missing data. The input is data converted to a common data format, and the output is clean data with duplicates removed and missing data filled in.

[1496] Step 5:

[1497] The server stores the cleansed data in a database. The input is the cleansed unified format data, and the output is the data stored in the database. This database manages data from both brick-and-mortar stores and online sales in an integrated manner.

[1498] Step 6:

[1499] When a user searches for a product, the user device sends a search query to the server. The input is the search query entered by the user, such as a keyword like "laptop." The server receives this, retrieves price information for the corresponding product (both in physical stores and online stores) from the database, and returns it to the user device as output.

[1500] Step 7:

[1501] The user device displays the acquired price information on the screen. The input is price information from the server, and the output is a screen display in a format that the user can check. This display allows the user to easily compare prices between physical stores and online stores.

[1502] Step 8:

[1503] The server inputs sales history, inventory status, and market trend data into the AI ​​model. The input data includes this information, and the AI ​​model calculates the optimal selling price and appropriate inventory quantity. The output is a recommended optimized price and inventory quantity, which are displayed on the business's dashboard.

[1504] Step 9:

[1505] Businesses can check the optimal selling price and inventory quantity calculated by the AI ​​model through a dashboard. The input is the calculation result from the AI ​​model, and the output is data that businesses can visually check on the dashboard.

[1506] Step 10:

[1507] The server uses an emotion engine to recognize the user's emotions. The input is the user's search history and purchase history, which the emotion engine analyzes. The output is the user's emotional state (e.g., uncertainty, interest, satisfaction, etc.).

[1508] Step 11:

[1509] The server recommends products based on the user's emotions. The input is the output of the emotion engine and related product data. The server recommends the most suitable product and sends the recommendation information to the user's device as output. The user's device displays the recommendation information, such as "Special discount laptop: 85,000 yen."

[1510] Step 12:

[1511] The server integrates the user's emotions and sales history to set a customized price for each individual user. The input is the emotional state and sales history data, the server calculates the individual price, and the special price is displayed on the user's terminal as the output.

[1512] Prompt Sentence Examples

[1513] "Users frequently search for the product 'laptop' but don't end up purchasing it. Can you give me a Python example that uses the DeepFace library to recognize user emotions and then set a limited-time discount price based on those emotions?"

[1514] 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.

[1515] 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.

[1516] 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.

[1517] [Fourth embodiment]

[1518] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1519] 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.

[1520] 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).

[1521] 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.

[1522] 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.

[1523] 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).

[1524] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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.

[1529] 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.

[1530] 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."

[1531] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. This system includes a product price comparison service for users and a service that provides fair sales prices and inventory levels for businesses. Specific implementation methods for the system are described below.

[1532] 1. Data Acquisition

[1533] server:

[1534] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[1535] 2. Data formatting and cleansing

[1536] server:

[1537] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[1538] 3. Data Storage

[1539] server:

[1540] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[1541] 4. Price comparison service for users

[1542] User device:

[1543] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1544] Specific examples

[1545] The user enters "laptop computer" in the product search box and presses the search button.

[1546] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[1547] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[1548] 5. Sales price and inventory information service for businesses

[1549] server:

[1550] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[1551] Operator terminal:

[1552] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[1553] Specific examples

[1554] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[1555] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[1556] The server displays the results on the operator's dashboard, where the operator can confirm them.

[1557] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, providing useful information to both users and businesses. This system brings great value to marketing strategies and sales management.

[1558] The processing flow will be explained below.

[1559] Step 1:

[1560] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[1561] Step 2:

[1562] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[1563] Step 3:

[1564] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[1565] Step 4:

[1566] The server receives the response data from the online sales platform and stores it in a buffer as well.

[1567] Step 5:

[1568] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[1569] Step 6:

[1570] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[1571] Step 7:

[1572] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[1573] Step 8:

[1574] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[1575] Step 9:

[1576] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[1577] Step 10:

[1578] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[1579] Step 11:

[1580] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[1581] Step 12:

[1582] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[1583] Step 13:

[1584] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[1585] Step 14:

[1586] The server uses a scheduling means to set the task to start automatically in order to periodically execute the data acquisition and analysis processes.

[1587] Through the above steps, a system is built that integrates and manages sales data from physical and online stores and provides useful information to users and businesses.

[1588] Example 1

[1589] 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."

[1590] In today's retail industry, there is a need to integrate and efficiently manage sales data from both brick-and-mortar and online stores. However, building an integrated database is difficult because each sales channel uses a different data format, which can easily result in data duplication or omissions. There is also a lack of systems that allow users to easily compare product information, or tools that allow businesses to determine optimal sales prices and inventory levels. To solve this problem, a system that efficiently acquires and accurately integrates sales data is needed.

[1591] 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.

