System

Abstract

A system is provided.SOLUTION: A system including means for automatically performing background removal, color adjustment, and size change in order to optimize a product image, means for automatically generating an attractive draft based on detailed information of a product, means for acquiring analysis data of a web site, analyzing improvement points of the site, and generating a specific improvement proposal, and means for generating an appropriate answer to an inquiry from a customer, and analyzing and responding to an emotion of the customer.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Operating an e-commerce website requires a wide range of tasks, placing a significant burden on the operator. These tasks include editing product images, writing product descriptions, analyzing website performance, and responding to customer inquiries. These tasks consume time and effort, preventing operators from concentrating on their primary goal: providing high-quality products and improving services. The present invention aims to solve these problems and streamline e-commerce website operations. [Means for solving the problem]

[0005] The present invention solves the aforementioned problems by proposing a system that includes the following means: It utilizes means for automatically removing backgrounds, adjusting colors, and resizing product images to optimize them. It also incorporates means for automatically generating attractive copy based on detailed product information. It also provides means for acquiring website analytics data, analyzing site improvements, and generating specific improvement proposals. It also includes means for generating appropriate responses to customer inquiries and analyzing and responding to customer sentiment. Such an integrated system frees e-commerce site operators from tedious tasks, allowing them to focus on strategic operations and improving service quality.

[0006] The "automatic product image editing module" is a system that executes a series of processes to automatically optimize product images, specifically removing backgrounds, adjusting colors, and resizing.

[0007] The "automatic text generation module" is a system that automatically generates attractive product descriptions based on detailed product information.

[0008] The "site analysis automation module" is a system that automatically acquires website analysis data, analyzes areas for improvement on the site, and generates specific improvement proposals.

[0009] A "customer support AI chatbot" is an artificial intelligence system that can generate appropriate responses to customer inquiries and analyze customer emotions to respond accordingly.

[0010] "Background removal" refers to the process of automatically removing the background portion of a product image using image processing techniques.

[0011] "Color adjustment" is the process of optimizing the color balance of an image to produce a visually appealing product image.

[0012] "Resizing" is the process of adjusting the dimensions of an image to an appropriate size based on specified criteria.

[0013] "Detailed information" refers to a set of information necessary for a buyer to select a product, such as product features, size, material, and color.

[0014] "Analytics Data" means data used to measure and evaluate Site performance, including website traffic, user behavior, and visitor characteristics.

[0015] "Improvement Suggestions" are specific actions or changes suggested based on analytics data to improve site performance.

[0016] "Sentiment analysis" is the process of analyzing the emotions of customers based on their inquiries and determining the most appropriate response method. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[0039] 1. Product image automatic editing module

[0040] overview:

[0041] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[0042] What happens:

[0043] The user uploads a product image on the EC management screen.

[0044] The server receives the uploaded image and temporarily stores it.

[0045] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[0046] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[0047] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[0048] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[0049] Examples:

[0050] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[0051] 2. Automatic copy generation module

[0052] overview:

[0053] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[0054] What happens:

[0055] The user enters and saves new product information (features, size, material, etc.).

[0056] The server stores the new product information in a database.

[0057] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[0058] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0059] Examples:

[0060] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[0061] 3. Site Analysis Automation Module

[0062] overview:

[0063] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[0064] What happens:

[0065] The server periodically retrieves site analytics data via the Google Analytics API.

[0066] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement.

[0067] The server converts the received analysis results into a report format and notifies the operator of the generated report.

[0068] Examples:

[0069] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[0070] 4. Customer Support AI Chatbot

[0071] overview:

[0072] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[0073] What happens:

[0074] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[0075] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's sentiment to determine how to respond.

[0076] The chatbot server returns the generated answer to the customer.

[0077] Examples:

[0078] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[0079] In this way, a system is provided that automates various tasks related to operating an e-commerce site and reduces the burden on operators.

[0080] The processing flow will be explained below.

[0081] Product image automatic editing module

[0082] Processing Steps:

[0083] Step 1:

[0084] The user uploads a product image on the EC management screen.

[0085] Step 2:

[0086] The server receives the uploaded image and temporarily stores it.

[0087] Step 3:

[0088] The server sends the image to the AI ​​image processing engine and requests a background removal task.

[0089] Step 4:

[0090] The AI ​​image processing engine identifies the background of the image and removes it.

[0091] Step 5:

[0092] The AI ​​image processing engine returns the image with the background removed to the server.

[0093] Step 6:

[0094] The server requests a color adjustment task and sends the background-removed image back to the AI ​​image processing engine.

[0095] Step 7:

[0096] The AI ​​image processing engine adjusts the color tone of the image to create attractive colors.

[0097] Step 8:

[0098] The AI ​​image processing engine sends the color-adjusted image back to the server.

[0099] Step 9:

[0100] The server receives the color-adjusted image and resizes it to the optimal image size.

[0101] Step 10:

[0102] The server saves the final edited image in a database and reflects it on the product page of the e-commerce site.

[0103] Automatic copy generation module

[0104] Processing Steps:

[0105] Step 1:

[0106] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[0107] Step 2:

[0108] The server stores the new product information in a database.

[0109] Step 3:

[0110] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[0111] Step 4:

[0112] The AI ​​text generation engine analyzes the product's features and generates compelling copy.

[0113] Step 5:

[0114] The AI ​​text generation engine sends the generated text back to the server.

[0115] Step 6:

[0116] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0117] Site analysis automation module

[0118] Processing Steps:

[0119] Step 1:

[0120] The server uses the Google Analytics API to retrieve site analytics data periodically (e.g. daily, weekly).

[0121] Step 2:

[0122] The server sends the acquired analysis data to the AI ​​analysis engine.

[0123] Step 3:

[0124] An AI analytics engine analyzes traffic patterns and user behavior.

[0125] Step 4:

[0126] The AI ​​analysis engine extracts areas for improvement on the site and generates specific improvement suggestions.

[0127] Step 5:

[0128] The improvement suggestions generated by the AI ​​analysis engine are sent back to the server.

[0129] Step 6:

[0130] The server formats the analysis results it receives into a report format.

[0131] Step 7:

[0132] The server will then email the generated report to the site operator or display it in the admin panel.

[0133] Customer Support AI Chatbot

[0134] Processing Steps:

[0135] Step 1:

[0136] A user (customer) makes an inquiry to a chatbot on an e-commerce site.

[0137] Step 2:

[0138] The customer terminal sends the inquiry to the chatbot server.

[0139] Step 3:

[0140] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[0141] Step 4:

[0142] The AI ​​engine analyzes the inquiry and generates an appropriate answer.

[0143] Step 5:

[0144] The AI ​​engine analyzes the sentiment from the customer's text and determines the best way to respond.

[0145] Step 6:

[0146] The chatbot server returns the generated answer to the user's terminal.

[0147] Step 7:

[0148] The user (customer) receives the answer and takes the next action (e.g., purchase, ask additional questions).

[0149] The above are the specific processing steps in each module.

[0150] Example 1

[0151] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0152] Traditional e-commerce site operations required a great deal of time and effort to edit product images, create product descriptions, analyze the site, and respond to customers. Performing these tasks manually increased the burden on operators and hindered efficient operations. Furthermore, responding in a way that takes customer feelings into consideration required advanced expertise, making it difficult to respond quickly and appropriately.

[0153] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0154] In this invention, the server includes means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating product descriptions based on detailed product information, means for acquiring analytical data, analyzing website improvements, and generating improvement proposals, means for generating appropriate responses to customer inquiries, and analyzing and responding to customer sentiments, means for receiving product images and saving them in a temporary storage area, means for sending product images to an AI image processing engine and requesting a background removal task, means for sending the image with the background removed to the AI ​​image processing engine and requesting a color adjustment task, means for resizing the color-adjusted image, and means for storing the edited image in a database. and reflecting it on the product page, means for inputting and saving product features, means for saving the saved product information in a database, means for sending the product features to an AI text generation engine and generating a product description, means for saving the generated product description in a database and reflecting it on the product page, means for acquiring data from an analysis platform, means for sending the data to an AI analysis engine and extracting improvements, means for formatting the generated improvement proposals into a report and notifying an operator, means for sending the inquiry content to a chatbot server and requesting an answer generation task, and means for responding to the customer with an answer and sending an additional message that takes emotions into consideration. This makes it possible to significantly reduce the time and effort required to operate an e-commerce site and reduce the burden on the operator.

[0155] "Product Image" means a digital image uploaded to an e-commerce site for the visual representation of a product.

[0156] "Background removal" is the process of identifying and removing unnecessary background parts from product images.

[0157] "Color adjustment" is the process of adjusting the color tone, brightness, contrast, etc. of a product image to an optimal state.

[0158] "Resize" is the operation of converting the size of a product image to the optimal dimensions for display or storage.

[0159] "Detailed product information" is data that includes specific information such as product features, size, material, and price.

[0160] A "product description" is automatically generated text that describes a product in an attractive way.

[0161] "Analytics Data" is a collection of information about website usage and user behavior.

[0162] "Improvements" are specific changes or actions you take to improve your website's performance.

[0163] An "inquiry" is a question or request that a customer makes to the operator regarding a product or service.

[0164] "Analyzing sentiment" is the act of identifying and evaluating the emotions and tone that customers express through their inquiries and feedback.

[0165] A "server" is a computer system that processes, stores, and provides network services.

[0166] An "AI image processing engine" is a software system that uses artificial intelligence technology to automatically edit images.

[0167] An "AI text generation engine" is a software system that uses artificial intelligence technology to automatically generate text in natural language.

[0168] A "report" is a document that organizes analysis results and improvement proposals and provides them to operators.

[0169] A "chatbot server" is a server system that automatically responds to inquiries from customers.

[0170] "Transmission" is the act of moving data or information from one system to another.

[0171] A "task" is an individual process or unit of work that a system executes.

