system

Abstract

Provide a system. 【Solution means】 Data management means for e-commerce transactions, Data input means for registering merchandise information, Database means for unified management of sales performance and inventory information, Calculation means for distributing initial products by store based on the aggregated data, Artificial intelligence means for analyzing the sales situation in real time and proposing inventory replenishment, Predictive data analysis means for revising the replenishment proposal considering external data, Product development support means for proposing specifications for new merchandise, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional merchandise management systems, it has been difficult to individually analyze different sales results and inventory status for each store and achieve efficient inventory replenishment. In addition, developing proposals for new products based on consumer trends requires accurate analysis of data and prompt response, which has required a great deal of labor and time. Therefore, there is an increasing demand for a system that can perform rapid and accurate inventory management and new product proposals.

Means for Solving the Problems

[0005] This invention centers on a data management system for e-commerce, comprising a data input system for registering product information and a database system for centralizing sales performance and inventory information. This allows for the use of artificial intelligence to analyze sales status in real time and propose inventory replenishment. Furthermore, by including a predictive data analysis system that revises replenishment proposals considering external data and a product development support system for proposing specifications for new products, the invention achieves centralized and efficient inventory management and rapid proposal of new products.

[0006] "Electronic commerce" is a form of transaction in which goods and services are bought and sold via computer networks.

[0007] A "data management system" is a part of a system that has the function of efficiently collecting, storing, and processing product information and transaction data, and providing it as needed.

[0008] "Product information" refers to basic data related to a product or service, including attribute information such as name, price, inventory level, and category.

[0009] "Data input means" refers to interfaces or devices used to input data such as product information into a system.

[0010] "Sales performance" refers to data that shows the results of sales activities over a specific period, and includes indicators such as sales revenue and sales volume.

[0011] A "database" refers to a structure or system that centrally stores data, enabling efficient searching and persistent preservation.

[0012] A "computational means" refers to a system or technology that processes data using a specific computational algorithm or procedure and derives a result.

[0013] "Artificial intelligence tools" refer to a part of a system that uses machine learning and other AI technologies to analyze data and make predictions and suggestions.

[0014] A "predictive data analysis tool" is a system function that implements an analytical method to predict future trends based on past data and external factors.

[0015] "Product development support tools" refer to technologies and algorithms that support the process of developing the specifications and features of new products. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the 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.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0030] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The automated ordering system of this invention is designed to efficiently manage data for e-commerce. This system automates the entire process, from registering product information and analyzing sales performance to inventory management and new product proposals, as an automated workflow. Various components of this system work together to comprehensively support store operations, inventory management, and product development.

[0038] The server plays a central role, centrally managing product information and sales data in a database. Product information is registered on the server through data entry methods, and this information, along with sales performance data, is stored in the database. This allows users to check product inventory and sales status in real time.

[0039] For example, when a user registers a new product, the server uses this information to calculate the initial allocation for each store and place the inventory appropriately. The administrator is notified of this calculation result via a terminal, and the administrator can review and correct it as needed.

[0040] The AI ​​agent automatically generates the optimal inventory replenishment plan by analyzing sales performance and external data (such as weather and event information). Users review this replenishment plan, make adjustments as needed, and then place an order based on the finalized details.

[0041] Furthermore, the AI ​​agent analyzes sales trends of similar products and proposes specifications and designs for new products. Based on these proposals, the server provides feedback to the manufacturer, supporting the development of new products.

[0042] This system aims to improve the efficiency of store operations and maximize sales by optimizing inventory and providing products that meet consumer demand. Specifically, for example, when rising temperatures are predicted during the summer, the AI ​​will suggest replenishing stock with more cooling clothing, enabling a rapid response to the market.

[0043] The above describes the embodiments for carrying out the present invention, and this system is expected to contribute to the overall efficiency of merchandise management operations.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user uses a terminal to enter product information (product name, category, price, initial stock quantity, etc.) on a data entry screen. The server receives this data and saves the registered product information to a database.

[0047] Step 2:

[0048] Users configure product classification and inventory turnover criteria based on sales policies and product characteristics through the management screen. The server receives the configured criteria and updates the database settings.

[0049] Step 3:

[0050] The server uses an AI agent to calculate the initial allocation amount for each store and e-commerce site based on registered product information and past sales data. The calculated allocation amount is notified to the terminal and displayed to the user.

[0051] Step 4:

[0052] The POS system transmits sales information and inventory status from each store to the server in real time. The server receives this information and updates the database. This ensures that the latest sales and inventory information is always stored in the database.

[0053] Step 5:

[0054] The AI ​​agent analyzes sales data and inventory information stored on the server to generate an optimal inventory replenishment plan. The generated replenishment plan is displayed to the user via their terminal, which they can review and adjust if necessary.

[0055] Step 6:

[0056] After the user approves the replenishment plan, the server uses the confirmed information to process the order. This ensures that the specified goods are replenished within the supply chain.

[0057] Step 7:

[0058] The AI ​​agent analyzes sales data and market trends to propose specifications and designs for new products. The proposed new product information is provided to manufacturers via a server, accelerating the development of new products.

[0059] The above outlines the specific processing flow within this system. Through these steps, efficient inventory management and product provision that meets consumer supply and demand are achieved.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Traditional sales management systems faced challenges in efficiently handling a wide range of tasks, from registering product information and collecting sales data to inventory management and proposing new product development. Furthermore, data management and analysis were often performed manually, hindering rapid decision-making. Additionally, the lack of optimization for inventory replenishment, taking external factors into account, frequently resulted in insufficient response to demand.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes data management means for managing information related to commercial transactions, data input means for registering product information, and database means for integrating and managing sales performance and inventory information of products. This enables the automation of product management and rapid and accurate data-driven decision-making.

[0065] "Commercial transactions" refer to a series of trading activities involving the buying and selling of goods and services.

[0066] "Data management means" refers to technical means for effectively collecting, storing, and processing information, enabling access to and use of that data as needed.

[0067] "Data input means" refers to the interface or tools that users use to input information into the system, and in this system, it is used for registering item information.

[0068] A "database" is a system or technology that centrally stores and manages multiple pieces of information, enabling efficient searching and editing.

[0069] "Computational means" refers to technologies for automatically performing data analysis and calculations, specifically used for product distribution.

[0070] "Artificial intelligence tools" refer to technologies that use machine learning and data analysis techniques to extract insights from data and make judgments and suggestions.

[0071] "Predictive data analysis methods" are analytical techniques used to predict future events and outcomes based on past data and external information.

[0072] "Product development support tools" are technologies that analyze sales data and other information to support the development process in order to propose specifications and designs for new products.

[0073] "Display means" refers to a device or method for visually presenting system output information to a user.

[0074] This invention provides a system for effectively managing and utilizing information related to commercial transactions. The server plays a role in streamlining store operations and sales strategies by comprehensively managing product information and analyzing sales performance and inventory data in real time.

[0075] Specifically, users register product information on the server using a data entry system. This information is centrally managed in the server's database and used together with sales performance and inventory data. Based on this data, the server utilizes AI technology to automatically generate inventory replenishment plans. It also considers external data such as weather and event information to propose the optimal sales strategy according to the time of year and circumstances.

[0076] By using an AI agent, the system can propose specifications and designs for new products based on sales trends and provide rapid feedback to manufacturers. This enables inventory optimization and product supply tailored to demand, contributing to maximizing sales.

[0077] For example, if a user registers new summer clothing items using their device, the server analyzes this information using AI and, considering the predicted increase in demand due to rising temperatures, suggests a plan to replenish inventory of cooling-material clothing. This allows for a swift response to the market.

[0078] An example of a prompt to be input into the generating AI model is, "Generate the optimal inventory replenishment plan based on sales performance and weather forecasts." This prompt allows the system to quickly provide the most suitable suggestion to the user.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] Users input item information using a terminal. This data includes the product name, category, price, and quantity. Once the user has finished entering this information, they send it to the server via the data entry system. The server stores the received item information in a database, enabling centralized information management. Accurate data entry is required because the entered information will be used for subsequent analysis.

[0082] Step 2:

[0083] The server periodically retrieves sales performance data and inventory information from the database. This includes the number of units sold and inventory status of each product. Based on the retrieved data, the server uses a generative AI model to analyze the data in real time. Specific data processing includes sales trend analysis and demand forecasting. The results of this analysis are then used in the next step.

[0084] Step 3:

[0085] The server uses an AI agent to generate an optimal inventory replenishment plan based on the analysis results. This process also takes into account external data such as weather and event information. The generated replenishment plan is output as product name and recommended replenishment quantity. The server distributes this information to terminals and presents it to the user. Specifically, this step involves the automatic creation of a replenishment plan based on sales forecasts.

[0086] Step 4:

[0087] Users review the replenishment plan presented on their terminal and adjust it as needed. This adjustment includes changes to accommodate unexpected sales or changes in economic conditions. After adjustment, users send the finalized replenishment plan to the server. The server receives this information and processes the order based on its contents. User-initiated adjustments increase the flexibility of inventory management.

[0088] Step 5:

[0089] The AI ​​agent analyzes sales trends of similar products based on sales data and proposes specifications and designs for new products. The server outputs a report detailing these proposals for feedback to the manufacturer. This report serves as foundational data to support new product development and is useful for the manufacturer's development strategy.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] In modern e-commerce, inventory management and sales strategy optimization are critical challenges. In particular, responding quickly to fluctuations in product demand and ensuring appropriate replenishment is essential, but this requires complex data analysis and forecasting, which is difficult to do manually. Therefore, there is a need for systems that support efficient and accurate inventory management and product replenishment strategies.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes data management means for e-commerce, data input means for registering product information, and database means for centrally managing sales performance and inventory information. This enables the prediction of fluctuations in product demand, automation of inventory management and product replenishment, and efficient store operations.

[0095] "Data management means for electronic commerce" refers to methods and devices for effectively managing product information and sales data in commercial transactions conducted over the internet.

[0096] "Data input means" refers to interfaces or methods for inputting necessary data, such as product information and sales performance, into a system.

[0097] A "database means" is a technology or device for centrally storing multiple pieces of information and performing searches and analyses as needed.

[0098] A "computational tool" is a logical method or system used to perform necessary calculations based on aggregated data and derive specific instructions or suggestions.

[0099] "Artificial intelligence means" refers to technologies that allow machines to mimic human intellectual activity, analyze sales data, and suggest inventory replenishment.

[0100] "Predictive data analysis methods" are analytical techniques that use external data to predict future trends and demand, and to make appropriate recommendations.

[0101] "Product development support means" refers to technologies or processes for proposing specifications for new products and supporting product planning and design.

[0102] A "smartphone application" refers to software that supports users in efficiently replenishing products by performing demand forecasting and inventory management on a portable device.

[0103] The system for realizing this invention consists of multiple hardware and software components. The server functions as the core for managing data for e-commerce, centrally managing sales performance and inventory information in a database. The database is operated scalably using the AWS® cloud and efficiently processes large amounts of data using DynamoDB.

[0104] The device provides users with real-time inventory information and AI-powered sales forecasts through a smartphone application. This application is developed using React Native, enabling it to run on a variety of platforms.

[0105] The AI-generated inventory replenishment suggestions are generated by a model utilizing TENSORFLOW®. The server uses a predictive data analysis tool developed in Python to acquire external data such as weather information and analyze sales trends based on that data. During this process, sales performance data is aggregated and analyzed using Python scripts.

[0106] Users can review suggested replenishment plans through a smartphone application and make adjustments as needed. In this way, intuitive use of AI-generated data-driven insights can lead to more efficient inventory management and maximized sales opportunities.

[0107] A concrete example would be a user replenishing their stock of sunscreen products in preparation for sunny weather over the weekend. In this scenario, the AI ​​predicts demand based on past sales data and weather forecasts, and notifies the user with a prompt message such as, "Based on the weather this weekend, what products are expected to be in high demand?" By responding to this prompt, the user can refer to the suggestions and replenish their stock without missing a sales opportunity.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server registers product information and sales performance data into a database. This involves a process that efficiently stores data using AWS DynamoDB. The input is product information and sales performance data, and the output is the updated database.

[0111] Step 2:

[0112] The device makes API calls to allow the AI ​​agent to collect external data such as weather forecasts and event information. This data is used as input for a demand forecasting model. The input is data obtained from external APIs, and the output is the analysis result from the AI ​​agent.