[1592] In this invention, the server includes means for acquiring sales data from real stores, means for acquiring online sales performance data, means for converting the sales data from real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate and missing data, means for storing the converted data in a database, means for a user to search for a product and acquire price information from real stores and online stores from the database, means for displaying the acquired price information on a user terminal, means for inputting sales history, inventory status, and market trend data into an AI model, means for calculating an appropriate sales price and an appropriate inventory quantity using the AI ​​model, means for displaying the calculation results on a dashboard for business operators, means for scheduling the periodic acquisition of sales data from real stores and online sales performance data, means for inputting prompt statements into the AI ​​model, and means for correcting and supplementing the acquired data. This makes it possible to efficiently integrate and manage sales data from real stores and online stores and provide useful information to users and business operators.

[1593] "Brick and mortar sales data" refers to data related to the sale of products in physical stores, including information such as transaction date and time, product name, price, and quantity.

[1594] "Online sales performance data" refers to data related to the sale of products via the Internet, including transaction dates and times, product names, prices, quantities, and delivery information.

[1595] A "common data format" refers to a standardized data representation that transforms data collected from different sources into a consistent format, facilitating uniform management of the data.

[1596] "Duplicate data" refers to the existence of two copies of the same data. Duplicate data can take up space in a database and can compromise data consistency.

[1597] "Missing data" refers to the absence of necessary information in a dataset, which can reduce the accuracy of data analysis and statistical models.

[1598] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data. There are various types, such as SQL and NoSQL.

[1599] "User terminal" refers to an electronic device used by a user to access the system, including a personal computer, smartphone, tablet, etc.

[1600] An "AI model" refers to an algorithm that uses artificial intelligence technology to extract meaningful information from data and make predictions or classifications for specific purposes.

[1601] A "prompt" is an input given to an AI model or natural language processing system, which controls the system's response and behavior.

[1602] "Scheduling means" refers to a mechanism that automatically executes specific processes or tasks at regular intervals, enabling regular data acquisition and updating.

[1603] The "business dashboard" refers to an interface that allows businesses to view and manage management data and analysis results in real time. This dashboard displays information such as sales analysis, inventory status, and optimal price proposals.

[1604] "Sales History" refers to a record of all past transactions, including details such as purchase date, product, quantity, and price.

[1605] "Inventory status" refers to information about the quantity and type of products currently in stock, which allows for effective inventory management.

[1606] "Market trend data" refers to information on consumer purchasing trends in the market, the actions of competitors, etc. This data plays an important role in sales strategies and pricing.

[1607] The system of the present invention efficiently integrates sales data from brick-and-mortar stores with online sales performance data, and provides useful information to users and businesses based on the integration. A specific implementation method of this system will now be described.

[1608] Data Acquisition

[1609] server

[1610] The server periodically sends an HTTP request to the POS system to retrieve sales data from the physical store. This request includes authentication information, and the POS system returns sales data in JSON format. Similarly, the server sends an HTTP request to the API of the online sales platform to retrieve online sales performance data. All retrieved data is stored in memory on the server.

[1611] Data transformation and cleansing

[1612] server

[1613] The acquired data is converted into a common data format. Specifically, different data formats (for example, JSON key names and value formats) are unified. Data cleansing is then performed to remove duplicate data and fill in missing data.

[1614] Data storage

[1615] server

[1616] After cleansing and unifying the data, it is stored in a database using a database connection library such as SQLAlchemy. This database manages data from both physical stores and online sales in an integrated manner.

[1617] Price comparison service for users

[1618] User terminal

[1619] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1620] Specific examples

[1621] The user enters "laptop" in the product search box and presses the search button. The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this on the user's screen.

[1622] Sales price and inventory information service for businesses

[1623] server

[1624] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity.

[1625] Operator terminal

[1626] When a business accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[1627] Specific examples

[1628] The server inputs the sales history of "notebook_pc" for the past six months, the current inventory, and market trends into the AI ​​model. The AI ​​model calculates an optimal selling price of 90,000 yen and an inventory of 20 units. The server displays the results on the business's dashboard, where the business can confirm them.

[1629] The implementation of this system will enable integrated management of sales data from brick-and-mortar and online stores, providing useful information for users and businesses. In addition, the use of generative AI models will enable highly accurate predictions and analysis using prompt sentences.

[1630] Examples of prompt statements

[1631] "Please tell me the best selling price and stock quantity for laptops."

[1632] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1633] Step 1:

[1634] Acquiring sales data from real stores

[1635] The server periodically sends an HTTP request to the POS system. This request includes authentication information such as an API key. The POS system responds with sales data in JSON format. The response data is stored in memory.

[1636] Input: HTTP request sent by the server to the POS system

[1637] Output: Sales data returned from the POS system (JSON format)

[1638] Specific operation: The server retrieves the data using requests.get('https: / / api.pos-system.com / data', headers={'Authorization': 'Bearer YOUR_API_KEY'}).