[0172] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[0173] Product image automatic editing module

[0174] overview:

[0175] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[0176] Hardware and software:

[0177] Server: Manages image processing tasks and interacts with the database.

[0178] AI image processing engine: Image processing software such as Adobe Photoshop API and CorelDRAW API.

[0179] Database: Stores and manages image data.

[0180] explanation:

[0181] The user uploads a product image on the e-commerce management screen. The server receives the uploaded image and temporarily stores it. Next, the server sends the image to the AI ​​image processing engine and requests a background removal task. The AI ​​image processing engine identifies and removes the background from the image. The server then sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. After the color-adjusted image is received by the server, it is resized to the appropriate size. Finally, the edited image is saved in the database and reflected on the product page of the e-commerce site.

[0182] Examples:

[0183] When a user uploads a new product image, the server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the server optimizes the image size and saves it in the format that will be displayed on the website.

[0184] Example prompt:

[0185] "New product image uploaded. Remove background, adjust color, and resize for optimal fit."

[0186] Automatic copy generation module

[0187] overview:

[0188] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[0189] Hardware and software:

[0190] Server: Manages product data and copy generation tasks.

[0191] AI text generation engines: Text generation software such as GPT-3 and BERT.

[0192] Database: Stores and manages product information.

[0193] explanation:

[0194] The user enters and saves new product information (features, size, material, etc.). The server saves the new product information in a database. The server then sends the new product information to an AI text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates appealing copy. The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0195] Examples:

[0196] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[0197] Example prompt:

[0198] "Generate an attractive product description of 100 characters or less based on the new product information."

[0199] Site analysis automation module

[0200] overview:

[0201] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[0202] Hardware and software:

[0203] Server: Acquires and manages analysis data.

[0204] AI analytics engine: Data analytics software such as BigQuery and Data Studio.

[0205] Database: Stores and manages analysis results.

[0206] explanation:

[0207] The server periodically obtains website analysis data via the Google Analytics API. The server then sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior and identifies areas for improvement. The server then formats the analysis results into a report and notifies the operator.

[0208] Examples:

[0209] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[0210] Example prompt:

[0211] "Generate a report with site improvements based on this week's Google Analytics data."

[0212] Customer Support AI Chatbot

[0213] overview:

[0214] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[0215] Hardware and software:

[0216] Server: Responsible for query management and response generation.

[0217] AI engine: Chatbot software such as Dialogflow, IBM Watson, etc.

[0218] Database: Stores and manages inquiry details and response records.

[0219] explanation:

[0220] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server. The chatbot server then sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's emotions to determine how to respond. The chatbot server then returns the generated answer to the customer.

[0221] Examples:

[0222] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[0223] Example prompt:

[0224] "Use sentiment analysis to generate appropriate answers to questions that customers express emotions about."

[0225] In this way, each module works together to automate the operation of the e-commerce site, realizing a system that reduces the burden on operators.

[0226] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0227] Product image automatic editing module

[0228] Step 1:

[0229] The user uploads a product image on the EC management screen.

[0230] Input: The user specifies the image file for the product and clicks the upload button.

[0231] Specific operation: Product images are sent from the user's device to the server.

[0232] Output: Product images are temporarily saved on the server.

[0233] Step 2:

[0234] The server receives the uploaded product images and stores them in a temporary storage area.

[0235] Input: Product image file sent from the user's device.

[0236] Specific operation: The server stores the product image in a temporary storage area.

[0237] Output: Product image files saved in temporary storage area.

[0238] Step 3:

[0239] The server retrieves the product image from the temporary storage area and requests the background removal task from the AI ​​image processing engine.

[0240] Input: Product image file saved in temporary storage area.

[0241] Specific operation: The server sends the image to an AI image processing engine (e.g., Adobe Photoshop API) and instructs it to perform the background removal task.

[0242] Output: Product image files with background removed.

[0243] Step 4:

[0244] The server sends the background-removed image to the AI ​​image processing engine and requests a color adjustment task.

[0245] Input: Background removed product image file.

[0246] Specific operation: The server again sends the image to the AI ​​image processing engine and instructs it to perform color adjustment tasks.

[0247] Output: Color-adjusted product image files.

[0248] Step 5:

[0249] The server resizes the color-adjusted image.

[0250] Input: Color adjusted product image files.

[0251] What happens: The server resizes the image using a built-in image processing library (e.g., Pillow).

[0252] Output: Resized product image files.

[0253] Step 6:

[0254] The server saves the edited product images in a database and reflects them on the product page of the e-commerce site.

[0255] Input: Resized product image files.

[0256] Specific operation: The server saves the image in the database and reflects the image URL on the product page.

[0257] Output: Optimized product images that are displayed on the product page of your ecommerce site.

[0258] Automatic copy generation module

[0259] Step 1:

[0260] The user enters and saves new product information (features, size, material, etc.).

[0261] Input: The user enters details about the new product into an input form.

[0262] Specific operation: Information entered from the user's terminal is sent to the server.

[0263] Output: New product information is saved on the server.

[0264] Step 2:

[0265] The server stores the new product information in a database.

[0266] Input: New product information submitted by the user.

[0267] Specific operation: The server stores the new product information in the database.

[0268] Output: New product information stored in the database.

[0269] Step 3:

[0270] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[0271] Input: New product information stored in the database.

[0272] Specific operation: The server sends product information to an AI text generation engine (e.g., GPT-3) and instructs it to generate a copy.

[0273] Output: The generated product description.

[0274] Step 4:

[0275] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0276] Input: The generated product description.

[0277] Specific operation: The server saves the product description in the database and reflects it on the product page.

[0278] Output: Product description displayed on the product page of the e-commerce site.

[0279] Site analysis automation module

[0280] Step 1:

[0281] The server periodically retrieves site analytics data via the Google Analytics API.

[0282] Input: Analytics data obtained from Google Analytics.

[0283] Specific operation: The server connects to the Google Analytics API and retrieves analytics data.

[0284] Output: The acquired analysis data.

[0285] Step 2:

[0286] The server sends the analysis data to the AI ​​analysis engine and requests a data analysis task.

[0287] Input: Acquired analytical data.

[0288] Specific operation: The server sends the analysis data to an AI analysis engine (e.g., BigQuery, Data Studio) and instructs it to analyze the data.

[0289] Output: Improvements extracted through data analysis.

[0290] Step 3:

[0291] The server formats the analysis results it receives into a report format and notifies the operator.

[0292] Input: Improvements extracted through data analysis.

[0293] Specific operation: The server prepares the analysis results in a report format (e.g., Excel, PDF).

[0294] Output: Report notifying operators.

[0295] Customer Support AI Chatbot

[0296] Step 1:

[0297] A user makes an inquiry to a chatbot on an e-commerce site.

[0298] Input: The query that the user types into the chatbot widget.

[0299] Specific operation: The user's inquiry is sent from the customer terminal to the chatbot server.

[0300] Output: The query received by the chatbot server.

[0301] Step 2:

[0302] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[0303] Input: The received inquiry.

[0304] Specific operation: The server sends the query content to an AI engine (e.g., Dialogflow, IBM Watson) and instructs it to generate an answer.

[0305] Output: The generated answer.

[0306] Step 3:

[0307] The chatbot server returns the generated answer to the customer.

[0308] Input: The generated answer.

[0309] Specific operation: The server sends the answer to the customer's terminal and displays it to the customer.

[0310] Output: The answer that is shown to the customer.

[0311] Step 4:

[0312] The chatbot server analyzes the customer's emotions and generates and sends additional messages that take their emotions into consideration.

[0313] Input: Customer sentiment data.

[0314] Specific operation: The server uses an AI engine to perform sentiment analysis and generate additional messages appropriate to the situation.

[0315] Output: Additional sentiment-sensitive messages sent to customers.

[0316] (Application example 1)

[0317] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0318] In operating an e-commerce site, tasks such as editing product images, generating product descriptions, analyzing site analytics data, and responding to customer inquiries require a lot of time and effort. Performing these tasks manually places a heavy burden on operators, hindering efficient operation. Furthermore, there is a need for an approach that allows these operations to be easily performed via smart devices.

[0319] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0320] In this invention, the server is a system including means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating attractive copy based on detailed product information, means for acquiring website analysis data, analyzing site improvements, and generating specific improvement proposals, and means for generating appropriate responses to customer inquiries and analyzing customer sentiments to respond accordingly, and the system is equipped with means for controlling these means via a smart device application, means for generating prompts for removing backgrounds, adjusting colors, and resizing product images, means for generating copy generation prompts based on detailed product information, and means for generating prompts for site improvement based on web analysis data. This automates various tasks involved in operating an e-commerce site, significantly reducing the burden on operators and enabling them to easily perform operations via smart devices.

[0321] "Optimizing product images" means removing the background from product images, adjusting the color, and resizing them to an appropriate size.

[0322] "Background removal" refers to identifying and removing background areas from product images.

[0323] "Color adjustment" refers to adjusting the color, brightness, etc. to improve the appearance of a product.

[0324] "Resizing" refers to resizing the product image to an appropriate size.

[0325] "Detailed product information" refers to information about the product, such as its features, size, and material.

[0326] "Automatically generating copy" refers to the use of artificial intelligence technology to automatically create attractive and appropriate product descriptions based on detailed product information.

[0327] "Website Analytics Data" refers to data such as website traffic, user behavior, and conversion rates.

[0328] "Site Improvements" means any changes or modifications needed to improve the performance and user experience of the Website.

[0329] "Specific improvement suggestions" refers to providing specific action plans and revisions based on areas for improvement on the site.

[0330] "Customer inquiries" refers to questions and requests from customers using the e-commerce site regarding product information, stock availability, returns and exchanges, etc.

[0331] "Generating appropriate responses" refers to automatically creating accurate and effective responses to customer inquiries.