[0113] Step 3:

[0114] The server uses TensorFlow to run an AI model and forecast demand for the product. Sales data and external data are input to the model, and a demand forecast value is generated as output. This forecast value serves as the basis for inventory replenishment plans.

[0115] Step 4:

[0116] The terminal receives inventory replenishment proposals from the server and notifies the user via their smartphone. The user reviews this notification and, if necessary, makes adjustments according to the proposed replenishment plan. The input is the inventory replenishment proposal from the server, and the output is the notification to the user.

[0117] Step 5:

[0118] Users review, approve, or modify inventory replenishment proposals through the application. This ensures that user decisions are reflected in inventory management. The input is the proposed replenishment plan, and the output is the final replenishment plan based on the user's decision.

[0119] Step 6:

[0120] The server automates the actual ordering process based on the approved replenishment plan and sends the order information to the supplier. The input here is the replenishment plan approved by the user, and the output is the order information sent to the supplier.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention is an automated ordering system that combines an emotion engine to enhance data management in e-commerce. This system highly automates the registration of product information, management of sales performance, optimization of inventory, and proposal of new products, and also utilizes user emotion data.

[0123] The server first receives product information through data entry methods and centrally stores it in a database. Users input product information via terminals and then perform the necessary settings based on sales policies. This ensures a smooth initial product launch.

[0124] Next, the AI ​​agent analyzes sales data and generates an optimal inventory replenishment plan. Based on this data, the server creates a replenishment proposal tailored to consumer trends and seasonal fluctuations, and presents it to the user via the terminal. The user reviews the proposal and approves or modifies it as needed.

[0125] Furthermore, this system incorporates an emotion engine that extracts emotional data from user feedback and reviews. This emotional data is analyzed on a server and reflected in sales strategies and new product proposals. For example, if user reviews show a high proportion of positive emotions, a strategy to promote related products will be considered.

[0126] As a concrete example, consider a product whose demand increases due to climate change. The emotion engine analyzes user emotions regarding interest and satisfaction, and based on this, an AI agent adjusts replenishment plans. This process facilitates appropriate inventory placement for best-selling products, thereby maximizing sales.

[0127] Embodiments of the present invention enable efficient inventory management and marketing strategies that reflect consumer needs. This method is expected to allow companies to respond more quickly to market fluctuations and contribute to improved customer satisfaction.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The user uses a terminal to enter product information on a data entry screen. This includes basic information such as product name, category, price, and initial stock quantity. The server receives this information and records it in the database.

[0131] Step 2:

[0132] The server uses an AI agent to calculate the initial allocation to each store based on registered product information and sales performance data. The calculated allocation amount is notified to the user's terminal, and the user confirms the details.

[0133] Step 3:

[0134] After sales begin, the POS system transmits sales data and inventory status to the server in real time. The server retrieves this data and updates the database. This ensures that accurate sales figures are always maintained.

[0135] Step 4:

[0136] The AI ​​agent analyzes updated sales data and inventory information to generate optimal inventory replenishment plans. The server sends these plans to the user's terminal, where the user reviews, approves, or modifies the suggestions.

[0137] Step 5:

[0138] When analyzing sales data and user reviews, the emotion engine analyzes user feedback and extracts emotional data. Based on this emotional data, the server adapts sales strategies and new product suggestions.

[0139] Step 6:

[0140] Users develop promotional and inventory strategies that take into account insights gained from the emotion engine. This information is shared via a server and used to develop specifications and launch plans for new products.

[0141] Step 7:

[0142] The server provides feedback to manufacturers with new product suggestions and improvement ideas based on all analysis results, including emotional data. This process ensures that products are developed in line with consumer demand and preferences.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0145] In e-commerce, it is necessary to efficiently manage sales data, inventory data, and consumer feedback, and to respond quickly to market fluctuations. However, traditional systems have the problem of difficulty in integrating and analyzing this data to formulate optimal sales strategies. In particular, there is a need for flexible inventory replenishment and new product recommendations that utilize consumer sentiment data, but there is a lack of means to effectively implement this.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes information management means, data input means, and intelligent processing means. This enables integrated analysis of sales data and consumer sentiment data, allowing for effective inventory management and market adaptation.

[0148] "Information management methods" refer to techniques for centrally collecting and managing sales performance and inventory information in e-commerce.

[0149] "Data entry method" refers to a method of entering product information in electronic format and transmitting it to a system.

[0150] "Calculation means" refers to algorithms or calculation systems used to distribute merchandise to each store based on aggregated information.

[0151] "Intelligent processing means" refers to a method that uses artificial intelligence technology to analyze sales conditions and propose inventory replenishment.

[0152] A "predictive information analysis tool" is an analytical tool for optimizing inventory replenishment suggestions based on external data.

[0153] A "product development support system" is an information processing system for proposing specifications for new products.

[0154] "Emotional analysis methods" refer to technologies that analyze users' emotional data and utilize it in marketing strategies.

[0155] "Integration methods" refer to the process of analyzing multiple data sets using generative AI models to optimize strategies.

[0156] This invention is a system that combines the latest intelligent processing technology with sentiment analysis to enhance data processing and inventory management in e-commerce. The implementation method is described in detail below.

[0157] Hardware and software configuration

[0158] The server serves as the central hub for data management, utilizing database management systems such as MySQL® and PostgreSQL as means of information management. This allows for centralized management of sales performance and inventory information.

[0159] The terminal functions as a data entry device for users to input product information. At this stage, the terminal sends data to the server using a web browser or mobile application.

[0160] The server uses machine learning frameworks such as TensorFlow and PyTorch as intelligent processing tools. It uses these frameworks to analyze sales data in real time and generate appropriate inventory replenishment suggestions.

[0161] The sentiment analysis method analyzes user feedback using natural language processing (NLP) techniques. BERT and GPT are utilized as generative AI models.

[0162] In this integration system, the server combines sales data and user sentiment data to optimize sales strategies. This involves an AI agent using a generated AI model to handle data analysis and strategy formulation.

[0163] Specific examples and the use of prompt statements

[0164] For example, for products whose demand increases due to climate change, an AI agent forecasts demand and adjusts inventory replenishment plans based on positive feedback obtained from sentiment analysis. Through this process, the system enables effective inventory placement in line with market trends.

[0165] An example of a prompt from a generating AI model is, "Analyze purchase history data from the past three months and propose a promotional strategy for popular products and related products." This prompt leads to the development of a strategy centered on products that interest the user.

[0166] Embodiments of the present invention provide concrete measures to quickly respond to market fluctuations and enhance customer satisfaction through the use of advanced data analysis and emotional feedback.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The user uses a terminal to input product information into a data entry system. This input includes product name, category, price, and stock quantity. This data is immediately sent to the server. The server stores the received product information in a database. Here, information management systems are used to check the integrity of the data and ensure reliable storage.

[0170] Step 2:

[0171] The server periodically collects sales performance data. Input data includes purchase date and time, sales quantity, and sales location. The server stores this data in a database in real time. The collected data is then passed to an AI agent using intelligent processing tools. The AI ​​agent analyzes sales trends and generates an inventory replenishment plan. The output is the proposed replenishment plan.

[0172] Step 3:

[0173] The server sends inventory replenishment proposals generated by the AI ​​agent to the user via the terminal. The user reviews the proposals and makes modifications as needed. Specifically, the proposals are modified and approved based on the user's actions. The server then records the updated replenishment proposals back into the database.

[0174] Step 4:

[0175] The server analyzes user feedback and reviews using sentiment analysis tools. Input data consists of text-based reviews and evaluation comments. Sentimental attributes are extracted using generative AI models (e.g., BERT or GPT). The output is presented as positive or negative sentiment data, which is used in product promotion strategies.

[0176] Step 5:

[0177] The server combines sales data and sentiment data through integration methods to formulate a comprehensive sales strategy. Inputs include historical sales performance and user sentiment analysis data. Generative AI models facilitate smooth data analysis and strategic decision-making. Outputs include timely promotional plans and inventory placement proposals, enabling companies to respond quickly to market trends.

[0178] (Application Example 2)

[0179] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0180] In e-commerce, inventory management and product recommendations were often conducted without considering user preferences or emotions, resulting in insufficient improvements in consumer satisfaction and maximization of inventory efficiency. Furthermore, a lack of dynamic and user-optimized information delivery led to inefficient sales promotion. To address these issues, it is necessary to utilize user sentiment data to improve personalized product recommendations and inventory management.

[0181] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0182] In this invention, the server includes information management means for e-commerce, information input means for registering product information, and information storage means for aggregating and managing sales performance and inventory information. This enables optimal product recommendations and efficient inventory replenishment based on user sentiment data.

[0183] 1. "Information management system for e-commerce" refers to a mechanism for centrally managing and processing information related to goods, sales, and inventory in e-commerce.

[0184] 2. "Information input means for registering product information" refers to tools or interfaces for registering detailed information about a product into a system.

[0185] 3. "Information storage means for aggregating and managing sales performance and inventory information" refers to a database mechanism that centrally stores past sales history and current inventory status, making them accessible as needed.

[0186] 4. A "computational means" is a computational mechanism for calculating efficient inventory allocation and replenishment based on e-commerce data.

[0187] 5. "Artificial intelligence means" refers to a system that uses AI technology to analyze sales data and external factors and generate optimal inventory replenishment and sales strategies.

[0188] 6. A "predictive information analysis tool" is an analytical mechanism that takes external information into consideration to predict future sales trends and inventory needs.

[0189] 7. A "new product specification proposal mechanism" is a support system for proposing the specifications and features of a new product to the development team.

[0190] 8. "Sentiment analysis methods" refer to technologies for extracting and analyzing emotional data from user reviews and feedback.

[0191] 9. A "dynamic display means" is a mechanism for displaying optimal product suggestions and information in real time based on user behavior and emotional data.

[0192] This invention provides a system that streamlines personalized product recommendations and inventory management in e-commerce. The server serves as the central hub of this system, handling information management, analysis, and display. Specifically, the server utilizes cloud services such as Google Cloud to aggregate and manage product information and sales performance. A relational database such as MySQL is recommended for database management.

[0193] When a user enters product information via a terminal, this information is sent to a server and processed by the information input method. Based on this information, the server uses an AI model (for example, a deep learning model using TensorFlow) to analyze sales data and generate optimal inventory replenishment and product recommendations. For sentiment analysis, the Google Cloud Natural Language API is used to extract user sentiment data based on reviews and feedback.

[0194] Based on the analysis of emotional data, the server provides real-time product recommendations tailored to each user's preferences. Dynamic display methods are used to show relevant information on smartphone or computer screens.

[0195] For example, if a user has posted multiple positive reviews on a particular genre, the server has a function that suggests related new products based on that information. This allows users to quickly find products that meet their individual needs, improving the purchasing experience. By inputting prompt sentences like the following into the generating AI model, more precise data analysis becomes possible.

[0196] Example prompt: "Analyze user reviews for sentiment and combine it with current weather patterns to suggest recommended products."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server receives product information and sales performance data from the user's terminal. Input data includes product ID, sales quantity, and inventory status. The server stores this data in a database, preparing it for use in sales analysis. This data is stored in a MySQL database via an information storage system.

[0200] Step 2:

[0201] The server inputs stored product information and sales data into an AI model to predict inventory replenishment. TensorFlow is used to perform data calculations that take into account past sales trends and seasonal fluctuations. As a result, the system outputs how much of each product should be replenished.

[0202] Step 3:

[0203] The server collects product reviews and feedback submitted by users through their devices. This text data is then analyzed for sentiment using the Google Cloud Natural Language API to extract positive or negative sentiment data. The input for this analysis is the review text, and the output is a sentiment score.

[0204] Step 4:

[0205] The server selects products suitable for the user based on sentiment scores and generates dynamic product recommendations. This process utilizes a generative AI model; for example, by inputting a prompt such as, "Analyze the sentiment from user reviews and suggest recommended products in combination with current weather patterns," the AI ​​selects the optimal set of products. A recommended product list is then generated as output.

[0206] Step 5:

[0207] The terminal displays a list of recommended products received from the server in its user interface. Personalized suggested products and promotions are displayed on the screen in real time, and users can view detailed information by clicking on them. Dynamic display functionality is used in this step to provide consistent visual feedback to the user as output.