[1639] Step 2:

[1640] Acquisition of online sales performance data

[1641] The server sends an HTTP request to the API of the online sales platform. This request includes authentication information, and the sales platform responds with sales performance data in JSON format. The response data is stored in memory.

[1642] Input: HTTP request sent by the server to the online sales platform

[1643] Output: Sales performance data (JSON format) returned from the online sales platform

[1644] Specific behavior: The server retrieves the data using requests.get('https: / / api.ecommerce-platform.com / sales-data', headers={'Authorization': 'Bearer YOUR_API_KEY'}) .

[1645] Step 3:

[1646] Standardized data format

[1647] The server uses the Python pandas library to convert the retrieved data into a common data format, unifying different data formats (for example, JSON key names and value formats).

[1648] Input: Data obtained from POS systems and online sales platforms (JSON format)

[1649] Output: Data converted into a common data format

[1650] Specific behavior: The server converts the data as follows: data = pd.DataFrame(json_data).rename(columns={'shop_id': 'store_id', 'item_price': 'price'}) .

[1651] Step 4:

[1652] Data Cleansing

[1653] The server performs data cleansing, removing duplicate data and filling in missing data. Missing data is filled in based on historical data, average values, etc.

[1654] Input: Data converted into a common data format

[1655] Output: Cleansed data

[1656] Specific behavior: The server performs data cleansing as in data.drop_duplicates(inplace=True) or data.fillna(method='ffill', inplace=True).

[1657] Step 5:

[1658] Storing data in a database

[1659] The cleansed and unified formatted data is stored in a database using a database connection library such as SQLAlchemy.

[1660] Input: Cleansed data

[1661] Output: Data stored in a database

[1662] Specific operation: The server stores data in the database using engine = create_engine('mysql+pymysql: / / user:password@host / dbname') or data.to_sql('sales_data', con=engine, if_exists='replace', index=False).

[1663] Step 6:

[1664] Price comparison service processing for users

[1665] When a user searches for a product, the search query is sent to the server. The server retrieves the price information for the corresponding product from the database and returns it in JSON format to the user's device. The user's device then displays the retrieved price information on the screen.

[1666] Input: User search query

[1667] Output: Price information returned by the server (JSON format)

[1668] What happens: When a user searches for laptop, the query is sent as ' / search?query=laptop'. The server retrieves the data as result = pd.read_sql('SELECT FROM sales_data WHERE product_name="laptop"', con=engine).

[1669] Step 7:

[1670] Sales price and inventory quantity provision service processing for businesses

[1671] Data such as sales history, inventory status, and market trends are input into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. When a business owner accesses the dashboard, the server sends the results of the AI ​​model, which are then displayed on the dashboard.

[1672] Input: Sales history, inventory status, and market trend data

[1673] Output: Optimal selling price and inventory quantity calculated by the AI ​​model

[1674] Specific operation: The server prepares the data as follows: model_input = create_model_input(sales_history, inventory_data) , and calculates the optimal selling price as follows: predictions = ai_model.predict(model_input) .

[1675] This series of processes enables integrated management of sales data from brick-and-mortar stores and online stores. In addition, by using prompt statements, it becomes possible to efficiently input data into the AI ​​model and develop appropriate sales strategies.

[1676] (Application example 1)

[1677] 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."

[1678] With conventional systems, it was difficult to manage sales data from brick-and-mortar stores and online stores in an integrated manner, making it difficult for users to easily compare prices and for businesses to develop optimal sales strategies.In addition, the inability to compare prices or grasp inventory status in real time resulted in problems with the user's purchasing experience and the business's inventory management being inefficient.

[1679] 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.

[1680] In this invention, the server includes a means for acquiring sales data from brick-and-mortar stores, a means for acquiring online sales performance data, and a display device for acquiring product IDs by barcode scanning and displaying product prices and stock status corresponding to the product IDs. This allows users to compare prices and check stock status in real time, and enables businesses to calculate optimal sales prices and stock quantities, enabling efficient inventory management.

[1681] "Real store sales data" refers to data that includes sales information from physical stores.

[1682] "Online sales performance data" refers to data that includes sales information for products sold over the Internet.

[1683] A "common data format" is a data structure for converting multiple pieces of data in different formats into one unified format.

[1684] "Duplicate data" refers to data in which the same data exists multiple times.

[1685] "Missing data" refers to data that is missing data that should be present.

[1686] A "database" is a management system for systematically storing large amounts of data and using it efficiently.

[1687] "User terminal" is a general term for electronic devices that can be directly operated by a user.

[1688] "Price information" is data relating to the selling price of a particular product.

[1689] The "display device" is a device or software for visually displaying acquired data.

[1690] "Sales history" is a record of past sales information for a product.

[1691] "Stock status" refers to information about how much of a particular product is currently in stock.

[1692] "Market trend data" refers to data that indicates current market trends and tendencies.