[0332] "Analyzing customer emotions" refers to analyzing and understanding the customer's emotional state based on the content of their inquiry and their reaction.

[0333] "Smart device applications" refers to application software that can be used on smart devices such as smartphones and tablets.

[0334] A "prompt" refers to an input sentence used to give instructions or ask questions to artificial intelligence technology.

[0335] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate and analyze text.

[0336] This invention provides a series of automated systems to streamline e-commerce site operations and reduce the burden on operators. This system edits product images, generates product descriptions, analyzes websites, and responds to customer inquiries through smart device applications.

[0337] 1. Product image automatic editing module

[0338] When a user uploads a product image via a smart device application, the server receives and temporarily stores the image, then sends it to an AI image processing engine (such as TensorFlow or OpenCV) for background removal, color adjustment, and resizing.

[0339] Example: When you upload a picture of a new pair of sneakers, it will automatically have its background removed, its colors adjusted (whites are emphasized), and it will be resized to 200x200 pixels.

[0340] Example prompt:

[0341] Remove the background from your product images, adjust the colors, and resize them to the optimal size.

[0342] 2. Automatic copy generation module

[0343] When a user enters product information, the application sends the data to the server, which then requests an AI text generation engine (e.g., GPT-3) to generate a text based on the product information. The generated text is stored in a database and reflected on the e-commerce site.

[0344] Example: Enter the details of a new backpack and the following text is generated: "This backpack is made from durable materials and is comfortable to wear."

[0345] Example prompt:

[0346] "Generate compelling descriptions based on new product information."

[0347] 3. Site Analysis Automation Module

[0348] The server periodically retrieves website analytics data via APIs such as Google Analytics, sends it to an AI analytics engine, which analyzes traffic patterns and user behavior, and generates a report containing suggestions for improvement and notifies the website operator.

[0349] Example: A report includes a specific suggestion for improvement: "Page B has a low conversion rate and needs improvement."

[0350] Example prompt:

[0351] "Identify areas for improvement on your website based on Google Analytics data."

[0352] 4. AI Customer Support Chatbots

[0353] When a user makes an inquiry via a smart device application, the chatbot server receives the inquiry and sends it to the AI ​​engine to generate an appropriate answer. It also performs sentiment analysis and determines how to respond.

[0354] Example: When a customer asks, "What's the status of my order?", the chatbot responds, "Your order is currently being prepared for shipping." If a customer expresses dissatisfaction, the chatbot responds, "Sorry for the wait. We'll get back to you as soon as possible."

[0355] Example prompt:

[0356] "Generate appropriate responses to customer queries and respond emotionally if necessary."

[0357] In this way, the system of the present invention utilizes smart device applications to make the operation of an EC site more efficient and reduce the burden on the operator.

[0358] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0359] Step 1:

[0360] The user takes or selects and uploads a product image through a smart device application.

[0361] Input: Product image file.

[0362] How it works: The application transfers the image to a cloud server.

[0363] Output: Raw images uploaded to the server.

[0364] Step 2:

[0365] The server temporarily stores the received product image.

[0366] Input: Product image sent from a smart device.

[0367] How it works: The server stores image files in a dedicated directory.

[0368] Output: Temporarily saved product image files.

[0369] Step 3:

[0370] The server sends the image to an AI image processing engine (e.g., TensorFlow or OpenCV) and requests background removal.

[0371] Input: Temporarily saved product image file.

[0372] How it works: The server generates a prompt to the AI ​​engine and requests an image processing task.

[0373] Output: Product image with background removed.

[0374] Step 4:

[0375] The server sends the background-removed image back to the AI ​​image processing engine, requesting color adjustment and resizing.

[0376] Input: Product image with background removed.

[0377] How it works: The server generates a prompt for color adjustment and resizing and requests the AI ​​engine to process it.

[0378] Output: Color adjusted and resized product images.

[0379] Step 5:

[0380] The server saves the processed product images in a database and reflects them on the product page of the e-commerce site.

[0381] Input: Optimized product images.

[0382] Operation: The server saves the image to the database and updates the page on the e-commerce site.

[0383] Output: Updated e-commerce product page.

[0384] Step 6:

[0385] The user enters detailed product information into a smart device application and submits it.

[0386] Input: Product details (features, size, material, etc.).

[0387] Action: The application transfers the input data to the server.

[0388] Output: Product details received by the server.

[0389] Step 7:

[0390] The server sends the received product details to an AI text generation engine (e.g., GPT-3) and requests it to generate a product description.

[0391] Input: Product details.

[0392] How it works: The server generates a prompt to the AI ​​engine and asks it to perform a text generation task.

[0393] Output: The generated product description.

[0394] Step 8:

[0395] The server saves the generated product description in a database and reflects it on the product page of the e-commerce site.

[0396] Input: Product description.

[0397] What happens: The server saves the text to a database and updates the page on the e-commerce site.

[0398] Output: Updated e-commerce product page.

[0399] Step 9:

[0400] The server periodically collects analytics data such as Google Analytics.

[0401] Input: Web analytics data.

[0402] How it works: The server calls the analytics platform's API to retrieve data.

[0403] Output: Captured web analytics data.

[0404] Step 10:

[0405] The server sends the acquired analytical data to the AI ​​analysis engine, requesting it to analyze areas for improvement and generate a report.

[0406] Input: Web analytics data.

[0407] How it works: The server generates a prompt to the AI ​​analytics engine, requesting a data analysis task.

[0408] Output: A report containing generated improvement suggestions.

[0409] Step 11:

[0410] The server notifies the operator of the improvement proposal.

[0411] Input: Report with improvement suggestions.

[0412] Operation: The server notifies the operator of the report to his / her smart device.

[0413] Output: Report notified to the operator.

[0414] Step 12:

[0415] Users and customers make inquiries via smart device applications.

[0416] Input: Enquiry details.

[0417] How it works: The application sends the query data to the chatbot server.

[0418] Output: The query received by the server.

[0419] Step 13:

[0420] The chatbot server sends the received inquiry to the AI ​​engine, requesting answer generation and sentiment analysis.

[0421] Input: Enquiry details.

[0422] How it works: The server generates prompts for the AI ​​engine and assigns it answer generation and sentiment analysis tasks.

[0423] Output: Generated answers and sentiment analysis results.

[0424] Step 14:

[0425] The chatbot server responds to the customer with the generated answer and takes appropriate action based on the results of sentiment analysis.

[0426] Input: Generated answers and sentiment analysis results.

[0427] What it does: The server sends a response and, if necessary, responds based on the emotion.

[0428] Output: Answers returned to the customer and appropriate responses.

[0429] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0430] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[0431] 1. Product image automatic editing module

[0432] overview:

[0433] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[0434] What happens:

[0435] The user uploads a product image on the EC management screen.

[0436] The server receives the uploaded image and temporarily stores it.

[0437] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[0438] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[0439] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[0440] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[0441] Examples:

[0442] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[0443] 2. Automatic copy generation module

[0444] overview:

[0445] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[0446] What happens:

[0447] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[0448] The server stores the new product information in a database.

[0449] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[0450] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0451] Examples:

[0452] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[0453] 3. Site Analysis Automation Module

[0454] overview:

[0455] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[0456] What happens:

[0457] The server periodically retrieves site analytics data via the Google Analytics API.

[0458] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement.

[0459] The server converts the received analysis results into a report format and notifies the operator of the generated report.

[0460] Examples:

[0461] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[0462] 4. Customer Support AI Chatbots Combined with Emotion Engines

[0463] overview:

[0464] The AI ​​chatbot responds to customer inquiries 24 hours a day, using an emotion engine to analyze customer emotions and provide appropriate responses.

[0465] What happens:

[0466] A user (customer) makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[0467] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the sentiment.

[0468] The emotion engine recognizes emotions from customer text and determines the appropriate response.

[0469] The chatbot server returns the generated answer to the user's terminal.

[0470] Examples:

[0471] If an operator introduces a chatbot and emotion engine and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's emotions, such as, "We will do our best to respond quickly."

[0472] In this way, a system is provided that automates various tasks related to operating an e-commerce site and reduces the burden on operators.

[0473] The processing flow will be explained below.

[0474] Product image automatic editing module

[0475] Processing Steps:

[0476] Step 1:

[0477] The user uploads a product image on the EC management screen.

[0478] Step 2:

[0479] The server receives the uploaded image and temporarily stores it.

[0480] Step 3:

[0481] The server sends the image to the AI ​​image processing engine and requests a background removal task.

[0482] Step 4:

[0483] The AI ​​image processing engine identifies the background of the image and removes it.

[0484] Step 5:

[0485] The AI ​​image processing engine returns the image with the background removed to the server.

[0486] Step 6:

[0487] The server requests a color adjustment task and sends the background-removed image back to the AI ​​image processing engine.

[0488] Step 7:

[0489] The AI ​​image processing engine adjusts the color tone of the image to create attractive colors.

[0490] Step 8:

[0491] The AI ​​image processing engine sends the color-adjusted image back to the server.

[0492] Step 9:

[0493] The server receives the color-adjusted image and resizes it to the optimal image size.

[0494] Step 10:

[0495] The server saves the final edited image in a database and reflects it on the product page of the e-commerce site.

[0496] Automatic copy generation module

[0497] Processing Steps:

[0498] Step 1:

[0499] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[0500] Step 2:

[0501] The server stores the new product information in a database.

[0502] Step 3:

[0503] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[0504] Step 4:

[0505] The AI ​​text generation engine analyzes the product's features and generates compelling copy.

[0506] Step 5:

[0507] The AI ​​text generation engine sends the generated text back to the server.

[0508] Step 6:

[0509] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0510] Site analysis automation module

[0511] Processing Steps:

[0512] Step 1:

[0513] The server uses the Google Analytics API to retrieve site analytics data periodically (e.g. daily, weekly).