[0208] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0224] The automated ordering system of this invention is designed to efficiently manage data for e-commerce. This system automates the entire process, from registering product information and analyzing sales performance to inventory management and new product proposals, as an automated workflow. Various components of this system work together to comprehensively support store operations, inventory management, and product development.

[0225] The server plays a central role, centrally managing product information and sales data in a database. Product information is registered on the server through data entry methods, and this information, along with sales performance data, is stored in the database. This allows users to check product inventory and sales status in real time.

[0226] For example, when a user registers a new product, the server uses this information to calculate the initial allocation for each store and place the inventory appropriately. The administrator is notified of this calculation result via a terminal, and the administrator can review and correct it as needed.

[0227] The AI ​​agent automatically generates the optimal inventory replenishment plan by analyzing sales performance and external data (such as weather and event information). Users review this replenishment plan, make adjustments as needed, and then place an order based on the finalized details.

[0228] Furthermore, the AI ​​agent analyzes sales trends of similar products and proposes specifications and designs for new products. Based on these proposals, the server provides feedback to the manufacturer, supporting the development of new products.

[0229] This system aims to improve the efficiency of store operations and maximize sales by optimizing inventory and providing products that meet consumer demand. Specifically, for example, when rising temperatures are predicted during the summer, the AI ​​will suggest replenishing stock with more cooling clothing, enabling a rapid response to the market.

[0230] The above describes the embodiments for carrying out the present invention, and this system is expected to contribute to the overall efficiency of merchandise management operations.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The user uses a terminal to enter product information (product name, category, price, initial stock quantity, etc.) on a data entry screen. The server receives this data and saves the registered product information to a database.

[0234] Step 2:

[0235] Users configure product classification and inventory turnover criteria based on sales policies and product characteristics through the management screen. The server receives the configured criteria and updates the database settings.

[0236] Step 3:

[0237] The server uses an AI agent to calculate the initial allocation amount for each store and e-commerce site based on registered product information and past sales data. The calculated allocation amount is notified to the terminal and displayed to the user.

[0238] Step 4:

[0239] The POS system transmits sales information and inventory status from each store to the server in real time. The server receives this information and updates the database. This ensures that the latest sales and inventory information is always stored in the database.

[0240] Step 5:

[0241] The AI ​​agent analyzes sales data and inventory information stored on the server to generate an optimal inventory replenishment plan. The generated replenishment plan is displayed to the user via their terminal, which they can review and adjust if necessary.

[0242] Step 6:

[0243] After the user approves the replenishment plan, the server uses the confirmed information to process the order. This ensures that the specified goods are replenished within the supply chain.

[0244] Step 7:

[0245] The AI ​​agent analyzes sales data and market trends to propose specifications and designs for new products. The proposed new product information is provided to manufacturers via a server, accelerating the development of new products.

[0246] The above outlines the specific processing flow within this system. Through these steps, efficient inventory management and product provision that meets consumer supply and demand are achieved.

[0247] (Example 1)

[0248] Next, we will describe Example 1. 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."

[0249] Traditional sales management systems faced challenges in efficiently handling a wide range of tasks, from registering product information and collecting sales data to inventory management and proposing new product development. Furthermore, data management and analysis were often performed manually, hindering rapid decision-making. Additionally, the lack of optimization for inventory replenishment, taking external factors into account, frequently resulted in insufficient response to demand.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes data management means for managing information related to commercial transactions, data input means for registering product information, and database means for integrating and managing sales performance and inventory information of products. This enables the automation of product management and rapid and accurate data-driven decision-making.

[0252] "Commercial transactions" refer to a series of trading activities involving the buying and selling of goods and services.

[0253] "Data management means" refers to technical means for effectively collecting, storing, and processing information, enabling access to and use of that data as needed.

[0254] "Data input means" refers to the interface or tools that users use to input information into the system, and in this system, it is used for registering item information.

[0255] A "database" is a system or technology that centrally stores and manages multiple pieces of information, enabling efficient searching and editing.

[0256] "Computational means" refers to technologies for automatically performing data analysis and calculations, specifically used for product distribution.

[0257] "Artificial intelligence tools" refer to technologies that use machine learning and data analysis techniques to extract insights from data and make judgments and suggestions.

[0258] "Predictive data analysis methods" are analytical techniques used to predict future events and outcomes based on past data and external information.

[0259] "Product development support tools" are technologies that analyze sales data and other information to support the development process in order to propose specifications and designs for new products.

[0260] "Display means" refers to a device or method for visually presenting system output information to a user.

[0261] This invention provides a system for effectively managing and utilizing information related to commercial transactions. The server plays a role in streamlining store operations and sales strategies by comprehensively managing product information and analyzing sales performance and inventory data in real time.

[0262] Specifically, users register product information on the server using a data entry system. This information is centrally managed in the server's database and used together with sales performance and inventory data. Based on this data, the server utilizes AI technology to automatically generate inventory replenishment plans. It also considers external data such as weather and event information to propose the optimal sales strategy according to the time of year and circumstances.

[0263] By using an AI agent, the system can propose specifications and designs for new products based on sales trends and provide rapid feedback to manufacturers. This enables inventory optimization and product supply tailored to demand, contributing to maximizing sales.

[0264] For example, if a user registers new summer clothing items using their device, the server analyzes this information using AI and, considering the predicted increase in demand due to rising temperatures, suggests a plan to replenish inventory of cooling-material clothing. This allows for a swift response to the market.

[0265] An example of a prompt to be input into the generating AI model is, "Generate the optimal inventory replenishment plan based on sales performance and weather forecasts." This prompt allows the system to quickly provide the most suitable suggestion to the user.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] Users input item information using a terminal. This data includes the product name, category, price, and quantity. Once the user has finished entering this information, they send it to the server via the data entry system. The server stores the received item information in a database, enabling centralized information management. Accurate data entry is required because the entered information will be used for subsequent analysis.

[0269] Step 2:

[0270] The server periodically retrieves sales performance data and inventory information from the database. This includes the number of units sold and inventory status of each product. Based on the retrieved data, the server uses a generative AI model to analyze the data in real time. Specific data processing includes sales trend analysis and demand forecasting. The results of this analysis are then used in the next step.

[0271] Step 3:

[0272] The server uses an AI agent to generate an optimal inventory replenishment plan based on the analysis results. This process also takes into account external data such as weather and event information. The generated replenishment plan is output as product name and recommended replenishment quantity. The server distributes this information to terminals and presents it to the user. Specifically, this step involves the automatic creation of a replenishment plan based on sales forecasts.

[0273] Step 4:

[0274] Users review the replenishment plan presented on their terminal and adjust it as needed. This adjustment includes changes to accommodate unexpected sales or changes in economic conditions. After adjustment, users send the finalized replenishment plan to the server. The server receives this information and processes the order based on its contents. User-initiated adjustments increase the flexibility of inventory management.

[0275] Step 5:

[0276] The AI ​​agent analyzes sales trends of similar products based on sales data and proposes specifications and designs for new products. The server outputs a report detailing these proposals for feedback to the manufacturer. This report serves as foundational data to support new product development and is useful for the manufacturer's development strategy.

[0277] (Application Example 1)

[0278] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0279] In modern e-commerce, inventory management and optimization of sales strategies are important issues. In particular, it is required to quickly respond to fluctuations in product demand and perform appropriate product replenishment, but this requires complex data analysis and prediction, which is difficult to do manually. For this reason, a system that supports efficient and accurate inventory management and product replenishment strategies is required.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0281] In this invention, the server includes data management means for e-commerce, data input means for registering merchandise information, and database means for unified management of sales results and inventory information. Thereby, fluctuations in product demand can be predicted, inventory management and product replenishment can be automated, and efficient store operation becomes possible.

[0282] The "data management means for e-commerce" is a method and apparatus for effectively managing merchandise information and sales data in commercial transactions via the Internet.

[0283] The "data input means" is an interface or method for inputting necessary data such as merchandise information and sales results into the system.

[0284] The "database means" is a technology or apparatus for storing a plurality of information in a unified manner and performing search and analysis as needed.

[0285] The "calculation means" is a logical method or system for performing necessary calculations based on the aggregated data and deriving specific instructions and proposals.

[0286] The "artificial intelligence means" is a technology in which a machine imitates human intellectual activities and analyzes sales situations to propose inventory replenishment.

[0287] The "prediction data analysis means" is an analysis technology that uses external data to predict future trends and demands and makes appropriate proposals.

[0288] The "product development support means" is a technology or process that proposes specifications for new products and supports product planning and design.

[0289] The "smartphone application means" is software that performs demand prediction and inventory management on portable devices and supports users to efficiently replenish products.

[0290] The system for realizing this invention is composed of a plurality of hardware and software. The server functions as the core for managing data for e-commerce, and centrally manages sales results and inventory information in a database. The database is scalable using AWS cloud and efficiently processes large volumes of data using DynamoDB.

[0291] The terminal provides real-time inventory information and AI-based sales predictions to users through a smartphone application. This application is developed using React Native and enables operation on various platforms.

[0292] The proposal for inventory replenishment by AI is generated by a model using TensorFlow. The server uses prediction data analysis means developed in Python to obtain external data such as weather information and analyzes sales trends based on it. In this process, sales performance data is aggregated and analyzed using Python scripts.

[0293] Users can review suggested replenishment plans through a smartphone application and make adjustments as needed. In this way, intuitive use of AI-generated data-driven insights can lead to more efficient inventory management and maximized sales opportunities.

[0294] A concrete example would be a user replenishing their stock of sunscreen products in preparation for sunny weather over the weekend. In this scenario, the AI ​​predicts demand based on past sales data and weather forecasts, and notifies the user with a prompt message such as, "Based on the weather this weekend, what products are expected to be in high demand?" By responding to this prompt, the user can refer to the suggestions and replenish their stock without missing a sales opportunity.

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The server registers product information and sales performance data into a database. This involves a process that efficiently stores data using AWS DynamoDB. The input is product information and sales performance data, and the output is the updated database.

[0298] Step 2:

[0299] The device makes API calls to allow the AI ​​agent to collect external data such as weather forecasts and event information. This data is used as input for a demand forecasting model. The input is data obtained from external APIs, and the output is the analysis result from the AI ​​agent.

[0300] Step 3:

[0301] The server uses TensorFlow to execute a generative AI model and predict the demand for commercial products. Sales performance data and external data are input into the model, and a demand prediction value is generated as the output. This prediction value serves as the basic data for the inventory replenishment plan.

[0302] Step 4:

[0303] The terminal receives the inventory replenishment plan from the server and notifies the user on the smartphone. The user checks this notification and makes adjustments according to the proposed replenishment plan if necessary. The input is the inventory replenishment plan from the server, and the output is the notification to the user.

[0304] Step 5:

[0305] The user reviews the inventory replenishment plan through the application and approves or modifies it. This reflects the user's decision-making in inventory management. The input is the proposed replenishment plan, and the output is the final replenishment plan based on the user's decision.

[0306] Step 6:

[0307] The server automates the actual order placement based on the approved replenishment plan and sends the order information to the supplier. The input here is the replenishment plan approved by the user, and the output is the order information to the supplier.

[0308] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0309] The present invention is an automatic order placement system that combines an emotion engine to enhance data management in e-commerce. This system highly automates the registration of commercial product information, the management of sales performance, the optimization of inventory, and the proposal of new products, and also utilizes the user's emotion data.

[0310] The server first receives product information through data entry methods and centrally stores it in a database. Users input product information via terminals and then perform the necessary settings based on sales policies. This ensures a smooth initial product launch.

[0311] Next, the AI ​​agent analyzes sales data and generates an optimal inventory replenishment plan. Based on this data, the server creates a replenishment proposal tailored to consumer trends and seasonal fluctuations, and presents it to the user via the terminal. The user reviews the proposal and approves or modifies it as needed.

[0312] Furthermore, this system incorporates an emotion engine that extracts emotional data from user feedback and reviews. This emotional data is analyzed on a server and reflected in sales strategies and new product proposals. For example, if user reviews show a high proportion of positive emotions, a strategy to promote related products will be considered.

[0313] As a concrete example, consider a product whose demand increases due to climate change. The emotion engine analyzes user emotions regarding interest and satisfaction, and based on this, an AI agent adjusts replenishment plans. This process facilitates appropriate inventory placement for best-selling products, thereby maximizing sales.