[1693] A "generative AI model" is an artificial intelligence model used to predict appropriate selling prices and inventory levels based on data.

[1694] A "business dashboard" is an interface that allows businesses to view and manage their business data.

[1695] "Barcode scanning" is a method of obtaining a product ID by reading a barcode.

[1696] The "prompt sentence generation means" is a function that automatically generates the required prompt sentences according to instructions from the system.

[1697] The present invention is a system that efficiently integrates sales data from brick-and-mortar stores with online sales performance data and provides services based on the integration. Specifically, this system includes a product price comparison service for users and a service that provides fair sales prices and inventory numbers for businesses. An embodiment of this system is described below.

[1698] 1. Data Acquisition

[1699] The server periodically sends an HTTP request to the POS system to obtain sales data for the physical store. This request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data, and the response data is returned to the server.

[1700] 2. Data formatting and cleansing

[1701] The server converts the retrieved data into a common data format. This conversion unifies different data formats (for example, JSON key names and value formats). Next, it performs data cleansing to detect and correct duplicates and missing data. Duplicates are removed and missing data is filled in.

[1702] 3. Data Storage

[1703] The server stores the cleansed and unified data in a database, which is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[1704] 4. Price comparison service for users

[1705] A user device (e.g., smart glasses or a smartphone) obtains a product ID by scanning a barcode. When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from a database and returns the results to the user device. The user device displays the retrieved price information, allowing the user to easily compare prices.

[1706] Specific examples

[1707] The user scans the barcode and obtains the product ID "1234567890." The server receives the request " / search?query=1234567890" and retrieves the price information for the corresponding product from the database. The server returns to the user's device the price in the physical store (¥1000) and the price in the online store (¥950), and displays this information on the screen of the smart glasses.

[1708] 5. Sales price and inventory information service for businesses

[1709] The server inputs data such as sales history, inventory status, and market trends into a generative AI model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on a dashboard for business owners.

[1710] Businesses can access this dashboard from their terminals and check the optimal prices and inventory levels estimated by the generative AI model.

[1711] Specific examples

[1712] The server inputs the past six months' sales history of "laptop computers," current inventory levels, and market trends into the generative AI model. The generative AI model calculates the optimal selling price of 90,000 yen and inventory level of 20 units, and displays the results on the business dashboard.

[1713] Prompt Sentence Examples

[1714] User: Uses smart glasses to get information about product ID 1234567890.

[1715] Generative AI models: Obtain price and availability information from brick-and-mortar and online stores.

[1716] This allows users to compare prices and check stock status in real time, enabling businesses to efficiently manage inventory and set optimal sales prices.

[1717] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1718] Step 1:

[1719] Obtaining product IDs by scanning barcodes

[1720] The user scans a product using the smart glasses' barcode scanner. The input is the product barcode, and the output is the product ID. Specifically, the user activates the glasses' scanning function, reads the barcode, and sends the product ID to the glasses' internal system.

[1721] Step 2:

[1722] Sending a database search request based on product ID

[1723] The smart glasses user device sends an HTTP request to the server using the acquired product ID. The product ID is required as input, and the device waits for a response from the server as output. Specifically, the device sends an HTTP GET request to the server with a URL such as " / search?query=productID".

[1724] Step 3:

[1725] Acquiring in-store and online sales data

[1726] Based on the received product ID, the server sends an HTTP request to the physical store's POS system and the online sales platform API. The product ID is required as input, and sales data and inventory data are obtained from each system as output. Specifically, the server retrieves data in JSON format from the POS system and online platform.

[1727] Step 4:

[1728] Data formatting and cleansing

[1729] The server converts the acquired store and online sales data into a common data format and performs data cleansing. Various acquired data is required as input, and unified data is obtained as output. Specifically, the server performs tasks such as unifying JSON keys, deleting duplicate data, and filling in missing data.

[1730] Step 5:

[1731] Unified data storage in a database

[1732] The server stores the formatted and cleansed data in a database. The cleansed data is required as input and saved in the database as output. Specifically, the server inserts data into the database using SQL queries.

[1733] Step 6:

[1734] Consolidating and sending price information to user devices

[1735] The server integrates price information from brick-and-mortar stores and online stores based on the unified data and returns it to the user's device. Product IDs and unified data are required as input, and price information is obtained as output. Specifically, the server extracts relevant information from the database and sends it to the user's device in JSON format.

[1736] Step 7:

[1737] View pricing information

[1738] The user device displays the price information received from the server on the screen. The price information from the server is required as input, and is visually displayed to the user as output. Specifically, the smart glasses display shows the prices in real stores and online stores, allowing the user to compare them.

[1739] These steps will enable users to compare prices and check stock availability in real time, allowing businesses to develop optimal sales strategies based on the data.

[1740] 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.

[1741] This invention combines an emotion engine with a system that integrates sales data from brick-and-mortar stores and online sales performance data to provide services to users and businesses. This system recognizes user emotions and can recommend products and set prices based on those emotions. Specific implementation methods for the system are described below.