[0514] Step 2:

[0515] The server sends the acquired analysis data to the AI ​​analysis engine.

[0516] Step 3:

[0517] An AI analytics engine analyzes traffic patterns and user behavior.

[0518] Step 4:

[0519] The AI ​​analysis engine extracts areas for improvement on the site and generates specific improvement suggestions.

[0520] Step 5:

[0521] The improvement suggestions generated by the AI ​​analysis engine are sent back to the server.

[0522] Step 6:

[0523] The server formats the analysis results it receives into a report format.

[0524] Step 7:

[0525] The server will then email the generated report to the site operator or display it in the admin panel.

[0526] Customer support AI chatbot combined with emotion engine

[0527] Processing Steps:

[0528] Step 1:

[0529] A user (customer) makes an inquiry to a chatbot on an e-commerce site.

[0530] Step 2:

[0531] The customer terminal sends the inquiry to the chatbot server.

[0532] Step 3:

[0533] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[0534] Step 4:

[0535] The AI ​​engine analyzes the inquiry and generates an appropriate answer.

[0536] Step 5:

[0537] The emotion engine recognizes emotions from customer text and determines the appropriate response.

[0538] Step 6:

[0539] The chatbot server returns the generated answer to the user's terminal.

[0540] Step 7:

[0541] The user (customer) receives the answer and takes the next action (e.g., purchase, ask additional questions).

[0542] Example 2

[0543] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0544] On online shopping sites, managing the quality of product images, creating attractive product descriptions, improving website usability, and streamlining customer support are major burdens for operators. While automating these tasks would be desirable to reduce operational costs and improve user experience, there are still not enough systems available to achieve this.

[0545] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0546] In this invention, the server includes means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating attractive copy based on detailed product information, means for acquiring website analysis data, analyzing site improvements, and generating specific improvement proposals, means for generating appropriate responses to customer inquiries and analyzing and responding to customer sentiment, means for utilizing an external image processing engine, means for utilizing an external text generation engine, means for utilizing an external analysis platform, and means for analyzing customer sentiment using an external sentiment analysis engine and generating appropriate responses. This reduces the burden on operators and makes it possible to operate online shopping sites more efficiently.

[0547] "Product image optimization" means automatically removing backgrounds, adjusting colors, and resizing images to make them suitable for e-commerce sites.

[0548] "Background removal" is a process that removes the background from the product image, focusing only on the product.

[0549] "Color adjustment" is the process of adjusting the color tone, brightness, and contrast of product images to make them appear clearer and more attractive.

[0550] "Resizing" is the process of resizing the dimensions of product images to a size suitable for an e-commerce site.

[0551] "Automatic copy generation" refers to the automatic creation of attractive and purchasing-motivating text based on detailed product information.

[0552] "Website analytics data" refers to data on user behavior, such as the number of visitors to a website, the number of page views, the length of stay, and the bounce rate.

[0553] "Site Improvements" are areas that need to be fixed or changed to improve the website's usability or conversion rate.

[0554] An "AI image processing engine" is a program or system that uses machine learning and artificial intelligence technology to perform image editing processes (background removal, color adjustment, resizing, etc.).

[0555] An "AI text generation engine" is a program or system that automatically generates text (e.g., product descriptions) using natural language processing technology.

[0556] An "AI analytics engine" is a program or system that uses machine learning and artificial intelligence techniques to analyze large amounts of data and extract insights.

[0557] An "emotion analysis engine" is a program or system that detects and analyzes a speaker's emotions (e.g., joy, anger, sadness, etc.) from text data.

[0558] "External Analytics Platform" means a third-party service or system used to collect, store and analyze website analytics data.

[0559] "External Image Processing Engine" means a third-party image editing service or system used to perform processing such as background removal, color adjustment, or resizing of product images.

[0560] An "external text generation engine" is a third-party service or system that automatically generates text based on product feature information, etc.

[0561] This invention is a system that improves the efficiency of EC site operations and reduces the burden on operators. Below, we will explain the main modules that make up this system and how to implement it in detail.

[0562] Product image automatic editing module

[0563] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them using an external image processing engine (e.g., Adobe Photoshop API).

[0564] Hardware and software used:

[0565] Terminals, servers, and image processing engines used by users

[0566] Data processing and calculation:

[0567] 1. The user uploads a product image from the EC management screen.

[0568] 2. The server receives the image and temporarily stores it.

[0569] 3. The server sends the image to the image processing engine for background removal. The image processing engine identifies and removes the background of the image.

[0570] 4. The server receives the image with the background removed and sends it back to the image processing engine, requesting color adjustment.

[0571] 5. The server receives the color-adjusted image and optimizes its size.

[0572] 6. The server saves the edited image in the database and reflects it on the product page of the e-commerce site.

[0573] Examples:

[0574] A user uploads a new product image. The server receives the image, and the Adobe Photoshop API automatically removes the background and performs color adjustments. Finally, the server optimizes the image size and saves it in a format suitable for display on the website.

[0575] Example prompt sentence:

[0576] "Remove the background of this image, adjust the color, and resize it to the optimal size for your e-commerce site."

[0577] Automatic copy generation module

[0578] The server uses AI to automatically generate attractive product descriptions based on detailed product information retrieved from a product database. This process uses an external text generation engine (e.g., OpenAI GPT-4).

[0579] Hardware and software used:

[0580] The terminal, server, and text generation engine used by the user

[0581] Data processing and calculation:

[0582] 1. The user enters new product information (features, size, material, etc.) on the EC management screen and saves it.

[0583] 2. The server saves the new product information in the database.

[0584] 3. The server sends the new product information to the text generation engine and requests it to generate a copy. The text generation engine analyzes the product's features and generates an attractive copy.

[0585] 4. The server receives the generated draft and stores it in a database.

[0586] 5. The server reflects the text on the product page of the e-commerce site.

[0587] Examples:

[0588] When a new product is added, the server sends the product's characteristics to OpenAI GPT-4, which then generates a summary such as, "This T-shirt is made of 100% cotton and is extremely comfortable. Its casual design makes it suitable for any occasion."

[0589] Example prompt sentence:

[0590] "Create a compelling product description based on this product's features, size, and materials."

[0591] Site analysis automation module

[0592] The server analyzes the Google Analytics data and reports specific improvements to the site. This analysis is performed using an external analysis platform (e.g., Google Cloud AI).

[0593] Hardware and software used:

[0594] Server, analysis platform

[0595] Data processing and calculation:

[0596] 1. The server retrieves site analytics data via the Google Analytics API.

[0597] 2. The server sends the analysis data to the analysis platform and requests data analysis.

[0598] 3. The server receives the analysis results and formats them into a report.

[0599] 4. The server notifies the operator of the generated report.

[0600] Examples:

[0601] Every week, the server retrieves data from Google Analytics, and Google Cloud AI generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site's design and content.

[0602] Example prompt sentence:

[0603] "Please analyze this Google Analytics data and let us know how we can improve it."

[0604] Customer support AI chatbot combined with emotion engine

[0605] The server uses an AI chatbot to respond to customer inquiries 24 hours a day, analyzes customer emotions using an emotion engine, and responds appropriately. This process uses an external emotion analysis engine (e.g., IBM Watson Tone Analyzer).

[0606] Hardware and software used:

[0607] User devices, chatbot servers, and emotion analysis engines

[0608] Data processing and calculation:

[0609] 1. A user (customer) makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[0610] 2. The chatbot server sends the received inquiry to the AI ​​engine and requests it to generate an answer.

[0611] 3. The emotion engine recognizes emotions from the customer's text and determines the appropriate response.

[0612] 4. The chatbot server sends the generated answer back to the user's device.

[0613] Examples:

[0614] If an operator introduces a chatbot and emotion engine and a customer asks, "Please tell me the stock status of product A," the AI ​​will respond, "Product A is in stock." If the customer expresses dissatisfaction, the AI ​​will respond by taking their feelings into consideration, such as, "We will do our best to respond quickly."

[0615] Example prompt sentence:

[0616] "Analyze customer sentiment and generate relevant, responsive responses."

[0617] This system reduces the burden on operators and makes it possible to run online shopping sites more efficiently.

[0618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0619] Product image automatic editing module

[0620] Step 1:

[0621] The user selects a product image on the EC admin screen and clicks the upload button. The input is the image file selected by the user, and the output is the image data included in the HTTP POST request.

[0622] Step 2:

[0623] The server receives image data sent by the user and temporarily stores it. The input is the image data received via an HTTP POST request, and the output is an image file saved in a temporary folder on the server.

[0624] Step 3:

[0625] The server sends the image to the image processing engine and requests background removal. The input is the image file saved in the temporary folder, and the output is the image data sent in the HTTP request.

[0626] Step 4:

[0627] The server receives the background-removed image. The input is the HTTP response from the image processing engine, and the output is the background-removed image file saved in a temporary folder on the server.

[0628] Step 5:

[0629] The server sends the image with the background removed to the image processing engine again and requests color adjustment. The input is the image file with the background removed, and the output is the image data sent in the HTTP request.

[0630] Step 6:

[0631] The server receives the color-adjusted image. The input is the HTTP response from the image processing engine, and the output is the color-adjusted image file saved in a temporary folder on the server.

[0632] Step 7:

[0633] The server resizes the color-adjusted image to the optimal size. The input is the color-adjusted image file, and the output is the resized image file. Specifically, the resizing process is performed using an image processing library.

[0634] Step 8:

[0635] The server saves the resized image in a database. The input is the resized image file, and the output is the image data saved in the database.

[0636] Step 9:

[0637] The server reflects the image on the product page of the EC site. The input is the image data stored in the database, and the output is the image displayed on the product page of the EC site.

[0638] Automatic copy generation module

[0639] Step 1:

[0640] A user enters new product information (features, size, material, etc.) on the e-commerce management screen and clicks the save button. The input is the product information entered by the user, and the output is the product data included in the HTTP POST request.