[0314] Embodiments of the present invention enable efficient inventory management and marketing strategies that reflect consumer needs. This method is expected to allow companies to respond more quickly to market fluctuations and contribute to improved customer satisfaction.

[0315] The following describes the processing flow.

[0316] Step 1:

[0317] The user uses a terminal to enter product information on a data entry screen. This includes basic information such as product name, category, price, and initial stock quantity. The server receives this information and records it in the database.

[0318] Step 2:

[0319] The server uses an AI agent to calculate the initial allocation to each store based on registered product information and sales performance data. The calculated allocation amount is notified to the user's terminal, and the user confirms the details.

[0320] Step 3:

[0321] After sales begin, the POS system transmits sales data and inventory status to the server in real time. The server retrieves this data and updates the database. This ensures that accurate sales figures are always maintained.

[0322] Step 4:

[0323] The AI ​​agent analyzes updated sales data and inventory information to generate optimal inventory replenishment plans. The server sends these plans to the user's terminal, where the user reviews, approves, or modifies the suggestions.

[0324] Step 5:

[0325] When analyzing sales data and user reviews, the emotion engine analyzes user feedback and extracts emotional data. Based on this emotional data, the server adapts sales strategies and new product suggestions.

[0326] Step 6:

[0327] Users develop promotional and inventory strategies that take into account insights gained from the emotion engine. This information is shared via a server and used to develop specifications and launch plans for new products.

[0328] Step 7:

[0329] The server provides feedback to manufacturers with new product suggestions and improvement ideas based on all analysis results, including emotional data. This process ensures that products are developed in line with consumer demand and preferences.

[0330] (Example 2)

[0331] Next, we will describe Example 2. 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".

[0332] In e-commerce, it is necessary to efficiently manage sales data, inventory data, and consumer feedback, and to respond quickly to market fluctuations. However, traditional systems have the problem of difficulty in integrating and analyzing this data to formulate optimal sales strategies. In particular, there is a need for flexible inventory replenishment and new product recommendations that utilize consumer sentiment data, but there is a lack of means to effectively implement this.

[0333] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0334] In this invention, the server includes information management means, data input means, and intelligent processing means. This enables integrated analysis of sales data and consumer sentiment data, allowing for effective inventory management and market adaptation.

[0335] "Information management methods" refer to techniques for centrally collecting and managing sales performance and inventory information in e-commerce.

[0336] "Data entry method" refers to a method of entering product information in electronic format and transmitting it to a system.

[0337] "Calculation means" refers to algorithms or calculation systems used to distribute merchandise to each store based on aggregated information.

[0338] "Intelligent processing means" refers to a method that uses artificial intelligence technology to analyze sales conditions and propose inventory replenishment.

[0339] A "predictive information analysis tool" is an analytical tool for optimizing inventory replenishment suggestions based on external data.

[0340] A "product development support system" is an information processing system for proposing specifications for new products.

[0341] "Emotional analysis methods" refer to technologies that analyze users' emotional data and utilize it in marketing strategies.

[0342] "Integration methods" refer to the process of analyzing multiple data sets using generative AI models to optimize strategies.

[0343] This invention is a system that combines the latest intelligent processing technology with sentiment analysis to enhance data processing and inventory management in e-commerce. The implementation method is described in detail below.

[0344] Hardware and software configuration

[0345] The server serves as the central hub for data management, utilizing database management systems such as MySQL and PostgreSQL for information management. This allows for centralized management of sales performance and inventory information.

[0346] The terminal functions as a data entry device for users to input product information. At this stage, the terminal sends data to the server using a web browser or mobile application.

[0347] The server uses machine learning frameworks such as TensorFlow and PyTorch as intelligent processing tools. It uses these frameworks to analyze sales data in real time and generate appropriate inventory replenishment suggestions.

[0348] The sentiment analysis method analyzes user feedback using natural language processing (NLP) techniques. BERT and GPT are utilized as generative AI models.

[0349] In this integration system, the server combines sales data and user sentiment data to optimize sales strategies. This involves an AI agent using a generated AI model to handle data analysis and strategy formulation.

[0350] Specific examples and the use of prompt statements

[0351] For example, for products whose demand increases due to climate change, an AI agent forecasts demand and adjusts inventory replenishment plans based on positive feedback obtained from sentiment analysis. Through this process, the system enables effective inventory placement in line with market trends.

[0352] An example of a prompt from a generating AI model is, "Analyze purchase history data from the past three months and propose a promotional strategy for popular products and related products." This prompt leads to the development of a strategy centered on products that interest the user.

[0353] Embodiments of the present invention provide concrete measures to quickly respond to market fluctuations and enhance customer satisfaction through the use of advanced data analysis and emotional feedback.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The user uses a terminal to input product information into a data entry system. This input includes product name, category, price, and stock quantity. This data is immediately sent to the server. The server stores the received product information in a database. Here, information management systems are used to check the integrity of the data and ensure reliable storage.

[0357] Step 2:

[0358] The server periodically collects sales performance data. Input data includes purchase date and time, sales quantity, and sales location. The server stores this data in a database in real time. The collected data is then passed to an AI agent using intelligent processing tools. The AI ​​agent analyzes sales trends and generates an inventory replenishment plan. The output is the proposed replenishment plan.

[0359] Step 3:

[0360] The server sends inventory replenishment proposals generated by the AI ​​agent to the user via the terminal. The user reviews the proposals and makes modifications as needed. Specifically, the proposals are modified and approved based on the user's actions. The server then records the updated replenishment proposals back into the database.

[0361] Step 4:

[0362] The server analyzes user feedback and reviews using sentiment analysis tools. Input data consists of text-based reviews and evaluation comments. Sentimental attributes are extracted using generative AI models (e.g., BERT or GPT). The output is presented as positive or negative sentiment data, which is used in product promotion strategies.

[0363] Step 5:

[0364] The server combines sales data and sentiment data through integration methods to formulate a comprehensive sales strategy. Inputs include historical sales performance and user sentiment analysis data. Generative AI models facilitate smooth data analysis and strategic decision-making. Outputs include timely promotional plans and inventory placement proposals, enabling companies to respond quickly to market trends.

[0365] (Application Example 2)

[0366] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0367] In e-commerce, inventory management and product recommendations were often conducted without considering user preferences or emotions, resulting in insufficient improvements in consumer satisfaction and maximization of inventory efficiency. Furthermore, a lack of dynamic and user-optimized information delivery led to inefficient sales promotion. To address these issues, it is necessary to utilize user sentiment data to improve personalized product recommendations and inventory management.

[0368] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0369] In this invention, the server includes information management means for e-commerce, information input means for registering product information, and information storage means for aggregating and managing sales performance and inventory information. This enables optimal product recommendations and efficient inventory replenishment based on user sentiment data.

[0370] 1. "Information management system for e-commerce" refers to a mechanism for centrally managing and processing information related to goods, sales, and inventory in e-commerce.

[0371] 2. "Information input means for registering product information" refers to tools or interfaces for registering detailed information about a product into a system.

[0372] 3. "Information storage means for aggregating and managing sales performance and inventory information" refers to a database mechanism that centrally stores past sales history and current inventory status, making them accessible as needed.

[0373] 4. A "computational means" is a computational mechanism for calculating efficient inventory allocation and replenishment based on e-commerce data.

[0374] 5. "Artificial intelligence means" refers to a system that uses AI technology to analyze sales data and external factors and generate optimal inventory replenishment and sales strategies.

[0375] 6. A "predictive information analysis tool" is an analytical mechanism that takes external information into consideration to predict future sales trends and inventory needs.

[0376] 7. A "new product specification proposal mechanism" is a support system for proposing the specifications and features of a new product to the development team.

[0377] 8. "Sentiment analysis methods" refer to technologies for extracting and analyzing emotional data from user reviews and feedback.

[0378] 9. A "dynamic display means" is a mechanism for displaying optimal product suggestions and information in real time based on user behavior and emotional data.

[0379] This invention provides a system that streamlines personalized product recommendations and inventory management in e-commerce. A server serves as the central hub of this system, responsible for information management, analysis, and display. Specifically, the server utilizes cloud services such as Google Cloud to aggregate and manage product information and sales performance. A relational database such as MySQL is recommended for database management.

[0380] When a user enters product information via a terminal, this information is sent to a server and processed by the information input method. Based on this information, the server uses an AI model (for example, a deep learning model using TensorFlow) to analyze sales data and generate optimal inventory replenishment and product recommendations. For sentiment analysis, the Google Cloud Natural Language API is used to extract user sentiment data based on reviews and feedback.

[0381] Based on the analysis of emotional data, the server provides real-time product recommendations tailored to each user's preferences. Dynamic display methods are used to show relevant information on smartphone or computer screens.

[0382] For example, if a user has posted multiple positive reviews on a particular genre, the server has a function that suggests related new products based on that information. This allows users to quickly find products that meet their individual needs, improving the purchasing experience. By inputting prompt sentences like the following into the generating AI model, more precise data analysis becomes possible.

[0383] Example prompt: "Analyze user reviews for sentiment and combine it with current weather patterns to suggest recommended products."

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server receives product information and sales performance data from the user's terminal. Input data includes product ID, sales quantity, and inventory status. The server stores this data in a database, preparing it for use in sales analysis. This data is stored in a MySQL database via an information storage system.

[0387] Step 2:

[0388] The server inputs stored product information and sales data into an AI model to predict inventory replenishment. TensorFlow is used to perform data calculations that take into account past sales trends and seasonal fluctuations. As a result, the system outputs how much of each product should be replenished.

[0389] Step 3:

[0390] The server collects product reviews and feedback submitted by users through their devices. This text data is then analyzed for sentiment using the Google Cloud Natural Language API to extract positive or negative sentiment data. The input for this analysis is the review text, and the output is a sentiment score.

[0391] Step 4:

[0392] The server selects products suitable for the user based on sentiment scores and generates dynamic product recommendations. This process utilizes a generative AI model; for example, by inputting a prompt such as, "Analyze the sentiment from user reviews and suggest recommended products in combination with current weather patterns," the AI ​​selects the optimal set of products. A recommended product list is then generated as output.

[0393] Step 5:

[0394] The terminal displays a list of recommended products received from the server in its user interface. Personalized suggested products and promotions are displayed on the screen in real time, and users can view detailed information by clicking on them. Dynamic display functionality is used in this step to provide consistent visual feedback to the user as output.

[0395] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0396] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0397] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0398] [Third Embodiment]

[0399] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0400] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0401] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0402] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0403] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0404] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0405] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0406] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0407] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0408] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0409] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0410] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0411] The automated ordering system of this invention is designed to efficiently manage data for e-commerce. This system automates the entire process, from registering product information and analyzing sales performance to inventory management and new product proposals, as an automated workflow. Various components of this system work together to comprehensively support store operations, inventory management, and product development.

[0412] The server plays a central role, centrally managing product information and sales data in a database. Product information is registered on the server through data entry methods, and this information, along with sales performance data, is stored in the database. This allows users to check product inventory and sales status in real time.

[0413] For example, when a user registers a new product, the server uses this information to calculate the initial allocation for each store and place the inventory appropriately. The administrator is notified of this calculation result via a terminal, and the administrator can review and correct it as needed.

[0414] The AI ​​agent automatically generates the optimal inventory replenishment plan by analyzing sales performance and external data (such as weather and event information). Users review this replenishment plan, make adjustments as needed, and then place an order based on the finalized details.

[0415] Furthermore, the AI ​​agent analyzes sales trends of similar products and proposes specifications and designs for new products. Based on these proposals, the server provides feedback to the manufacturer, supporting the development of new products.

[0416] This system aims to improve the efficiency of store operations and maximize sales by optimizing inventory and providing products that meet consumer demand. Specifically, for example, when rising temperatures are predicted during the summer, the AI ​​will suggest replenishing stock with more cooling clothing, enabling a rapid response to the market.

[0417] The above describes the embodiments for carrying out the present invention, and this system is expected to contribute to the overall efficiency of merchandise management operations.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] The user uses a terminal to enter product information (product name, category, price, initial stock quantity, etc.) on a data entry screen. The server receives this data and saves the registered product information to a database.

[0421] Step 2:

[0422] Users configure product classification and inventory turnover criteria based on sales policies and product characteristics through the management screen. The server receives the configured criteria and updates the database settings.