[1742] 1. Data Acquisition

[1743] server:

[1744] First, to obtain sales data from the physical store, the server periodically sends an HTTP request to the POS system. This request includes appropriate authentication information, and the response data from the POS system is returned to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This response data is also returned to the server.

[1745] 2. Data formatting and cleansing

[1746] server:

[1747] The acquired data is first converted into a common data format, which unifies different data formats (for example, JSON key names and value formats). Next, data cleansing is performed to detect and correct duplicates and missing data. Duplicates are removed and missing parts are filled in.

[1748] 3. Data Storage

[1749] server:

[1750] After cleansing and unifying the format, the data is stored in a database that is used to manage data from both brick-and-mortar stores and online sales in an integrated manner.

[1751] 4. Price comparison service for users

[1752] User device:

[1753] When a user searches for a product, the search query is sent to the server. The server retrieves the price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's device. The user's device then displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1754] Specific examples

[1755] The user enters "laptop computer" in the product search box and presses the search button.

[1756] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[1757] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[1758] 5. Sales price and inventory information service for businesses

[1759] server:

[1760] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, which then calculates the optimal selling price and appropriate inventory quantity. The results are displayed on the business's dashboard.

[1761] Operator terminal:

[1762] Businesses can access this dashboard to check the optimal prices and inventory levels estimated by the AI ​​model.

[1763] Specific examples

[1764] The server inputs the sales history of "notebook_pc" over the past six months, current inventory levels, and market trends into the AI ​​model.

[1765] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[1766] The server displays the results on the operator's dashboard, where the operator can confirm them.

[1767] 6. Introducing the Emotion Engine

[1768] server:

[1769] The emotion engine recognizes a user's emotions based on their search and purchase history. Specifically, it analyzes emotions from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it.

[1770] 7. Product recommendation

[1771] server:

[1772] Based on the user's emotions, the server recommends related products to the user, and the recommendation information is sent to the user's terminal and displayed on the screen.

[1773] Specific examples

[1774] If a user searches for "laptop" multiple times but doesn't end up buying it, the emotion engine will recognize that the user is undecided.

[1775] The server generates a request " / recommendations?user_id=12345" to recommend related products and discounts.

[1776] Recommendation information such as "Special discount laptop: \85,000" is displayed on the user's device.

[1777] 8. Individual User Pricing

[1778] server:

[1779] By integrating user sentiment and sales history data, we can optimize pricing for each individual user, providing them with a customized price that increases their motivation to buy.

[1780] Specific examples

[1781] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[1782] The server sets a special price for the user, for example, offering a "limited price of 80,000 yen."

[1783] Display "Special price for you: \80,000" on the user terminal.

[1784] In this way, the system of the present invention can integrate and manage sales data from brick-and-mortar stores and online stores, and can utilize user emotions to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[1785] The processing flow will be explained below.

[1786] 1. Data Acquisition

[1787] Step 1:

[1788] The server sends an HTTP request to the brick-and-mortar POS system, including authentication information, to the appropriate endpoint to retrieve sales data.

[1789] Step 2:

[1790] The server receives the response data from the POS system and temporarily stores the received data in a buffer.

[1791] Step 3:

[1792] The server also sends an HTTP request to the online sales platform's API to retrieve online sales performance data, again including the authentication information.

[1793] Step 4:

[1794] The server receives the response data from the online sales platform and stores it in a buffer as well.

[1795] 2. Data formatting and cleansing

[1796] Step 5:

[1797] The server converts data received from the POS system and online sales platform into a common data format, converting different data formats into specific key names and value formats to unify them.

[1798] Step 6:

[1799] The server performs data cleansing, removing any duplicates and filling in any missing data, and checking the integrity of the data.

[1800] 3. Data Storage

[1801] Step 7:

[1802] The server stores the formatted and cleansed data in a database, inserting it into the appropriate tables in the database.

[1803] 4. Price comparison service for users

[1804] Step 8:

[1805] A user enters a search query in a web browser or app and clicks the "Search" button, which sends the search query to the server.

[1806] Step 9:

[1807] The server queries a database based on the received search query to obtain price information for the relevant product at brick-and-mortar and online stores.

[1808] Step 10:

[1809] The server returns the acquired price information to the user terminal, which displays the received price information on its screen and provides the user with the price comparison results.

[1810] Specific examples

[1811] The user types "laptop" into the search box and presses the search button.

[1812] The server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database.

[1813] The information that the real store price is ¥100,000 and the online store price is ¥95,000 is returned to the user terminal and displayed on the user screen.

[1814] 5. Sales price and inventory information service for businesses

[1815] Step 11:

[1816] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model, providing the AI ​​with the data it needs for sales strategies.