[0641] Step 2:

[0642] The server saves the new product information to a database. The input is the product data received via an HTTP POST request, and the output is the product information saved in the database.

[0643] Step 3:

[0644] The server sends new product information to the text generation engine and requests it to generate text. The input is the product information stored in the database, and the output is the product data sent in the HTTP request.

[0645] Step 4:

[0646] The server receives the generated text from the text generation engine. The input is the HTTP response from the text generation engine, and the output is the generated text stored in the server's temporary memory.

[0647] Step 5:

[0648] The server stores the generated draft in a database. The input is the generated draft, and the output is the draft data stored in the database.

[0649] Step 6:

[0650] The server reflects the copy on the product page of the EC site. The input is the copy data stored in the database, and the output is the copy displayed on the product page of the EC site.

[0651] Site analysis automation module

[0652] Step 1:

[0653] The server periodically retrieves site analytics data via the Google Analytics API. The input is the API request, and the output is the retrieved site analytics data.

[0654] Step 2:

[0655] The server sends the acquired analysis data to the analysis platform and requests data analysis. The input is the acquired analysis data, and the output is the data sent in the HTTP request.

[0656] Step 3:

[0657] The server receives the analysis results from the analysis platform. The input is the HTTP response from the analysis platform, and the output is the analysis results stored in the server's temporary memory.

[0658] Step 4:

[0659] The server formats the analysis results it receives into a report format. The input is the analysis results, and the output is the formatted report data. Specifically, a report is created using a report generation tool.

[0660] Step 5:

[0661] The server notifies the operator of the generated report. The input is the formatted report data and the output is the notification sent to the operator.

[0662] Customer support AI chatbot combined with emotion engine

[0663] Step 1:

[0664] A user (customer) makes an inquiry to a chatbot on an e-commerce site. The input is the inquiry entered by the customer, and the output is chat data.

[0665] Step 2:

[0666] The chatbot server sends the received inquiry to the AI ​​engine and requests it to generate an answer. The input is chat data, and the output is the data sent in the HTTP request.

[0667] Step 3:

[0668] The emotion engine recognizes emotions from the customer's text and determines the appropriate response. The input is the customer's text data, and the output is the emotion analysis result.

[0669] Step 4:

[0670] The chatbot server receives the answer generated by the AI ​​engine. The input is the HTTP response from the AI ​​engine, and the output is the generated answer data.

[0671] Step 5:

[0672] The chatbot server sends the generated answer back to the user's device. The input is the generated answer data, and the output is the answer displayed in the customer's chat window.

[0673] This reduces the burden on operators and makes the operation of online shopping sites more efficient.

[0674] (Application example 2)

[0675] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0676] Managing product images and product descriptions on e-commerce sites, analyzing the site, and streamlining customer support are important, but these require a great deal of time and effort. Even in physical stores, product descriptions, inventory checks, and customer support must be carried out quickly and appropriately, but traditional methods place a heavy burden on staff. Furthermore, analyzing customer sentiment in real-time customer support can be difficult, making it difficult to provide an appropriate response.

[0677] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically removing background, adjusting color, and resizing to optimize product images; means for automatically generating attractive copy based on detailed product information; means for recognizing products using a device and displaying descriptions and inventory information in real time; means for generating appropriate responses to customer inquiries and analyzing and responding to customer emotions; and means for suggesting appropriate responses based on customer emotions. This improves operational efficiency at e-commerce sites and physical stores, reduces the burden on staff, and improves customer satisfaction.

[0678] "Product image optimization" refers to the process of automatically removing the background of product images, adjusting their color, and resizing them.

[0679] "Automatic copy generation" refers to the use of AI to automatically generate attractive product descriptions based on detailed product information.

[0680] "Device-based product recognition" refers to using a device such as smart glasses to scan products and recognize them in real time.

[0681] "Real-time display of product description and inventory information" refers to instantly displaying a product description and inventory information when a product is recognized.

[0682] "Generating appropriate responses to customer inquiries" refers to using AI to automatically generate appropriate responses based on the content of customer inquiries.

[0683] "Customer sentiment analysis" refers to analyzing the emotions expressed by customers' inquiries and comments and determining the appropriate response method.

[0684] "Emotion-based response suggestions" refers to suggesting appropriate response methods to staff based on the results of analyzing the customer's emotions.

[0685] A system embodying the present invention includes the following configuration: a server provides means for automatically removing backgrounds, adjusting colors, and resizing product images to optimize them; a server also includes means for automatically generating attractive copy based on detailed product information; a server also includes means for recognizing products using a device and displaying product descriptions and inventory information in real time; a server also includes means for generating appropriate responses to customer inquiries, analyzing and responding to customer sentiment, and suggesting appropriate responses based on the customer sentiment.

[0686] A specific embodiment of the system will now be described.

[0687] Hardware:

[0688] Smart glasses: Built-in camera, display, and microphone.

[0689] Server: Runs the AI ​​image processing engine, AI text generation engine, and sentiment analysis engine.

[0690] Device (smart glasses)

[0691] software:

[0692] Python: Used to implement the program.

[0693] OpenCV: Used for image processing.

[0694] Transformers (Hugging Face): Used for text generation using GPT-3.

[0695] SentimentAnalyzer (custom module): Used for voice sentiment analysis.

[0696] InventoryChecker (custom module): Used to check inventory.

[0697] Data processing and calculation:

[0698] The server receives product images taken by the smart glasses' camera and sends them to the image processing engine. The image processing engine recognizes the product, removes the background, adjusts the color, and resizes it. Based on the recognized product ID, detailed product information is obtained and input as a prompt to the generative AI model. The generated text (product description) and stock information are displayed in real time on the smart glasses.

[0699] When a customer makes an inquiry, the server receives the voice data, analyzes the voice, and analyzes the emotions expressed. Based on the results of the emotion analysis, the server suggests an appropriate response.

[0700] Examples:

[0701] Product Recognition Prompt:

[0702] Product information: Brand: Example Brand, Model: 12345, Material: 100% Cotton, Color: Blue, Size: M. Please create a description based on this.

[0703] Customer Sentiment Analysis Prompt:

[0704] Customer inquiry: "I think the price of this product is too high."

[0705] Please suggest an appropriate response to this.

[0706] This will improve operational efficiency on e-commerce sites and in physical stores. Not only will staff be able to explain products, check inventory, and respond to customers quickly and appropriately, but customer satisfaction will also increase as they will be able to respond with consideration for customer feelings.

[0707] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0708] Step 1:

[0709] A user uses smart glasses to scan an image of a product.

[0710] Specific operation: The camera in the smart glasses captures product images and sends the image data to the server.

[0711] Input: Product image

[0712] Output: Product image sent to the server

[0713] Step 2:

[0714] The server receives the product images and sends them to the image processing engine.

[0715] Specific operation: The received image data is processed using OpenCV to remove background, adjust color, and resize.

[0716] Input: Product image data

[0717] Output: Optimized product images

[0718] Step 3:

[0719] The server sends the optimized product images to an AI image processing engine, which recognizes the products.

[0720] Specific operation: The AI ​​image processing engine analyzes the image and identifies the product ID.

[0721] Input: Optimized product images

[0722] Output: Product ID

[0723] Step 4:

[0724] The server retrieves the product details from the database based on the product ID.

[0725] Specific behavior: Executes a database query to retrieve product-related information (features, materials, price, etc.).

[0726] Input: Product ID

[0727] Output: Product details

[0728] Step 5:

[0729] The detailed information obtained by the server is input into the generative AI model as a prompt sentence to generate a product description.

[0730] Specific operation: A prompt sentence is input into a generative AI model (e.g., GPT-3) to generate an attractive product description.

[0731] Input: Product details

[0732] Output: Product description

[0733] Step 6:

[0734] The server sends the generated product description and inventory information to the smart glasses.

[0735] Specific operation: Product description and stock information are displayed in text format on the smart glasses display.

[0736] Input: Product description, stock information

[0737] Output: Product description and stock information displayed on smart glasses

[0738] Step 7:

[0739] The user receives an inquiry from a customer and transmits voice data to the server through the smart glasses.

[0740] Specific operation: The smart glasses capture audio data and send it to the server.

[0741] Input: Customer inquiry voice data

[0742] Output: Audio data sent to the server

[0743] Step 8:

[0744] The server analyzes the voice data, converts the customer's inquiry into text, and analyzes emotions.

[0745] How it works: The speech analysis engine converts speech data into text, and the sentiment analysis engine identifies customer sentiment from the text.

[0746] Input: Customer inquiry voice data

[0747] Output: Customer sentiment analysis results

[0748] Step 9:

[0749] Based on the results of the sentiment analysis, the server generates an appropriate response method and displays it as a suggestion on the smart glasses.

[0750] Specific operation: The generative AI model creates prompts based on the results of sentiment analysis and generates responses, which are displayed on the smart glasses.

[0751] Input: Customer sentiment analysis results

[0752] Output: Suggested actions displayed on the smart glasses

[0753] This allows users to quickly provide product descriptions and inventory information, enabling them to respond appropriately to customers.

[0754] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0755] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0756] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0757] [Second embodiment]

[0758] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0759] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0760] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0761] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0762] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0763] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0764] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0765] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0766] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0767] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0768] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0769] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0770] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[0771] 1. Product image automatic editing module

[0772] overview:

[0773] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[0774] What happens:

[0775] The user uploads a product image on the EC management screen.

[0776] The server receives the uploaded image and temporarily stores it.

[0777] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[0778] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[0779] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[0780] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[0781] Examples:

[0782] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[0783] 2. Automatic copy generation module

[0784] overview:

[0785] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[0786] What happens:

[0787] The user enters and saves new product information (features, size, material, etc.).

[0788] The server stores the new product information in a database.