[0423] Step 3:

[0424] The server uses an AI agent to calculate the initial allocation amount for each store and e-commerce site based on registered product information and past sales data. The calculated allocation amount is notified to the terminal and displayed to the user.

[0425] Step 4:

[0426] The POS system transmits sales information and inventory status from each store to the server in real time. The server receives this information and updates the database. This ensures that the latest sales and inventory information is always stored in the database.

[0427] Step 5:

[0428] The AI ​​agent analyzes sales data and inventory information stored on the server to generate an optimal inventory replenishment plan. The generated replenishment plan is displayed to the user via their terminal, which they can review and adjust if necessary.

[0429] Step 6:

[0430] After the user approves the replenishment plan, the server uses the confirmed information to process the order. This ensures that the specified goods are replenished within the supply chain.

[0431] Step 7:

[0432] The AI ​​agent analyzes sales data and market trends to propose specifications and designs for new products. The proposed new product information is provided to manufacturers via a server, accelerating the development of new products.

[0433] The above outlines the specific processing flow within this system. Through these steps, efficient inventory management and product provision that meets consumer supply and demand are achieved.

[0434] (Example 1)

[0435] Next, we will describe Example 1. 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."

[0436] Traditional sales management systems faced challenges in efficiently handling a wide range of tasks, from registering product information and collecting sales data to inventory management and proposing new product development. Furthermore, data management and analysis were often performed manually, hindering rapid decision-making. Additionally, the lack of optimization for inventory replenishment, taking external factors into account, frequently resulted in insufficient response to demand.

[0437] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0438] In this invention, the server includes data management means for managing information related to commercial transactions, data input means for registering product information, and database means for integrating and managing sales performance and inventory information of products. This enables the automation of product management and rapid and accurate data-driven decision-making.

[0439] "Commercial transactions" refer to a series of trading activities involving the buying and selling of goods and services.

[0440] "Data management means" refers to technical means for effectively collecting, storing, and processing information, enabling access to and use of that data as needed.

[0441] "Data input means" refers to the interface or tools that users use to input information into the system, and in this system, it is used for registering item information.

[0442] A "database" is a system or technology that centrally stores and manages multiple pieces of information, enabling efficient searching and editing.

[0443] "Computational means" refers to technologies for automatically performing data analysis and calculations, specifically used for product distribution.

[0444] "Artificial intelligence tools" refer to technologies that use machine learning and data analysis techniques to extract insights from data and make judgments and suggestions.

[0445] "Predictive data analysis methods" are analytical techniques used to predict future events and outcomes based on past data and external information.

[0446] "Product development support tools" are technologies that analyze sales data and other information to support the development process in order to propose specifications and designs for new products.

[0447] "Display means" refers to a device or method for visually presenting system output information to a user.

[0448] This invention provides a system for effectively managing and utilizing information related to commercial transactions. The server plays a role in streamlining store operations and sales strategies by comprehensively managing product information and analyzing sales performance and inventory data in real time.

[0449] Specifically, users register product information on the server using a data entry system. This information is centrally managed in the server's database and used together with sales performance and inventory data. Based on this data, the server utilizes AI technology to automatically generate inventory replenishment plans. It also considers external data such as weather and event information to propose the optimal sales strategy according to the time of year and circumstances.

[0450] By using an AI agent, the system can propose specifications and designs for new products based on sales trends and provide rapid feedback to manufacturers. This enables inventory optimization and product supply tailored to demand, contributing to maximizing sales.

[0451] For example, if a user registers new summer clothing items using their device, the server analyzes this information using AI and, considering the predicted increase in demand due to rising temperatures, suggests a plan to replenish inventory of cooling-material clothing. This allows for a swift response to the market.

[0452] An example of a prompt to be input into the generating AI model is, "Generate the optimal inventory replenishment plan based on sales performance and weather forecasts." This prompt allows the system to quickly provide the most suitable suggestion to the user.

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] Users input item information using a terminal. This data includes the product name, category, price, and quantity. Once the user has finished entering this information, they send it to the server via the data entry system. The server stores the received item information in a database, enabling centralized information management. Accurate data entry is required because the entered information will be used for subsequent analysis.

[0456] Step 2:

[0457] The server periodically retrieves sales performance data and inventory information from the database. This includes the number of units sold and inventory status of each product. Based on the retrieved data, the server uses a generative AI model to analyze the data in real time. Specific data processing includes sales trend analysis and demand forecasting. The results of this analysis are then used in the next step.

[0458] Step 3:

[0459] The server uses an AI agent to generate an optimal inventory replenishment plan based on the analysis results. This process also takes into account external data such as weather and event information. The generated replenishment plan is output as product name and recommended replenishment quantity. The server distributes this information to terminals and presents it to the user. Specifically, this step involves the automatic creation of a replenishment plan based on sales forecasts.

[0460] Step 4:

[0461] Users review the replenishment plan presented on their terminal and adjust it as needed. This adjustment includes changes to accommodate unexpected sales or changes in economic conditions. After adjustment, users send the finalized replenishment plan to the server. The server receives this information and processes the order based on its contents. User-initiated adjustments increase the flexibility of inventory management.

[0462] Step 5:

[0463] The AI ​​agent analyzes sales trends of similar products based on sales data and proposes specifications and designs for new products. The server outputs a report detailing these proposals for feedback to the manufacturer. This report serves as foundational data to support new product development and is useful for the manufacturer's development strategy.

[0464] (Application Example 1)

[0465] Next, we will explain Application Example 1. In the following explanation, 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."

[0466] In modern e-commerce, inventory management and sales strategy optimization are critical challenges. In particular, responding quickly to fluctuations in product demand and ensuring appropriate replenishment is essential, but this requires complex data analysis and forecasting, which is difficult to do manually. Therefore, there is a need for systems that support efficient and accurate inventory management and product replenishment strategies.

[0467] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0468] In this invention, the server includes data management means for e-commerce, data input means for registering product information, and database means for centrally managing sales performance and inventory information. This enables the prediction of fluctuations in product demand, automation of inventory management and product replenishment, and efficient store operations.

[0469] "Data management means for electronic commerce" refers to methods and devices for effectively managing product information and sales data in commercial transactions conducted over the internet.

[0470] "Data input means" refers to interfaces or methods for inputting necessary data, such as product information and sales performance, into a system.

[0471] A "database means" is a technology or device for centrally storing multiple pieces of information and performing searches and analyses as needed.

[0472] A "computational tool" is a logical method or system used to perform necessary calculations based on aggregated data and derive specific instructions or suggestions.

[0473] "Artificial intelligence means" refers to technologies that allow machines to mimic human intellectual activity, analyze sales data, and suggest inventory replenishment.

[0474] "Predictive data analysis methods" are analytical techniques that use external data to predict future trends and demand, and to make appropriate recommendations.

[0475] "Product development support means" refers to technologies or processes for proposing specifications for new products and supporting product planning and design.

[0476] A "smartphone application" refers to software that supports users in efficiently replenishing products by performing demand forecasting and inventory management on a portable device.

[0477] The system for realizing this invention consists of multiple hardware and software components. The server functions as the core for managing data for e-commerce, centrally managing sales performance and inventory information in a database. The database is operated scalably using the AWS cloud and efficiently processes large amounts of data using DynamoDB.

[0478] The device provides users with real-time inventory information and AI-powered sales forecasts through a smartphone application. This application is developed using React Native, enabling it to run on a variety of platforms.

[0479] The AI-generated inventory replenishment suggestions are generated by a model using TensorFlow. The server uses a predictive data analysis tool developed in Python to acquire external data such as weather information and analyze sales trends based on that data. During this process, sales performance data is aggregated and analyzed using Python scripts.

[0480] Users can review suggested replenishment plans through a smartphone application and make adjustments as needed. In this way, intuitive use of AI-generated data-driven insights can lead to more efficient inventory management and maximized sales opportunities.

[0481] A concrete example would be a user replenishing their stock of sunscreen products in preparation for sunny weather over the weekend. In this scenario, the AI ​​predicts demand based on past sales data and weather forecasts, and notifies the user with a prompt message such as, "Based on the weather this weekend, what products are expected to be in high demand?" By responding to this prompt, the user can refer to the suggestions and replenish their stock without missing a sales opportunity.

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The server registers product information and sales performance data into a database. This involves a process that efficiently stores data using AWS DynamoDB. The input is product information and sales performance data, and the output is the updated database.

[0485] Step 2:

[0486] The device makes API calls to allow the AI ​​agent to collect external data such as weather forecasts and event information. This data is used as input for a demand forecasting model. The input is data obtained from external APIs, and the output is the analysis result from the AI ​​agent.

[0487] Step 3:

[0488] The server uses TensorFlow to run an AI model and forecast demand for the product. Sales data and external data are input to the model, and a demand forecast value is generated as output. This forecast value serves as the basis for inventory replenishment plans.

[0489] Step 4:

[0490] The terminal receives inventory replenishment proposals from the server and notifies the user via their smartphone. The user reviews this notification and, if necessary, makes adjustments according to the proposed replenishment plan. The input is the inventory replenishment proposal from the server, and the output is the notification to the user.

[0491] Step 5:

[0492] Users review, approve, or modify inventory replenishment proposals through the application. This ensures that user decisions are reflected in inventory management. The input is the proposed replenishment plan, and the output is the final replenishment plan based on the user's decision.

[0493] Step 6:

[0494] The server automates the actual ordering process based on the approved replenishment plan and sends the order information to the supplier. The input here is the replenishment plan approved by the user, and the output is the order information sent to the supplier.

[0495] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0496] This invention is an automated ordering system that combines an emotion engine to enhance data management in e-commerce. This system highly automates the registration of product information, management of sales performance, optimization of inventory, and proposal of new products, and also utilizes user emotion data.

[0497] The server first receives product information through data entry methods and centrally stores it in a database. Users input product information via terminals and then perform the necessary settings based on sales policies. This ensures a smooth initial product launch.

[0498] Next, the AI ​​agent analyzes sales data and generates an optimal inventory replenishment plan. Based on this data, the server creates a replenishment proposal tailored to consumer trends and seasonal fluctuations, and presents it to the user via the terminal. The user reviews the proposal and approves or modifies it as needed.

[0499] Furthermore, this system incorporates an emotion engine that extracts emotional data from user feedback and reviews. This emotional data is analyzed on a server and reflected in sales strategies and new product proposals. For example, if user reviews show a high proportion of positive emotions, a strategy to promote related products will be considered.

[0500] As a concrete example, consider a product whose demand increases due to climate change. The emotion engine analyzes user emotions regarding interest and satisfaction, and based on this, an AI agent adjusts replenishment plans. This process facilitates appropriate inventory placement for best-selling products, thereby maximizing sales.

[0501] Embodiments of the present invention enable efficient inventory management and marketing strategies that reflect consumer needs. This method is expected to allow companies to respond more quickly to market fluctuations and contribute to improved customer satisfaction.

[0502] The following describes the processing flow.

[0503] Step 1:

[0504] The user uses a terminal to enter product information on a data entry screen. This includes basic information such as product name, category, price, and initial stock quantity. The server receives this information and records it in the database.

[0505] Step 2:

[0506] The server uses an AI agent to calculate the initial allocation to each store based on registered product information and sales performance data. The calculated allocation amount is notified to the user's terminal, and the user confirms the details.

[0507] Step 3:

[0508] After sales begin, the POS system transmits sales data and inventory status to the server in real time. The server retrieves this data and updates the database. This ensures that accurate sales figures are always maintained.

[0509] Step 4:

[0510] The AI ​​agent analyzes updated sales data and inventory information to generate optimal inventory replenishment plans. The server sends these plans to the user's terminal, where the user reviews, approves, or modifies the suggestions.

[0511] Step 5:

[0512] When analyzing sales data and user reviews, the emotion engine analyzes user feedback and extracts emotional data. Based on this emotional data, the server adapts sales strategies and new product suggestions.

[0513] Step 6:

[0514] Users develop promotional and inventory strategies that take into account insights gained from the emotion engine. This information is shared via a server and used to develop specifications and launch plans for new products.

[0515] Step 7:

[0516] The server provides feedback to manufacturers with new product suggestions and improvement ideas based on all analysis results, including emotional data. This process ensures that products are developed in line with consumer demand and preferences.

[0517] (Example 2)

[0518] Next, we will describe Example 2. 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."