[1817] Step 12:

[1818] The AI ​​model calculates the optimal selling price and appropriate inventory quantity based on the input data, and the results are returned to the server.

[1819] Step 13:

[1820] The server displays the calculation results on a dashboard for businesses, who can access the dashboard to check optimal selling prices and inventory levels.

[1821] Specific examples

[1822] The server inputs data on sales history, inventory status, and market trends for "notebook_pc" into the AI ​​model.

[1823] The AI ​​model calculates the optimal selling price to be 90,000 yen and the inventory quantity to be 20 units.

[1824] The server displays the results on the operator's dashboard, where the operator can confirm them.

[1825] 6. Introducing the Emotion Engine

[1826] Step 14:

[1827] The server analyzes the user's search history and purchase history, and based on that, utilizes an emotion engine to recognize the user's emotions.

[1828] Step 15:

[1829] The emotion engine analyzes user behavior patterns and identifies emotions related to interests and purchasing intent.

[1830] 7. Product recommendation

[1831] Step 16:

[1832] The server recommends corresponding products based on the recognized user's emotions, and the recommendation information is sent to the user terminal.

[1833] Step 17:

[1834] The user terminal displays the received recommendation information on the screen and makes effective product suggestions to the user.

[1835] Specific examples

[1836] If a user searches for "laptop" multiple times but doesn't buy it, the sentiment engine will recognize that the user is undecided.

[1837] The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information.

[1838] The user terminal displays recommendation information such as "Special discount laptop: \85,000."

[1839] 8. Individual User Pricing

[1840] Step 18:

[1841] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[1842] Step 19:

[1843] The server transmits the customized price information to the user terminal, allowing the user to check the special price.

[1844] Specific examples

[1845] The sentiment engine determines that the user is very interested in a particular product but is unsure about the price.

[1846] The server sets a special price for the user and offers it as "Limited Price \80,000."

[1847] The user terminal displays "Special price for you: \80,000."

[1848] In this way, the system of the present invention integrates and manages sales data from brick-and-mortar stores and online stores, and by utilizing user emotions, it is possible to provide more personalized services to users and businesses. This system will significantly improve the efficiency of marketing strategies and sales management.

[1849] Example 2

[1850] 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."

[1851] Many current sales management systems have the problem that sales data from brick-and-mortar stores and online stores is separated, making centralized management difficult. Furthermore, product recommendations and pricing rarely take user emotions into account, making it difficult to provide personalized services. It is also difficult to develop optimal sales strategies based on sales history and market trends. Therefore, there is a need for a system that integrates sales data from brick-and-mortar stores and online stores and takes user emotions into account.

[1852] 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.

[1853] In this invention, the server includes: means for acquiring sales data from brick-and-mortar stores; means for acquiring online sales performance data; means for converting the brick-and-mortar store sales data and the online sales performance data into a common data format; means for detecting and correcting duplicate and missing data; means for storing the converted data in a database; means for a user to search for products and acquire price information from brick-and-mortar stores and online stores from the database; means for displaying the acquired price information on a user terminal; means including an emotion engine for recognizing user emotions; means for recommending products based on the recognized emotions; means for setting optimal prices for individual users; means for inputting sales history, inventory status, and market trend data into an AI model; means for calculating appropriate sales prices and appropriate inventory quantities using the AI ​​model; means for displaying the calculation results on a business dashboard; and means for providing optimal prices based on user emotions and sales history data. This enables integrated data management of brick-and-mortar stores and online stores, enables product recommendations and pricing based on user emotions, and significantly improves the efficiency of marketing strategies and sales management.

[1854] "Real store sales data" refers to data that shows records of sales made at physical stores.

[1855] "Online sales performance data" refers to data showing a record of sales made via the Internet.

[1856] A "common data format" is a data format that unifies different data formats and expresses them in a consistent format.

[1857] "Duplicate data" refers to data in which the same information is recorded multiple times.

[1858] "Missing data" refers to data that lacks essential information.

[1859] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1860] A "user terminal" is an electronic device (e.g., a personal computer or smartphone) that a user uses to input information or display received information.

[1861] An "emotion engine" is a system that analyzes a user's behavioral data and recognizes their emotional state (e.g., interest, hesitation, motivation, etc.).

[1862] The "means for recommending products" is a system that suggests products suitable for a user based on the user's recognized emotions.

[1863] The "means for setting optimal prices for individual users" is a system that sets optimal prices by taking into account the emotions and purchase history of each user.

[1864] "Sales history" is data showing records of past sales activities.

[1865] "Stock status" is data that indicates the quantity and condition of products currently in stock.

[1866] "Market trend data" refers to data that shows current market demand, supply, price fluctuations, etc.

[1867] An "AI model" is an artificial intelligence algorithm that analyzes large amounts of data and creates certain patterns and predictions.

[1868] The "Business Dashboard" is an interface that allows businesses to check important information such as sales status and market trends.