[0789] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[0790] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0791] Examples:

[0792] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[0793] 3. Site Analysis Automation Module

[0794] overview:

[0795] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[0796] What happens:

[0797] The server periodically retrieves site analytics data via the Google Analytics API.

[0798] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement.

[0799] The server converts the received analysis results into a report format and notifies the operator of the generated report.

[0800] Examples:

[0801] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[0802] 4. Customer Support AI Chatbot

[0803] overview:

[0804] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[0805] What happens:

[0806] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[0807] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's sentiment to determine how to respond.

[0808] The chatbot server returns the generated answer to the customer.

[0809] Examples:

[0810] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[0811] In this way, a system is provided that automates various tasks related to operating an e-commerce site and reduces the burden on operators.

[0812] The processing flow will be explained below.

[0813] Product image automatic editing module

[0814] Processing Steps:

[0815] Step 1:

[0816] The user uploads a product image on the EC management screen.

[0817] Step 2:

[0818] The server receives the uploaded image and temporarily stores it.

[0819] Step 3:

[0820] The server sends the image to the AI ​​image processing engine and requests a background removal task.

[0821] Step 4:

[0822] The AI ​​image processing engine identifies the background of the image and removes it.

[0823] Step 5:

[0824] The AI ​​image processing engine returns the image with the background removed to the server.

[0825] Step 6:

[0826] The server requests a color adjustment task and sends the background-removed image back to the AI ​​image processing engine.

[0827] Step 7:

[0828] The AI ​​image processing engine adjusts the color tone of the image to create attractive colors.

[0829] Step 8:

[0830] The AI ​​image processing engine sends the color-adjusted image back to the server.

[0831] Step 9:

[0832] The server receives the color-adjusted image and resizes it to the optimal image size.

[0833] Step 10:

[0834] The server saves the final edited image in a database and reflects it on the product page of the e-commerce site.

[0835] Automatic copy generation module

[0836] Processing Steps:

[0837] Step 1:

[0838] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[0839] Step 2:

[0840] The server stores the new product information in a database.

[0841] Step 3:

[0842] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[0843] Step 4:

[0844] The AI ​​text generation engine analyzes the product's features and generates compelling copy.

[0845] Step 5:

[0846] The AI ​​text generation engine sends the generated text back to the server.

[0847] Step 6:

[0848] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0849] Site analysis automation module

[0850] Processing Steps:

[0851] Step 1:

[0852] The server uses the Google Analytics API to retrieve site analytics data periodically (e.g. daily, weekly).

[0853] Step 2:

[0854] The server sends the acquired analysis data to the AI ​​analysis engine.

[0855] Step 3:

[0856] An AI analytics engine analyzes traffic patterns and user behavior.

[0857] Step 4:

[0858] The AI ​​analysis engine extracts areas for improvement on the site and generates specific improvement suggestions.

[0859] Step 5:

[0860] The improvement suggestions generated by the AI ​​analysis engine are sent back to the server.

[0861] Step 6:

[0862] The server formats the analysis results it receives into a report format.

[0863] Step 7:

[0864] The server will then email the generated report to the site operator or display it in the admin panel.

[0865] Customer Support AI Chatbot

[0866] Processing Steps:

[0867] Step 1:

[0868] A user (customer) makes an inquiry to a chatbot on an e-commerce site.

[0869] Step 2:

[0870] The customer terminal sends the inquiry to the chatbot server.

[0871] Step 3:

[0872] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[0873] Step 4:

[0874] The AI ​​engine analyzes the inquiry and generates an appropriate answer.

[0875] Step 5:

[0876] The AI ​​engine analyzes the sentiment from the customer's text and determines the best way to respond.

[0877] Step 6:

[0878] The chatbot server returns the generated answer to the user's terminal.

[0879] Step 7:

[0880] The user (customer) receives the answer and takes the next action (e.g., purchase, ask additional questions).

[0881] The above are the specific processing steps in each module.

[0882] Example 1

[0883] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0884] Traditional e-commerce site operations required a great deal of time and effort to edit product images, create product descriptions, analyze the site, and respond to customers. Performing these tasks manually increased the burden on operators and hindered efficient operations. Furthermore, responding in a way that takes customer feelings into consideration required advanced expertise, making it difficult to respond quickly and appropriately.

[0885] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0886] In this invention, the server includes means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating product descriptions based on detailed product information, means for acquiring analytical data, analyzing website improvements, and generating improvement proposals, means for generating appropriate responses to customer inquiries, and analyzing and responding to customer sentiments, means for receiving product images and saving them in a temporary storage area, means for sending product images to an AI image processing engine and requesting a background removal task, means for sending the image with the background removed to the AI ​​image processing engine and requesting a color adjustment task, means for resizing the color-adjusted image, and means for storing the edited image in a database. and reflecting it on the product page, means for inputting and saving product features, means for saving the saved product information in a database, means for sending the product features to an AI text generation engine and generating a product description, means for saving the generated product description in a database and reflecting it on the product page, means for acquiring data from an analysis platform, means for sending the data to an AI analysis engine and extracting improvements, means for formatting the generated improvement proposals into a report and notifying an operator, means for sending the inquiry content to a chatbot server and requesting an answer generation task, and means for responding to the customer with an answer and sending an additional message that takes emotions into consideration. This makes it possible to significantly reduce the time and effort required to operate an e-commerce site and reduce the burden on the operator.

[0887] "Product Image" means a digital image uploaded to an e-commerce site for the visual representation of a product.

[0888] "Background removal" is the process of identifying and removing unnecessary background parts from product images.

[0889] "Color adjustment" is the process of adjusting the color tone, brightness, contrast, etc. of a product image to an optimal state.

[0890] "Resize" is the operation of converting the size of a product image to the optimal dimensions for display or storage.

[0891] "Detailed product information" is data that includes specific information such as product features, size, material, and price.

[0892] A "product description" is automatically generated text that describes a product in an attractive way.

[0893] "Analytics Data" is a collection of information about website usage and user behavior.

[0894] "Improvements" are specific changes or actions you take to improve your website's performance.

[0895] An "inquiry" is a question or request that a customer makes to the operator regarding a product or service.

[0896] "Analyzing sentiment" is the act of identifying and evaluating the emotions and tone that customers express through their inquiries and feedback.

[0897] A "server" is a computer system that processes, stores, and provides network services.

[0898] An "AI image processing engine" is a software system that uses artificial intelligence technology to automatically edit images.

[0899] An "AI text generation engine" is a software system that uses artificial intelligence technology to automatically generate text in natural language.

[0900] A "report" is a document that organizes analysis results and improvement proposals and provides them to operators.

[0901] A "chatbot server" is a server system that automatically responds to inquiries from customers.

[0902] "Transmission" is the act of moving data or information from one system to another.

[0903] A "task" is an individual process or unit of work that a system executes.

[0904] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[0905] Product image automatic editing module

[0906] overview:

[0907] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[0908] Hardware and software:

[0909] Server: Manages image processing tasks and interacts with the database.

[0910] AI image processing engine: Image processing software such as Adobe Photoshop API and CorelDRAW API.

[0911] Database: Stores and manages image data.

[0912] explanation:

[0913] The user uploads a product image on the e-commerce management screen. The server receives the uploaded image and temporarily stores it. Next, the server sends the image to the AI ​​image processing engine and requests a background removal task. The AI ​​image processing engine identifies and removes the background from the image. The server then sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. After the color-adjusted image is received by the server, it is resized to the appropriate size. Finally, the edited image is saved in the database and reflected on the product page of the e-commerce site.

[0914] Examples:

[0915] When a user uploads a new product image, the server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the server optimizes the image size and saves it in the format that will be displayed on the website.

[0916] Example prompt:

[0917] "New product image uploaded. Remove background, adjust color, and resize for optimal fit."

[0918] Automatic copy generation module

[0919] overview:

[0920] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[0921] Hardware and software:

[0922] Server: Manages product data and copy generation tasks.

[0923] AI text generation engines: Text generation software such as GPT-3 and BERT.

[0924] Database: Stores and manages product information.

[0925] explanation:

[0926] The user enters and saves new product information (features, size, material, etc.). The server saves the new product information in a database. The server then sends the new product information to an AI text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates appealing copy. The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[0927] Examples:

[0928] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[0929] Example prompt:

[0930] "Generate an attractive product description of 100 characters or less based on the new product information."

[0931] Site analysis automation module

[0932] overview:

[0933] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[0934] Hardware and software:

[0935] Server: Acquires and manages analysis data.

[0936] AI analytics engine: Data analytics software such as BigQuery and Data Studio.

[0937] Database: Stores and manages analysis results.

[0938] explanation:

[0939] The server periodically obtains website analysis data via the Google Analytics API. The server then sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior and identifies areas for improvement. The server then formats the analysis results into a report and notifies the operator.

[0940] Examples:

[0941] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[0942] Example prompt:

[0943] "Generate a report with site improvements based on this week's Google Analytics data."

[0944] Customer Support AI Chatbot

[0945] overview:

[0946] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[0947] Hardware and software:

[0948] Server: Responsible for query management and response generation.

[0949] AI engine: Chatbot software such as Dialogflow, IBM Watson, etc.

[0950] Database: Stores and manages inquiry details and response records.

[0951] explanation:

[0952] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server. The chatbot server then sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's emotions to determine how to respond. The chatbot server then returns the generated answer to the customer.

[0953] Examples:

[0954] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[0955] Example prompt:

[0956] "Use sentiment analysis to generate appropriate answers to questions that customers express emotions about."

[0957] In this way, each module works together to automate the operation of the e-commerce site, realizing a system that reduces the burden on operators.

[0958] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0959] Product image automatic editing module

[0960] Step 1:

[0961] The user uploads a product image on the EC management screen.

[0962] Input: The user specifies the image file for the product and clicks the upload button.

[0963] Specific operation: Product images are sent from the user's device to the server.