[0519] In e-commerce, it is necessary to efficiently manage sales data, inventory data, and consumer feedback, and to respond quickly to market fluctuations. However, traditional systems have the problem of difficulty in integrating and analyzing this data to formulate optimal sales strategies. In particular, there is a need for flexible inventory replenishment and new product recommendations that utilize consumer sentiment data, but there is a lack of means to effectively implement this.

[0520] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0521] In this invention, the server includes information management means, data input means, and intelligent processing means. This enables integrated analysis of sales data and consumer sentiment data, allowing for effective inventory management and market adaptation.

[0522] "Information management methods" refer to techniques for centrally collecting and managing sales performance and inventory information in e-commerce.

[0523] "Data entry method" refers to a method of entering product information in electronic format and transmitting it to a system.

[0524] "Calculation means" refers to algorithms or calculation systems used to distribute merchandise to each store based on aggregated information.

[0525] "Intelligent processing means" refers to a method that uses artificial intelligence technology to analyze sales conditions and propose inventory replenishment.

[0526] A "predictive information analysis tool" is an analytical tool for optimizing inventory replenishment suggestions based on external data.

[0527] A "product development support system" is an information processing system for proposing specifications for new products.

[0528] "Emotional analysis methods" refer to technologies that analyze users' emotional data and utilize it in marketing strategies.

[0529] "Integration methods" refer to the process of analyzing multiple data sets using generative AI models to optimize strategies.

[0530] This invention is a system that combines the latest intelligent processing technology with sentiment analysis to enhance data processing and inventory management in e-commerce. The implementation method is described in detail below.

[0531] Hardware and software configuration

[0532] The server serves as the central hub for data management, utilizing database management systems such as MySQL and PostgreSQL for information management. This allows for centralized management of sales performance and inventory information.

[0533] The terminal functions as a data entry device for users to input product information. At this stage, the terminal sends data to the server using a web browser or mobile application.

[0534] The server uses machine learning frameworks such as TensorFlow and PyTorch as intelligent processing tools. It uses these frameworks to analyze sales data in real time and generate appropriate inventory replenishment suggestions.

[0535] The sentiment analysis method analyzes user feedback using natural language processing (NLP) techniques. BERT and GPT are utilized as generative AI models.

[0536] In this integration system, the server combines sales data and user sentiment data to optimize sales strategies. This involves an AI agent using a generated AI model to handle data analysis and strategy formulation.

[0537] Specific examples and the use of prompt statements

[0538] For example, for products whose demand increases due to climate change, an AI agent forecasts demand and adjusts inventory replenishment plans based on positive feedback obtained from sentiment analysis. Through this process, the system enables effective inventory placement in line with market trends.

[0539] An example of a prompt from a generating AI model is, "Analyze purchase history data from the past three months and propose a promotional strategy for popular products and related products." This prompt leads to the development of a strategy centered on products that interest the user.

[0540] Embodiments of the present invention provide concrete measures to quickly respond to market fluctuations and enhance customer satisfaction through the use of advanced data analysis and emotional feedback.

[0541] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0542] Step 1:

[0543] The user uses a terminal to input product information into a data entry system. This input includes product name, category, price, and stock quantity. This data is immediately sent to the server. The server stores the received product information in a database. Here, information management systems are used to check the integrity of the data and ensure reliable storage.

[0544] Step 2:

[0545] The server periodically collects sales performance data. Input data includes purchase date and time, sales quantity, and sales location. The server stores this data in a database in real time. The collected data is then passed to an AI agent using intelligent processing tools. The AI ​​agent analyzes sales trends and generates an inventory replenishment plan. The output is the proposed replenishment plan.

[0546] Step 3:

[0547] The server sends inventory replenishment proposals generated by the AI ​​agent to the user via the terminal. The user reviews the proposals and makes modifications as needed. Specifically, the proposals are modified and approved based on the user's actions. The server then records the updated replenishment proposals back into the database.

[0548] Step 4:

[0549] The server analyzes user feedback and reviews using sentiment analysis tools. Input data consists of text-based reviews and evaluation comments. Sentimental attributes are extracted using generative AI models (e.g., BERT or GPT). The output is presented as positive or negative sentiment data, which is used in product promotion strategies.

[0550] Step 5:

[0551] The server combines sales data and sentiment data through integration methods to formulate a comprehensive sales strategy. Inputs include historical sales performance and user sentiment analysis data. Generative AI models facilitate smooth data analysis and strategic decision-making. Outputs include timely promotional plans and inventory placement proposals, enabling companies to respond quickly to market trends.

[0552] (Application Example 2)

[0553] Next, we will explain application example 2. In the following explanation, 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."

[0554] In e-commerce, inventory management and product recommendations were often conducted without considering user preferences or emotions, resulting in insufficient improvements in consumer satisfaction and maximization of inventory efficiency. Furthermore, a lack of dynamic and user-optimized information delivery led to inefficient sales promotion. To address these issues, it is necessary to utilize user sentiment data to improve personalized product recommendations and inventory management.

[0555] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0556] In this invention, the server includes information management means for e-commerce, information input means for registering product information, and information storage means for aggregating and managing sales performance and inventory information. This enables optimal product recommendations and efficient inventory replenishment based on user sentiment data.

[0557] 1. "Information management system for e-commerce" refers to a mechanism for centrally managing and processing information related to goods, sales, and inventory in e-commerce.

[0558] 2. "Information input means for registering product information" refers to tools or interfaces for registering detailed information about a product into a system.

[0559] 3. "Information storage means for aggregating and managing sales performance and inventory information" refers to a database mechanism that centrally stores past sales history and current inventory status, making them accessible as needed.

[0560] 4. A "computational means" is a computational mechanism for calculating efficient inventory allocation and replenishment based on e-commerce data.

[0561] 5. "Artificial intelligence means" refers to a system that uses AI technology to analyze sales data and external factors and generate optimal inventory replenishment and sales strategies.

[0562] 6. A "predictive information analysis tool" is an analytical mechanism that takes external information into consideration to predict future sales trends and inventory needs.

[0563] 7. A "new product specification proposal mechanism" is a support system for proposing the specifications and features of a new product to the development team.

[0564] 8. "Sentiment analysis methods" refer to technologies for extracting and analyzing emotional data from user reviews and feedback.

[0565] 9. A "dynamic display means" is a mechanism for displaying optimal product suggestions and information in real time based on user behavior and emotional data.

[0566] This invention provides a system that streamlines personalized product recommendations and inventory management in e-commerce. A server serves as the central hub of this system, responsible for information management, analysis, and display. Specifically, the server utilizes cloud services such as Google Cloud to aggregate and manage product information and sales performance. A relational database such as MySQL is recommended for database management.

[0567] When a user enters product information via a terminal, this information is sent to a server and processed by the information input method. Based on this information, the server uses an AI model (for example, a deep learning model using TensorFlow) to analyze sales data and generate optimal inventory replenishment and product recommendations. For sentiment analysis, the Google Cloud Natural Language API is used to extract user sentiment data based on reviews and feedback.

[0568] Based on the analysis of emotional data, the server provides real-time product recommendations tailored to each user's preferences. Dynamic display methods are used to show relevant information on smartphone or computer screens.

[0569] For example, if a user has posted multiple positive reviews on a particular genre, the server has a function that suggests related new products based on that information. This allows users to quickly find products that meet their individual needs, improving the purchasing experience. By inputting prompt sentences like the following into the generating AI model, more precise data analysis becomes possible.

[0570] Example prompt: "Analyze user reviews for sentiment and combine it with current weather patterns to suggest recommended products."

[0571] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0572] Step 1:

[0573] The server receives product information and sales performance data from the user's terminal. Input data includes product ID, sales quantity, and inventory status. The server stores this data in a database, preparing it for use in sales analysis. This data is stored in a MySQL database via an information storage system.

[0574] Step 2:

[0575] The server inputs stored product information and sales data into an AI model to predict inventory replenishment. TensorFlow is used to perform data calculations that take into account past sales trends and seasonal fluctuations. As a result, the system outputs how much of each product should be replenished.

[0576] Step 3:

[0577] The server collects product reviews and feedback submitted by users through their devices. This text data is then analyzed for sentiment using the Google Cloud Natural Language API to extract positive or negative sentiment data. The input for this analysis is the review text, and the output is a sentiment score.

[0578] Step 4:

[0579] The server selects products suitable for the user based on sentiment scores and generates dynamic product recommendations. This process utilizes a generative AI model; for example, by inputting a prompt such as, "Analyze the sentiment from user reviews and suggest recommended products in combination with current weather patterns," the AI ​​selects the optimal set of products. A recommended product list is then generated as output.

[0580] Step 5:

[0581] The terminal displays a list of recommended products received from the server in its user interface. Personalized suggested products and promotions are displayed on the screen in real time, and users can view detailed information by clicking on them. Dynamic display functionality is used in this step to provide consistent visual feedback to the user as output.

[0582] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0583] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0584] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0585] [Fourth Embodiment]

[0586] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0587] As shown in Figure 7, the 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.

[0588] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0589] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0590] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0591] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0592] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0593] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0594] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0595] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0596] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0597] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0598] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0599] The automated ordering system of this invention is designed to efficiently manage data for e-commerce. This system automates the entire process, from registering product information and analyzing sales performance to inventory management and new product proposals, as an automated workflow. Various components of this system work together to comprehensively support store operations, inventory management, and product development.

[0600] The server plays a central role, centrally managing product information and sales data in a database. Product information is registered on the server through data entry methods, and this information, along with sales performance data, is stored in the database. This allows users to check product inventory and sales status in real time.

[0601] For example, when a user registers a new product, the server uses this information to calculate the initial allocation for each store and place the inventory appropriately. The administrator is notified of this calculation result via a terminal, and the administrator can review and correct it as needed.

[0602] The AI ​​agent automatically generates the optimal inventory replenishment plan by analyzing sales performance and external data (such as weather and event information). Users review this replenishment plan, make adjustments as needed, and then place an order based on the finalized details.

[0603] Furthermore, the AI ​​agent analyzes sales trends of similar products and proposes specifications and designs for new products. Based on these proposals, the server provides feedback to the manufacturer, supporting the development of new products.

[0604] This system aims to improve the efficiency of store operations and maximize sales by optimizing inventory and providing products that meet consumer demand. Specifically, for example, when rising temperatures are predicted during the summer, the AI ​​will suggest replenishing stock with more cooling clothing, enabling a rapid response to the market.

[0605] The above describes the embodiments for carrying out the present invention, and this system is expected to contribute to the overall efficiency of merchandise management operations.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The user uses a terminal to enter product information (product name, category, price, initial stock quantity, etc.) on a data entry screen. The server receives this data and saves the registered product information to a database.

[0609] Step 2:

[0610] Users configure product classification and inventory turnover criteria based on sales policies and product characteristics through the management screen. The server receives the configured criteria and updates the database settings.

[0611] Step 3:

[0612] The server uses an AI agent to calculate the initial allocation amount for each store and e-commerce site based on registered product information and past sales data. The calculated allocation amount is notified to the terminal and displayed to the user.

[0613] Step 4:

[0614] The POS system transmits sales information and inventory status from each store to the server in real time. The server receives this information and updates the database. This ensures that the latest sales and inventory information is always stored in the database.

[0615] Step 5:

[0616] The AI ​​agent analyzes sales data and inventory information stored on the server to generate an optimal inventory replenishment plan. The generated replenishment plan is displayed to the user via their terminal, which they can review and adjust if necessary.

[0617] Step 6:

[0618] After the user approves the replenishment plan, the server uses the confirmed information to process the order. This ensures that the specified goods are replenished within the supply chain.

[0619] Step 7:

[0620] The AI ​​agent analyzes sales data and market trends to propose specifications and designs for new products. The proposed new product information is provided to manufacturers via a server, accelerating the development of new products.

[0621] The above outlines the specific processing flow within this system. Through these steps, efficient inventory management and product provision that meets consumer supply and demand are achieved.

[0622] (Example 1)

[0623] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0624] Traditional sales management systems faced challenges in efficiently handling a wide range of tasks, from registering product information and collecting sales data to inventory management and proposing new product development. Furthermore, data management and analysis were often performed manually, hindering rapid decision-making. Additionally, the lack of optimization for inventory replenishment, taking external factors into account, frequently resulted in insufficient response to demand.