[1869] This invention is a system that integrates and manages sales data from brick-and-mortar and online stores, and provides personalized services to users and businesses. This system recognizes users' emotions and recommends products and sets prices based on those emotions. Specific implementation methods for this system are described below.

[1870] First, the server obtains sales data from the physical store. To do this, the server periodically sends an HTTP request to the POS system. The request includes appropriate authentication information, and the POS system returns response data to the server. Similarly, the server sends an HTTP request to the API of the online sales platform to obtain online sales performance data. This data is often returned in JSON format.

[1871] The acquired data is converted into a common data format by the server. When unifying data formats, for example, different data formats (JSON key names and value formats) are converted into a consistent format. Next, data cleansing is performed to detect and correct duplicate and missing data. Duplicate data is deleted and missing parts are filled in. This is often done using data processing tools such as the Python pandas library.

[1872] The cleansed and unified data is then stored in a database by the server. This database is used to manage data from both brick-and-mortar stores and online sales in an integrated manner. Specific databases used include MySQL and PostgreSQL.

[1873] Next, we will explain how a user searches for a product. The user searches for a product using a terminal. When a search query is sent to the server, the server retrieves price information (from brick-and-mortar stores and online stores) for the corresponding product from the database and returns the results to the user's terminal. The user's terminal displays the retrieved price information on the screen, allowing the user to easily compare prices.

[1874] For example, if a user types "laptop" into the search box and presses the search button, the server receives the request " / search?query=laptop" and retrieves the price information for the corresponding product from the database. It returns to the user's device the price in the physical store of 100,000 yen and the price in the online store of 95,000 yen, and displays this information on the user's device.

[1875] Next, we will explain the functions for businesses. The server inputs data such as sales history, inventory status, and market trends into the AI ​​model. This AI model is often implemented using a framework such as TensorFlow. The AI ​​model calculates the optimal selling price and appropriate inventory quantity, and displays the results on a dashboard for businesses. Businesses can access this dashboard and check the optimal price and inventory quantity estimated by the AI ​​model.

[1876] As a concrete example, when the server inputs the sales history of "notebook_pc" for the past six months, the current inventory quantity, and market trend data into the AI ​​model, the AI ​​model calculates the optimal selling price of 90,000 yen and the inventory quantity of 20 units. The server displays the results on the business operator's dashboard, where the business operator can confirm them.

[1877] We will also explain the introduction of an emotion engine. The server uses the emotion engine to recognize the user's emotions based on their search history and purchase history. Emotions are analyzed from patterns such as when a user frequently searches for a particular product or when they do not end up purchasing it. Emotion engines are often implemented using NLP (Natural Language Processing) models.

[1878] After recognizing the user's emotion, the server recommends related products. For example, if a user repeatedly searches for "laptop" but does not end up purchasing it, the emotion engine recognizes that the user is undecided. The server generates a request " / recommendations?user_id=12345" and recommends related products and discount information to the user. Recommendation information such as "Special Discount Laptop: ¥85,000" is displayed on the user's device.

[1879] Finally, we will explain pricing for individual users. The server integrates the user's emotions and sales history data to set the optimal price for each individual user. If the emotion engine determines that the user is very interested in a particular product but is unsure about the price, the server will set a special price for that user. For example, it will offer a "limited price of ¥80,000." The message "Special price for you: ¥80,000" will be displayed on the user's terminal.

[1880] This system will integrate and manage sales data from both brick-and-mortar and online stores, and will be able to provide personalized services by utilizing user emotions. As a result, the efficiency of marketing strategies and sales management will be greatly improved, and user satisfaction is expected to increase as well.

[1881] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1882] Step 1: Obtaining sales data from physical stores

[1883] The server sends an HTTP request to the POS system to obtain sales data from the physical store. The request includes authentication information, and the POS system returns response data.

[1884] Input: Request URL (https: / / pos-system / api / sales-data) and authentication information

[1885] Output: Sales data obtained from the POS system (JSON format)

[1886] Specific operation: The server periodically sends an HTTP GET request to the POS system to receive the latest sales data.

[1887] Step 2: Obtaining online sales performance data

[1888] The server sends an HTTP request to the API of the online sales platform to obtain online sales performance data.

[1889] Input: Request URL (https: / / online-platform / api / sales-data) and OAuth token

[1890] Output: Sales data obtained from online sales platforms (JSON format)

[1891] Specific operation: The server sends an HTTP GET request specifying a URL, and the online platform returns sales data.

[1892] Step 3: Standardize data formats

[1893] The server converts the retrieved data into a common data format, converting different key names and value formats into a consistent format.

[1894] Input: Raw data (JSON format) obtained from POS systems and online platforms

[1895] Output: Data converted to a common data format (JSON format)

[1896] Specific operation: The server runs a program that unifies data formats and performs operations such as converting "item_code" to "product_id."