[0964] Output: Product images are temporarily saved on the server.

[0965] Step 2:

[0966] The server receives the uploaded product images and stores them in a temporary storage area.

[0967] Input: Product image file sent from the user's device.

[0968] Specific operation: The server stores the product image in a temporary storage area.

[0969] Output: Product image files saved in temporary storage area.

[0970] Step 3:

[0971] The server retrieves the product image from the temporary storage area and requests the background removal task from the AI ​​image processing engine.

[0972] Input: Product image file saved in temporary storage area.

[0973] Specific operation: The server sends the image to an AI image processing engine (e.g., Adobe Photoshop API) and instructs it to perform the background removal task.

[0974] Output: Product image files with background removed.

[0975] Step 4:

[0976] The server sends the background-removed image to the AI ​​image processing engine and requests a color adjustment task.

[0977] Input: Background removed product image file.

[0978] Specific operation: The server again sends the image to the AI ​​image processing engine and instructs it to perform color adjustment tasks.

[0979] Output: Color-adjusted product image files.

[0980] Step 5:

[0981] The server resizes the color-adjusted image.

[0982] Input: Color adjusted product image files.

[0983] What happens: The server resizes the image using a built-in image processing library (e.g., Pillow).

[0984] Output: Resized product image files.

[0985] Step 6:

[0986] The server saves the edited product images in a database and reflects them on the product page of the e-commerce site.

[0987] Input: Resized product image files.

[0988] Specific operation: The server saves the image in the database and reflects the image URL on the product page.

[0989] Output: Optimized product images that are displayed on the product page of your ecommerce site.

[0990] Automatic copy generation module

[0991] Step 1:

[0992] The user enters and saves new product information (features, size, material, etc.).

[0993] Input: The user enters details about the new product into an input form.

[0994] Specific operation: Information entered from the user's terminal is sent to the server.

[0995] Output: New product information is saved on the server.

[0996] Step 2:

[0997] The server stores the new product information in a database.

[0998] Input: New product information submitted by the user.

[0999] Specific operation: The server stores the new product information in the database.

[1000] Output: New product information stored in the database.

[1001] Step 3:

[1002] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[1003] Input: New product information stored in the database.

[1004] Specific operation: The server sends product information to an AI text generation engine (e.g., GPT-3) and instructs it to generate a copy.

[1005] Output: The generated product description.

[1006] Step 4:

[1007] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1008] Input: The generated product description.

[1009] Specific operation: The server saves the product description in the database and reflects it on the product page.

[1010] Output: Product description displayed on the product page of the e-commerce site.

[1011] Site analysis automation module

[1012] Step 1:

[1013] The server periodically retrieves site analytics data via the Google Analytics API.

[1014] Input: Analytics data obtained from Google Analytics.

[1015] Specific operation: The server connects to the Google Analytics API and retrieves analytics data.

[1016] Output: The acquired analysis data.

[1017] Step 2:

[1018] The server sends the analysis data to the AI ​​analysis engine and requests a data analysis task.

[1019] Input: Acquired analytical data.

[1020] Specific operation: The server sends the analysis data to an AI analysis engine (e.g., BigQuery, Data Studio) and instructs it to analyze the data.

[1021] Output: Improvements extracted through data analysis.

[1022] Step 3:

[1023] The server formats the analysis results it receives into a report format and notifies the operator.

[1024] Input: Improvements extracted through data analysis.

[1025] Specific operation: The server prepares the analysis results in a report format (e.g., Excel, PDF).

[1026] Output: Report notifying operators.

[1027] Customer Support AI Chatbot

[1028] Step 1:

[1029] A user makes an inquiry to a chatbot on an e-commerce site.

[1030] Input: The query that the user types into the chatbot widget.

[1031] Specific operation: The user's inquiry is sent from the customer terminal to the chatbot server.

[1032] Output: The query received by the chatbot server.

[1033] Step 2:

[1034] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[1035] Input: The received inquiry.

[1036] Specific operation: The server sends the query content to an AI engine (e.g., Dialogflow, IBM Watson) and instructs it to generate an answer.

[1037] Output: The generated answer.

[1038] Step 3:

[1039] The chatbot server returns the generated answer to the customer.

[1040] Input: The generated answer.

[1041] Specific operation: The server sends the answer to the customer's terminal and displays it to the customer.

[1042] Output: The answer that is shown to the customer.

[1043] Step 4:

[1044] The chatbot server analyzes the customer's emotions and generates and sends additional messages that take their emotions into consideration.

[1045] Input: Customer sentiment data.

[1046] Specific operation: The server uses an AI engine to perform sentiment analysis and generate additional messages appropriate to the situation.

[1047] Output: Additional sentiment-sensitive messages sent to customers.

[1048] (Application example 1)

[1049] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1050] In operating an e-commerce site, tasks such as editing product images, generating product descriptions, analyzing site analytics data, and responding to customer inquiries require a lot of time and effort. Performing these tasks manually places a heavy burden on operators, hindering efficient operation. Furthermore, there is a need for an approach that allows these operations to be easily performed via smart devices.

[1051] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1052] In this invention, the server is a system including means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating attractive copy based on detailed product information, means for acquiring website analysis data, analyzing site improvements, and generating specific improvement proposals, and means for generating appropriate responses to customer inquiries and analyzing customer sentiments to respond accordingly, and the system is equipped with means for controlling these means via a smart device application, means for generating prompts for removing backgrounds, adjusting colors, and resizing product images, means for generating copy generation prompts based on detailed product information, and means for generating prompts for site improvement based on web analysis data. This automates various tasks involved in operating an e-commerce site, significantly reducing the burden on operators and enabling them to easily perform operations via smart devices.

[1053] "Optimizing product images" means removing the background from product images, adjusting the color, and resizing them to an appropriate size.

[1054] "Background removal" refers to identifying and removing background areas from product images.

[1055] "Color adjustment" refers to adjusting the color, brightness, etc. to improve the appearance of a product.

[1056] "Resizing" refers to resizing the product image to an appropriate size.

[1057] "Detailed product information" refers to information about the product, such as its features, size, and material.

[1058] "Automatically generating copy" refers to the use of artificial intelligence technology to automatically create attractive and appropriate product descriptions based on detailed product information.

[1059] "Website Analytics Data" refers to data such as website traffic, user behavior, and conversion rates.

[1060] "Site Improvements" means any changes or modifications needed to improve the performance and user experience of the Website.

[1061] "Specific improvement suggestions" refers to providing specific action plans and revisions based on areas for improvement on the site.

[1062] "Customer inquiries" refers to questions and requests from customers using the e-commerce site regarding product information, stock availability, returns and exchanges, etc.

[1063] "Generating appropriate responses" refers to automatically creating accurate and effective responses to customer inquiries.

[1064] "Analyzing customer emotions" refers to analyzing and understanding the customer's emotional state based on the content of their inquiry and their reaction.

[1065] "Smart device applications" refers to application software that can be used on smart devices such as smartphones and tablets.

[1066] A "prompt" refers to an input sentence used to give instructions or ask questions to artificial intelligence technology.

[1067] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate and analyze text.

[1068] This invention provides a series of automated systems to streamline e-commerce site operations and reduce the burden on operators. This system edits product images, generates product descriptions, analyzes websites, and responds to customer inquiries through smart device applications.

[1069] 1. Product image automatic editing module

[1070] When a user uploads a product image via a smart device application, the server receives and temporarily stores the image, then sends it to an AI image processing engine (such as TensorFlow or OpenCV) for background removal, color adjustment, and resizing.

[1071] Example: When you upload a picture of a new pair of sneakers, it will automatically have its background removed, its colors adjusted (whites are emphasized), and it will be resized to 200x200 pixels.

[1072] Example prompt:

[1073] Remove the background from your product images, adjust the colors, and resize them to the optimal size.

[1074] 2. Automatic copy generation module

[1075] When a user enters product information, the application sends the data to the server, which then requests an AI text generation engine (e.g., GPT-3) to generate a text based on the product information. The generated text is stored in a database and reflected on the e-commerce site.

[1076] Example: Enter the details of a new backpack and the following text is generated: "This backpack is made from durable materials and is comfortable to wear."

[1077] Example prompt:

[1078] "Generate compelling descriptions based on new product information."

[1079] 3. Site Analysis Automation Module

[1080] The server periodically retrieves website analytics data via APIs such as Google Analytics, sends it to an AI analytics engine, which analyzes traffic patterns and user behavior, and generates a report containing suggestions for improvement and notifies the website operator.

[1081] Example: A report includes a specific suggestion for improvement: "Page B has a low conversion rate and needs improvement."

[1082] Example prompt:

[1083] "Identify areas for improvement on your website based on Google Analytics data."

[1084] 4. AI Customer Support Chatbots

[1085] When a user makes an inquiry via a smart device application, the chatbot server receives the inquiry and sends it to the AI ​​engine to generate an appropriate answer. It also performs sentiment analysis and determines how to respond.

[1086] Example: When a customer asks, "What's the status of my order?", the chatbot responds, "Your order is currently being prepared for shipping." If a customer expresses dissatisfaction, the chatbot responds, "Sorry for the wait. We'll get back to you as soon as possible."

[1087] Example prompt:

[1088] "Generate appropriate responses to customer queries and respond emotionally if necessary."

[1089] In this way, the system of the present invention utilizes smart device applications to make the operation of an EC site more efficient and reduce the burden on the operator.

[1090] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1091] Step 1:

[1092] The user takes or selects and uploads a product image through a smart device application.

[1093] Input: Product image file.

[1094] How it works: The application transfers the image to a cloud server.

[1095] Output: Raw images uploaded to the server.

[1096] Step 2:

[1097] The server temporarily stores the received product image.

[1098] Input: Product image sent from a smart device.

[1099] How it works: The server stores image files in a dedicated directory.