[0625] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0626] In this invention, the server includes data management means for managing information related to commercial transactions, data input means for registering product information, and database means for integrating and managing sales performance and inventory information of products. This enables the automation of product management and rapid and accurate data-driven decision-making.

[0627] "Commercial transactions" refer to a series of trading activities involving the buying and selling of goods and services.

[0628] "Data management means" refers to technical means for effectively collecting, storing, and processing information, enabling access to and use of that data as needed.

[0629] "Data input means" refers to the interface or tools that users use to input information into the system, and in this system, it is used for registering item information.

[0630] A "database" is a system or technology that centrally stores and manages multiple pieces of information, enabling efficient searching and editing.

[0631] "Computational means" refers to technologies for automatically performing data analysis and calculations, specifically used for product distribution.

[0632] "Artificial intelligence tools" refer to technologies that use machine learning and data analysis techniques to extract insights from data and make judgments and suggestions.

[0633] "Predictive data analysis methods" are analytical techniques used to predict future events and outcomes based on past data and external information.

[0634] "Product development support tools" are technologies that analyze sales data and other information to support the development process in order to propose specifications and designs for new products.

[0635] "Display means" refers to a device or method for visually presenting system output information to a user.

[0636] This invention provides a system for effectively managing and utilizing information related to commercial transactions. The server plays a role in streamlining store operations and sales strategies by comprehensively managing product information and analyzing sales performance and inventory data in real time.

[0637] Specifically, users register product information on the server using a data entry system. This information is centrally managed in the server's database and used together with sales performance and inventory data. Based on this data, the server utilizes AI technology to automatically generate inventory replenishment plans. It also considers external data such as weather and event information to propose the optimal sales strategy according to the time of year and circumstances.

[0638] By using an AI agent, the system can propose specifications and designs for new products based on sales trends and provide rapid feedback to manufacturers. This enables inventory optimization and product supply tailored to demand, contributing to maximizing sales.

[0639] For example, if a user registers new summer clothing items using their device, the server analyzes this information using AI and, considering the predicted increase in demand due to rising temperatures, suggests a plan to replenish inventory of cooling-material clothing. This allows for a swift response to the market.

[0640] An example of a prompt to be input into the generating AI model is, "Generate the optimal inventory replenishment plan based on sales performance and weather forecasts." This prompt allows the system to quickly provide the most suitable suggestion to the user.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1:

[0643] Users input item information using a terminal. This data includes the product name, category, price, and quantity. Once the user has finished entering this information, they send it to the server via the data entry system. The server stores the received item information in a database, enabling centralized information management. Accurate data entry is required because the entered information will be used for subsequent analysis.

[0644] Step 2:

[0645] The server periodically retrieves sales performance data and inventory information from the database. This includes the number of units sold and inventory status of each product. Based on the retrieved data, the server uses a generative AI model to analyze the data in real time. Specific data processing includes sales trend analysis and demand forecasting. The results of this analysis are then used in the next step.

[0646] Step 3:

[0647] The server uses an AI agent to generate an optimal inventory replenishment plan based on the analysis results. This process also takes into account external data such as weather and event information. The generated replenishment plan is output as product name and recommended replenishment quantity. The server distributes this information to terminals and presents it to the user. Specifically, this step involves the automatic creation of a replenishment plan based on sales forecasts.

[0648] Step 4:

[0649] Users review the replenishment plan presented on their terminal and adjust it as needed. This adjustment includes changes to accommodate unexpected sales or changes in economic conditions. After adjustment, users send the finalized replenishment plan to the server. The server receives this information and processes the order based on its contents. User-initiated adjustments increase the flexibility of inventory management.

[0650] Step 5:

[0651] The AI ​​agent analyzes sales trends of similar products based on sales data and proposes specifications and designs for new products. The server outputs a report detailing these proposals for feedback to the manufacturer. This report serves as foundational data to support new product development and is useful for the manufacturer's development strategy.

[0652] (Application Example 1)

[0653] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0654] In modern e-commerce, inventory management and sales strategy optimization are critical challenges. In particular, responding quickly to fluctuations in product demand and ensuring appropriate replenishment is essential, but this requires complex data analysis and forecasting, which is difficult to do manually. Therefore, there is a need for systems that support efficient and accurate inventory management and product replenishment strategies.

[0655] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0656] In this invention, the server includes data management means for e-commerce, data input means for registering product information, and database means for centrally managing sales performance and inventory information. This enables the prediction of fluctuations in product demand, automation of inventory management and product replenishment, and efficient store operations.

[0657] "Data management means for electronic commerce" refers to methods and devices for effectively managing product information and sales data in commercial transactions conducted over the internet.

[0658] "Data input means" refers to interfaces or methods for inputting necessary data, such as product information and sales performance, into a system.

[0659] A "database means" is a technology or device for centrally storing multiple pieces of information and performing searches and analyses as needed.

[0660] A "computational tool" is a logical method or system used to perform necessary calculations based on aggregated data and derive specific instructions or suggestions.

[0661] "Artificial intelligence means" refers to technologies that allow machines to mimic human intellectual activity, analyze sales data, and suggest inventory replenishment.

[0662] "Predictive data analysis methods" are analytical techniques that use external data to predict future trends and demand, and to make appropriate recommendations.

[0663] "Product development support means" refers to technologies or processes for proposing specifications for new products and supporting product planning and design.

[0664] A "smartphone application" refers to software that supports users in efficiently replenishing products by performing demand forecasting and inventory management on a portable device.

[0665] The system for realizing this invention consists of multiple hardware and software components. The server functions as the core for managing data for e-commerce, centrally managing sales performance and inventory information in a database. The database is operated scalably using the AWS cloud and efficiently processes large amounts of data using DynamoDB.

[0666] The device provides users with real-time inventory information and AI-powered sales forecasts through a smartphone application. This application is developed using React Native, enabling it to run on a variety of platforms.

[0667] The AI-generated inventory replenishment suggestions are generated by a model using TensorFlow. The server uses a predictive data analysis tool developed in Python to acquire external data such as weather information and analyze sales trends based on that data. During this process, sales performance data is aggregated and analyzed using Python scripts.

[0668] Users can review suggested replenishment plans through a smartphone application and make adjustments as needed. In this way, intuitive use of AI-generated data-driven insights can lead to more efficient inventory management and maximized sales opportunities.

[0669] A concrete example would be a user replenishing their stock of sunscreen products in preparation for sunny weather over the weekend. In this scenario, the AI ​​predicts demand based on past sales data and weather forecasts, and notifies the user with a prompt message such as, "Based on the weather this weekend, what products are expected to be in high demand?" By responding to this prompt, the user can refer to the suggestions and replenish their stock without missing a sales opportunity.

[0670] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0671] Step 1:

[0672] The server registers product information and sales performance data into a database. This involves a process that efficiently stores data using AWS DynamoDB. The input is product information and sales performance data, and the output is the updated database.

[0673] Step 2:

[0674] The device makes API calls to allow the AI ​​agent to collect external data such as weather forecasts and event information. This data is used as input for a demand forecasting model. The input is data obtained from external APIs, and the output is the analysis result from the AI ​​agent.

[0675] Step 3:

[0676] The server uses TensorFlow to run an AI model and forecast demand for the product. Sales data and external data are input to the model, and a demand forecast value is generated as output. This forecast value serves as the basis for inventory replenishment plans.

[0677] Step 4:

[0678] The terminal receives inventory replenishment proposals from the server and notifies the user via their smartphone. The user reviews this notification and, if necessary, makes adjustments according to the proposed replenishment plan. The input is the inventory replenishment proposal from the server, and the output is the notification to the user.

[0679] Step 5:

[0680] Users review, approve, or modify inventory replenishment proposals through the application. This ensures that user decisions are reflected in inventory management. The input is the proposed replenishment plan, and the output is the final replenishment plan based on the user's decision.

[0681] Step 6:

[0682] The server automates the actual ordering process based on the approved replenishment plan and sends the order information to the supplier. The input here is the replenishment plan approved by the user, and the output is the order information sent to the supplier.

[0683] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0684] This invention is an automated ordering system that combines an emotion engine to enhance data management in e-commerce. This system highly automates the registration of product information, management of sales performance, optimization of inventory, and proposal of new products, and also utilizes user emotion data.

[0685] The server first receives product information through data entry methods and centrally stores it in a database. Users input product information via terminals and then perform the necessary settings based on sales policies. This ensures a smooth initial product launch.

[0686] Next, the AI ​​agent analyzes sales data and generates an optimal inventory replenishment plan. Based on this data, the server creates a replenishment proposal tailored to consumer trends and seasonal fluctuations, and presents it to the user via the terminal. The user reviews the proposal and approves or modifies it as needed.

[0687] Furthermore, this system incorporates an emotion engine that extracts emotional data from user feedback and reviews. This emotional data is analyzed on a server and reflected in sales strategies and new product proposals. For example, if user reviews show a high proportion of positive emotions, a strategy to promote related products will be considered.

[0688] As a concrete example, consider a product whose demand increases due to climate change. The emotion engine analyzes user emotions regarding interest and satisfaction, and based on this, an AI agent adjusts replenishment plans. This process facilitates appropriate inventory placement for best-selling products, thereby maximizing sales.

[0689] Embodiments of the present invention enable efficient inventory management and marketing strategies that reflect consumer needs. This method is expected to allow companies to respond more quickly to market fluctuations and contribute to improved customer satisfaction.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The user uses a terminal to enter product information on a data entry screen. This includes basic information such as product name, category, price, and initial stock quantity. The server receives this information and records it in the database.

[0693] Step 2:

[0694] The server uses an AI agent to calculate the initial allocation to each store based on registered product information and sales performance data. The calculated allocation amount is notified to the user's terminal, and the user confirms the details.

[0695] Step 3:

[0696] After sales begin, the POS system transmits sales data and inventory status to the server in real time. The server retrieves this data and updates the database. This ensures that accurate sales figures are always maintained.

[0697] Step 4:

[0698] The AI ​​agent analyzes updated sales data and inventory information to generate optimal inventory replenishment plans. The server sends these plans to the user's terminal, where the user reviews, approves, or modifies the suggestions.

[0699] Step 5:

[0700] When analyzing sales data and user reviews, the emotion engine analyzes user feedback and extracts emotional data. Based on this emotional data, the server adapts sales strategies and new product suggestions.

[0701] Step 6:

[0702] Users develop promotional and inventory strategies that take into account insights gained from the emotion engine. This information is shared via a server and used to develop specifications and launch plans for new products.

[0703] Step 7:

[0704] The server provides feedback to manufacturers with new product suggestions and improvement ideas based on all analysis results, including emotional data. This process ensures that products are developed in line with consumer demand and preferences.

[0705] (Example 2)

[0706] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0707] In e-commerce, it is necessary to efficiently manage sales data, inventory data, and consumer feedback, and to respond quickly to market fluctuations. However, traditional systems have the problem of difficulty in integrating and analyzing this data to formulate optimal sales strategies. In particular, there is a need for flexible inventory replenishment and new product recommendations that utilize consumer sentiment data, but there is a lack of means to effectively implement this.

[0708] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0709] In this invention, the server includes information management means, data input means, and intelligent processing means. This enables integrated analysis of sales data and consumer sentiment data, allowing for effective inventory management and market adaptation.

[0710] "Information management methods" refer to techniques for centrally collecting and managing sales performance and inventory information in e-commerce.

[0711] "Data entry method" refers to a method of entering product information in electronic format and transmitting it to a system.

[0712] "Calculation means" refers to algorithms or calculation systems used to distribute merchandise to each store based on aggregated information.

[0713] "Intelligent processing means" refers to a method that uses artificial intelligence technology to analyze sales conditions and propose inventory replenishment.

[0714] A "predictive information analysis tool" is an analytical tool for optimizing inventory replenishment suggestions based on external data.

[0715] A "product development support system" is an information processing system for proposing specifications for new products.

[0716] "Emotional analysis methods" refer to technologies that analyze users' emotional data and utilize it in marketing strategies.

[0717] "Integration methods" refer to the process of analyzing multiple data sets using generative AI models to optimize strategies.

[0718] This invention is a system that combines the latest intelligent processing technology with sentiment analysis to enhance data processing and inventory management in e-commerce. The implementation method is described in detail below.