[1897] Step 4: Data cleansing

[1898] The server detects and corrects duplicate and missing data.

[1899] Input: Data converted into a common data format

[1900] Output: Clean, cleansed data

[1901] Specific operation: Create a data frame using Python's pandas library, remove duplicate rows, and impute missing values.

[1902] Step 5: Store the data in a database

[1903] The server stores the cleansed and formatted data in a database.

[1904] Input: Clean, cleaned data

[1905] Output: Data stored in the database

[1906] Specific operation: The server establishes a database connection and executes an SQL query (INSERT INTO ...) to store the data.

[1907] Step 6: Receiving a user's search query

[1908] The user enters a search query into the search box and sends it to the server.

[1909] Input: The search query entered by the user (e.g., "laptop")

[1910] Output: The search query sent to the server

[1911] Specific behavior: A user enters a search query in a web interface and presses the search button, which sends a request to the server.

[1912] Step 7: Retrieving pricing information from the database

[1913] The server retrieves the price information of the relevant product from the database and returns it to the user terminal.

[1914] Input: The search query sent to the server

[1915] Output: Price information of the relevant product (prices in physical stores and online stores)

[1916] Specific operation: The server executes an SQL query (SELECT ...) to retrieve price information from the database and returns the results in JSON format to the user device.

[1917] Step 8: View pricing information

[1918] The price information acquired by the user terminal is displayed on the screen and provided to the user.

[1919] Input: Price information sent from the server

[1920] Output: Price information displayed on the user's device

[1921] What it does: Parse the JSON data using client-side JavaScript and display the price information on a web page.

[1922] Step 9: Data analysis for businesses

[1923] The server inputs data such as sales history, inventory status, and market trends into the AI ​​model for analysis.

[1924] Input: Sales history, inventory status, market trend data

[1925] Output: Optimal selling price and appropriate inventory quantity generated by the AI ​​model

[1926] How it works: The server feeds data into the AI ​​model and performs analysis using TensorFlow or other frameworks.

[1927] Step 10: Displaying results on a dashboard

[1928] The server displays the analysis results of the AI ​​model on a dashboard for businesses so that they can check them.

[1929] Input: Analysis results of the AI ​​model

[1930] Output: Optimal selling price and appropriate inventory quantity displayed on the business dashboard

[1931] Specific operation: The server sends the result data to the dashboard web page so that it can be displayed on the operator's terminal.

[1932] Step 11: Emotion Recognition with the Emotion Engine

[1933] The server uses an emotion engine to recognize the user's emotions based on the user's search history and purchase history.

[1934] Input: User search and purchase history

[1935] Output: User's emotional state

[1936] Specific operation: Analyze the user's activity data using an NLP model to determine their emotional state.

[1937] Step 12: Product Recommendation

[1938] The server recommends relevant products based on the user's emotional state.

[1939] Input: User's emotional state

[1940] Output: A list of recommended products

[1941] Specific operation: The server executes the recommendation algorithm, calculates related products, and displays them on the user's device.

[1942] Step 13: Pricing for Individual Users

[1943] The server integrates user sentiment and sales history data to determine optimal pricing for individual users.

[1944] Input: User sentiment and sales history data

[1945] Output: Special pricing set for individual users

[1946] Specific operation: The server sets a special price and displays it on the user's terminal as "Special price for you."

[1947] Through these steps, the system can integrate and manage sales data from brick-and-mortar and online stores, and utilize user emotions to provide personalized services, significantly improving the efficiency of marketing strategies and sales management.

[1948] (Application example 2)

[1949] 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."

[1950] In today's retail industry, there is a demand for integrating online and offline sales data and utilizing it effectively. However, rather than simply integrating data, it is expected that recognizing user emotions and providing personalized services will further increase purchasing motivation. Conventional systems have had difficulty analyzing user emotions to recommend products or set individual prices. Therefore, the present invention aims to provide a sales data management system with emotion recognition functionality and improve the user's purchasing experience.

[1951] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data of real stores, means for acquiring online sales performance data, means for converting the sales data of the real stores and the online sales performance data into a common data format, means for detecting and correcting duplicate data and missing data, means for storing the ...

Claims

1. A means of obtaining sales data from real stores, a means for obtaining online sales performance data; means for converting the sales data of the real store and the online sales performance data into a common data format; means for detecting and correcting duplicate and missing data; means for storing the converted data in a database; A means for a user to search for a product and obtain price information of real stores and online stores from the database; The system includes means for displaying the acquired price information on a user terminal.

2. A means of inputting sales history, inventory status, and market trend data into the AI ​​model; A means for calculating an appropriate selling price and an appropriate inventory quantity using the AI ​​model; The system of claim 1 , further comprising means for displaying the calculation results on a business dashboard.

3. The system according to claim 1 , further comprising a scheduling means for periodically acquiring the sales data of the brick-and-mortar store and the online sales performance data.

Images