[0719] Hardware and software configuration

[0720] The server serves as the central hub for data management, utilizing database management systems such as MySQL and PostgreSQL for information management. This allows for centralized management of sales performance and inventory information.

[0721] The terminal functions as a data entry device for users to input product information. At this stage, the terminal sends data to the server using a web browser or mobile application.

[0722] The server uses machine learning frameworks such as TensorFlow and PyTorch as intelligent processing tools. It uses these frameworks to analyze sales data in real time and generate appropriate inventory replenishment suggestions.

[0723] The sentiment analysis method analyzes user feedback using natural language processing (NLP) techniques. BERT and GPT are utilized as generative AI models.

[0724] In this integration system, the server combines sales data and user sentiment data to optimize sales strategies. This involves an AI agent using a generated AI model to handle data analysis and strategy formulation.

[0725] Specific examples and the use of prompt statements

[0726] For example, for products whose demand increases due to climate change, an AI agent forecasts demand and adjusts inventory replenishment plans based on positive feedback obtained from sentiment analysis. Through this process, the system enables effective inventory placement in line with market trends.

[0727] An example of a prompt from a generating AI model is, "Analyze purchase history data from the past three months and propose a promotional strategy for popular products and related products." This prompt leads to the development of a strategy centered on products that interest the user.

[0728] Embodiments of the present invention provide concrete measures to quickly respond to market fluctuations and enhance customer satisfaction through the use of advanced data analysis and emotional feedback.

[0729] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0730] Step 1:

[0731] The user uses a terminal to input product information into a data entry system. This input includes product name, category, price, and stock quantity. This data is immediately sent to the server. The server stores the received product information in a database. Here, information management systems are used to check the integrity of the data and ensure reliable storage.

[0732] Step 2:

[0733] The server periodically collects sales performance data. Input data includes purchase date and time, sales quantity, and sales location. The server stores this data in a database in real time. The collected data is then passed to an AI agent using intelligent processing tools. The AI ​​agent analyzes sales trends and generates an inventory replenishment plan. The output is the proposed replenishment plan.

[0734] Step 3:

[0735] The server sends inventory replenishment proposals generated by the AI ​​agent to the user via the terminal. The user reviews the proposals and makes modifications as needed. Specifically, the proposals are modified and approved based on the user's actions. The server then records the updated replenishment proposals back into the database.

[0736] Step 4:

[0737] The server analyzes user feedback and reviews using sentiment analysis tools. Input data consists of text-based reviews and evaluation comments. Sentimental attributes are extracted using generative AI models (e.g., BERT or GPT). The output is presented as positive or negative sentiment data, which is used in product promotion strategies.

[0738] Step 5:

[0739] The server combines sales data and sentiment data through integration methods to formulate a comprehensive sales strategy. Inputs include historical sales performance and user sentiment analysis data. Generative AI models facilitate smooth data analysis and strategic decision-making. Outputs include timely promotional plans and inventory placement proposals, enabling companies to respond quickly to market trends.

[0740] (Application Example 2)

[0741] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] In e-commerce, inventory management and product recommendations were often conducted without considering user preferences or emotions, resulting in insufficient improvements in consumer satisfaction and maximization of inventory efficiency. Furthermore, a lack of dynamic and user-optimized information delivery led to inefficient sales promotion. To address these issues, it is necessary to utilize user sentiment data to improve personalized product recommendations and inventory management.

[0743] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0744] In this invention, the server includes information management means for e-commerce, information input means for registering product information, and information storage means for aggregating and managing sales performance and inventory information. This enables optimal product recommendations and efficient inventory replenishment based on user sentiment data.

[0745] 1. "Information management system for e-commerce" refers to a mechanism for centrally managing and processing information related to goods, sales, and inventory in e-commerce.

[0746] 2. "Information input means for registering product information" refers to tools or interfaces for registering detailed information about a product into a system.

[0747] 3. "Information storage means for aggregating and managing sales performance and inventory information" refers to a database mechanism that centrally stores past sales history and current inventory status, making them accessible as needed.

[0748] 4. A "computational means" is a computational mechanism for calculating efficient inventory allocation and replenishment based on e-commerce data.

[0749] 5. "Artificial intelligence means" refers to a system that uses AI technology to analyze sales data and external factors and generate optimal inventory replenishment and sales strategies.

[0750] 6. A "predictive information analysis tool" is an analytical mechanism that takes external information into consideration to predict future sales trends and inventory needs.

[0751] 7. A "new product specification proposal mechanism" is a support system for proposing the specifications and features of a new product to the development team.

[0752] 8. "Sentiment analysis methods" refer to technologies for extracting and analyzing emotional data from user reviews and feedback.

[0753] 9. A "dynamic display means" is a mechanism for displaying optimal product suggestions and information in real time based on user behavior and emotional data.

[0754] This invention provides a system that streamlines personalized product recommendations and inventory management in e-commerce. A server serves as the central hub of this system, responsible for information management, analysis, and display. Specifically, the server utilizes cloud services such as Google Cloud to aggregate and manage product information and sales performance. A relational database such as MySQL is recommended for database management.

[0755] When a user enters product information via a terminal, this information is sent to a server and processed by the information input method. Based on this information, the server uses an AI model (for example, a deep learning model using TensorFlow) to analyze sales data and generate optimal inventory replenishment and product recommendations. For sentiment analysis, the Google Cloud Natural Language API is used to extract user sentiment data based on reviews and feedback.

[0756] Based on the analysis of emotional data, the server provides real-time product recommendations tailored to each user's preferences. Dynamic display methods are used to show relevant information on smartphone or computer screens.

[0757] For example, if a user has posted multiple positive reviews on a particular genre, the server has a function that suggests related new products based on that information. This allows users to quickly find products that meet their individual needs, improving the purchasing experience. By inputting prompt sentences like the following into the generating AI model, more precise data analysis becomes possible.

[0758] Example prompt: "Analyze user reviews for sentiment and combine it with current weather patterns to suggest recommended products."

[0759] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0760] Step 1:

[0761] The server receives product information and sales performance data from the user's terminal. Input data includes product ID, sales quantity, and inventory status. The server stores this data in a database, preparing it for use in sales analysis. This data is stored in a MySQL database via an information storage system.

[0762] Step 2:

[0763] The server inputs stored product information and sales data into an AI model to predict inventory replenishment. TensorFlow is used to perform data calculations that take into account past sales trends and seasonal fluctuations. As a result, the system outputs how much of each product should be replenished.

[0764] Step 3:

[0765] The server collects product reviews and feedback submitted by users through their devices. This text data is then analyzed for sentiment using the Google Cloud Natural Language API to extract positive or negative sentiment data. The input for this analysis is the review text, and the output is a sentiment score.

[0766] Step 4:

[0767] The server selects products suitable for the user based on sentiment scores and generates dynamic product recommendations. This process utilizes a generative AI model; for example, by inputting a prompt such as, "Analyze the sentiment from user reviews and suggest recommended products in combination with current weather patterns," the AI ​​selects the optimal set of products. A recommended product list is then generated as output.

[0768] Step 5:

[0769] The terminal displays a list of recommended products received from the server in its user interface. Personalized suggested products and promotions are displayed on the screen in real time, and users can view detailed information by clicking on them. Dynamic display functionality is used in this step to provide consistent visual feedback to the user as output.

[0770] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0771] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0772] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0773] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0774] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0775] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0776] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0777] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0778] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0779] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0780] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0781] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0782] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0783] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0784] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0785] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0786] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0787] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0788] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0789] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0790] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0791] The following is further disclosed regarding the embodiments described above.

[0792] (Claim 1)

[0793] Data management methods for e-commerce,

[0794] A data entry method for registering product information,

[0795] A database system for centrally managing sales performance and inventory information,

[0796] A calculation method for distributing initial products to each store based on aggregated data,

[0797] An artificial intelligence system for analyzing sales status in real time and suggesting inventory replenishment,

[0798] A predictive data analysis tool for revising supplementary proposals by taking external data into consideration,

[0799] A product development support tool for proposing specifications for new products,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, comprising means for automatically setting the inventory turnover rate of products based on entered product information and sales performance.

[0803] (Claim 3)

[0804] The system according to claim 1, further comprising means for making supplementary suggestions that take into account weather data and event information as external factors.

[0805] "Example 1"

[0806] (Claim 1)

[0807] A data management system for managing information related to commercial transactions,

[0808] A data entry means for registering item information,

[0809] A database system for integrating and managing sales performance and inventory information of goods,

[0810] A calculation means for distributing initial items to each sales office based on integrated data,

[0811] An artificial intelligence system for analyzing sales trends in real time and proposing the optimal inventory replenishment plan,

[0812] A predictive data analysis method for modifying supplementary plans based on external data,

[0813] A product development support tool for analyzing sales trends of similar items and proposing specifications for new items,

[0814] A display means for presenting the results of information processing,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, comprising means for automatically calculating the inventory turnover rate of goods based on registered goods information and sales performance.

[0818] (Claim 3)

[0819] The system according to claim 1, further comprising means for proposing supplementary plans that take into account weather data and event information as external elements.

[0820] "Application Example 1"

[0821] (Claim 1)

[0822] Data management methods for e-commerce,

[0823] A data entry method for registering product information,

[0824] A database system for centrally managing sales performance and inventory information,

[0825] A calculation method for distributing initial products to each store based on aggregated data,

[0826] An artificial intelligence system for analyzing sales status in real time and suggesting inventory replenishment,

[0827] A predictive data analysis tool for revising supplementary proposals by taking external data into consideration,

[0828] A product development support tool for proposing specifications for new products,

[0829] A smartphone application for predicting fluctuations in product demand and automating inventory management and product replenishment,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, comprising means for automatically setting the inventory turnover rate of products based on entered product information and sales performance.

[0833] (Claim 3)

[0834] The system according to claim 1, further comprising means for making supplementary suggestions that take into account weather data and event information as external factors.

[0835] "Example 2 of combining an emotion engine"

[0836] (Claim 1)

[0837] Information management tools for e-commerce,

[0838] A data entry method for registering product information,

[0839] An information management system that centrally manages sales performance and inventory information,

[0840] A calculation method for distributing initial products to each store based on aggregated information,

[0841] An intelligent processing system for analyzing sales status in real time and proposing inventory replenishment,

[0842] A predictive information analysis tool for revising supplementary proposals by taking external data into consideration,

[0843] A product development support tool for proposing specifications for new products,

[0844] A means of analyzing user sentiment data and utilizing it in sales strategies,

[0845] An integrated means for analyzing sales data and sentiment data using a generative AI model to generate optimal inventory replenishment plans,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, comprising means for automatically setting the inventory turnover rate of products based on entered product information and sales performance.

[0849] (Claim 3)

[0850] The system according to claim 1, further comprising means for making supplementary suggestions that take weather information and event information into consideration as external factors.

[0851] "Application example 2 when combining with an emotional engine"

[0852] (Claim 1)

[0853] Information management tools for e-commerce,

[0854] A means of inputting information for registering product information,

[0855] An information storage means for aggregating and managing sales performance and inventory information,

[0856] A calculation means for distributing the initial products to each store based on the aggregated information,

[0857] An artificial intelligence system for analyzing sales status in real time and suggesting inventory replenishment,

[0858] A predictive information analysis tool for revising supplementary proposals by taking external information into consideration,

[0859] A means of proposing new product specifications to support product development,

[0860] A sentiment analysis method that extracts emotional data from user product reviews and proposes new products based on that data,

[0861] A dynamic display method for presenting product suggestions and promotions to users in real time,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, comprising means for automatically setting the inventory turnover rate of products based on entered product information and sales performance.

[0865] (Claim 3)

[0866] The system according to claim 1, further comprising means for making supplementary suggestions that take into account weather information and event information as external factors, and further take into account user sentiment data. [Explanation of symbols]

[0867] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Data management methods for e-commerce, A data entry method for registering product information, A database system for centrally managing sales performance and inventory information, A calculation method for distributing initial products to each store based on aggregated data, An artificial intelligence system for analyzing sales status in real time and suggesting inventory replenishment, A predictive data analysis tool for revising supplementary proposals by taking external data into consideration, A product development support tool for proposing specifications for new products, A system that includes this.

2. The system according to claim 1, comprising means for automatically setting the inventory turnover rate of products based on entered product information and sales performance.

3. The system according to claim 1, further comprising means for making supplementary suggestions that take into account weather data and event information as external factors.

Images