[1100] Output: Temporarily saved product image files.

[1101] Step 3:

[1102] The server sends the image to an AI image processing engine (e.g., TensorFlow or OpenCV) and requests background removal.

[1103] Input: Temporarily saved product image file.

[1104] How it works: The server generates a prompt to the AI ​​engine and requests an image processing task.

[1105] Output: Product image with background removed.

[1106] Step 4:

[1107] The server sends the background-removed image back to the AI ​​image processing engine, requesting color adjustment and resizing.

[1108] Input: Product image with background removed.

[1109] How it works: The server generates a prompt for color adjustment and resizing and requests the AI ​​engine to process it.

[1110] Output: Color adjusted and resized product images.

[1111] Step 5:

[1112] The server saves the processed product images in a database and reflects them on the product page of the e-commerce site.

[1113] Input: Optimized product images.

[1114] Operation: The server saves the image to the database and updates the page on the e-commerce site.

[1115] Output: Updated e-commerce product page.

[1116] Step 6:

[1117] The user enters detailed product information into a smart device application and submits it.

[1118] Input: Product details (features, size, material, etc.).

[1119] Action: The application transfers the input data to the server.

[1120] Output: Product details received by the server.

[1121] Step 7:

[1122] The server sends the received product details to an AI text generation engine (e.g., GPT-3) and requests it to generate a product description.

[1123] Input: Product details.

[1124] How it works: The server generates a prompt to the AI ​​engine and asks it to perform a text generation task.

[1125] Output: The generated product description.

[1126] Step 8:

[1127] The server saves the generated product description in a database and reflects it on the product page of the e-commerce site.

[1128] Input: Product description.

[1129] What happens: The server saves the text to a database and updates the page on the e-commerce site.

[1130] Output: Updated e-commerce product page.

[1131] Step 9:

[1132] The server periodically collects analytics data such as Google Analytics.

[1133] Input: Web analytics data.

[1134] How it works: The server calls the analytics platform's API to retrieve data.

[1135] Output: Captured web analytics data.

[1136] Step 10:

[1137] The server sends the acquired analytical data to the AI ​​analysis engine, requesting it to analyze areas for improvement and generate a report.

[1138] Input: Web analytics data.

[1139] How it works: The server generates a prompt to the AI ​​analytics engine, requesting a data analysis task.

[1140] Output: A report containing generated improvement suggestions.

[1141] Step 11:

[1142] The server notifies the operator of the improvement proposal.

[1143] Input: Report with improvement suggestions.

[1144] Operation: The server notifies the operator of the report to his / her smart device.

[1145] Output: Report notified to the operator.

[1146] Step 12:

[1147] Users and customers make inquiries via smart device applications.

[1148] Input: Enquiry details.

[1149] How it works: The application sends the query data to the chatbot server.

[1150] Output: The query received by the server.

[1151] Step 13:

[1152] The chatbot server sends the received inquiry to the AI ​​engine, requesting answer generation and sentiment analysis.

[1153] Input: Enquiry details.

[1154] How it works: The server generates prompts for the AI ​​engine and assigns it answer generation and sentiment analysis tasks.

[1155] Output: Generated answers and sentiment analysis results.

[1156] Step 14:

[1157] The chatbot server responds to the customer with the generated answer and takes appropriate action based on the results of sentiment analysis.

[1158] Input: Generated answers and sentiment analysis results.

[1159] What it does: The server sends a response and, if necessary, responds based on the emotion.

[1160] Output: Answers returned to the customer and appropriate responses.

[1161] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1162] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[1163] 1. Product image automatic editing module

[1164] overview:

[1165] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[1166] What happens:

[1167] The user uploads a product image on the EC management screen.

[1168] The server receives the uploaded image and temporarily stores it.

[1169] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[1170] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[1171] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[1172] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[1173] Examples:

[1174] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[1175] 2. Automatic copy generation module

[1176] overview:

[1177] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[1178] What happens:

[1179] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[1180] The server stores the new product information in a database.

[1181] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[1182] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1183] Examples:

[1184] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[1185] 3. Site Analysis Automation Module

[1186] overview:

[1187] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[1188] What happens:

[1189] The server periodically retrieves site analytics data via the Google Analytics API.

[1190] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement.

[1191] The server converts the received analysis results into a report format and notifies the operator of the generated report.

[1192] Examples:

[1193] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[1194] 4. Customer Support AI Chatbots Combined with Emotion Engines

[1195] overview:

[1196] The AI ​​chatbot responds to customer inquiries 24 hours a day, using an emotion engine to analyze customer emotions and provide appropriate responses.

[1197] What happens:

[1198] A user (customer) makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[1199] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the sentiment.

[1200] The emotion engine recognizes emotions from customer text and determines the appropriate response.

[1201] The chatbot server returns the generated answer to the user's terminal.

[1202] Examples:

[1203] If an operator introduces a chatbot and emotion engine and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's emotions, such as, "We will do our best to respond quickly."

[1204] In this way, a system is provided that automates various tasks related to operating an e-commerce site and reduces the burden on operators.

[1205] The processing flow will be explained below.

[1206] Product image automatic editing module

[1207] Processing Steps:

[1208] Step 1:

[1209] The user uploads a product image on the EC management screen.

[1210] Step 2:

[1211] The server receives the uploaded image and temporarily stores it.

[1212] Step 3:

[1213] The server sends the image to the AI ​​image processing engine and requests a background removal task.

[1214] Step 4:

[1215] The AI ​​image processing engine identifies the background of the image and removes it.

[1216] Step 5:

[1217] The AI ​​image processing engine returns the image with the background removed to the server.

[1218] Step 6:

[1219] The server requests a color adjustment task and sends the background-removed image back to the AI ​​image processing engine.

[1220] Step 7:

[1221] The AI ​​image processing engine adjusts the color tone of the image to create attractive colors.

[1222] Step 8:

[1223] The AI ​​image processing engine sends the color-adjusted image back to the server.

[1224] Step 9:

[1225] The server receives the color-adjusted image and resizes it to the optimal image size.

[1226] Step 10:

[1227] The server saves the final edited image in a database and reflects it on the product page of the e-commerce site.

[1228] Automatic copy generation module

[1229] Processing Steps:

[1230] Step 1:

[1231] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[1232] Step 2:

[1233] The server stores the new product information in a database.

[1234] Step 3:

[1235] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[1236] Step 4:

[1237] The AI ​​text generation engine analyzes the product's features and generates compelling copy.

[1238] Step 5:

[1239] The AI ​​text generation engine sends the generated text back to the server.

[1240] Step 6:

[1241] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1242] Site analysis automation module

[1243] Processing Steps:

[1244] Step 1:

[1245] The server uses the Google Analytics API to retrieve site analytics data periodically (e.g. daily, weekly).

[1246] Step 2:

[1247] The server sends the acquired analysis data to the AI ​​analysis engine.

[1248] Step 3:

[1249] An AI analytics engine analyzes traffic patterns and user behavior.

[1250] Step 4:

[1251] The AI ​​analysis engine extracts areas for improvement on the site and generates specific improvement suggestions.

[1252] Step 5:

[1253] The improvement suggestions generated by the AI ​​analysis engine are sent back to the server.

[1254] Step 6:

[1255] The server formats the analysis results it receives into a report format.

[1256] Step 7:

[1257] The server will then email the generated report to the site operator or display it in the admin panel.

[1258] Customer support AI chatbot combined with emotion engine

[1259] Processing Steps:

[1260] Step 1:

[1261] A user (customer) makes an inquiry to a chatbot on an e-commerce site.

[1262] Step 2:

[1263] The customer terminal sends the inquiry to the chatbot server.

[1264] Step 3:

[1265] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[1266] Step 4:

[1267] The AI ​​engine analyzes the inquiry and generates an appropriate answer.

[1268] Step 5:

[1269] The emotion engine recognizes emotions from customer text and determines the appropriate response.

[1270] Step 6:

[1271] The chatbot server returns the generated answer to the user's terminal.

[1272] Step 7:

[1273] The user (customer) receives the answer and takes the next action (e.g., purchase, ask additional questions).

[1274] Example 2

[1275] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1276] On online shopping sites, managing the quality of product images, creating attractive product descriptions, improving website usability, and streamlining customer support are major burdens for operators. While automating these tasks would be desirable to reduce operational costs and improve user experience, there are still not enough systems available to achieve this.

[1277] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1278] In this invention, the server includes means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating attractive copy based on detailed product information, means for acquiring website analysis data, analyzing site improvements, and generating specific improvement proposals, means for generating appropriate responses to customer inquiries and analyzing and responding to customer sentiment, means for utilizing an external image processing engine, means for utilizing an external text generation engine, means for utilizing an external analysis platform, and means for analyzing customer sentiment using an external sentiment analysis engine and generating appropriate responses. This reduces the burden on operators and makes it possible to operate online shopping sites more efficiently.

[1279] "Product image optimization" means automatically removing backgrounds, adjusting colors, and resizing images to make them suitable for e-commerce sites.

[1280] "Background removal" is a process that removes the background from the product image, focusing only on the product.

[1281] "Color adjustment" is the process of adjusting the color tone, brightness, and contrast of product images to make them appear clearer and more attractive.

[1282] "Resizing" is the process of resizing the dimensions of product images to a size suitable for an e-commerce site.

[1283] "Automatic copy generation" refers to the automatic creation of attractive and purchasing-motivating text based on detailed product information.

[1284] "Website analytics data" refers to data on user behavior, such as the number of visitors to a website, the number of page views, the length of stay, and the bounce rate.

[1285] "Site Improvements" are areas that need to be fixed or changed to improve the website's usability or conversion rate.

[1286] An "AI image processing engine" is a program or system that uses machine learning and artificial intelligence technology to perform image editing processes (background removal, color adjustment, resizing, etc.).

[1287] An "AI text generation engine" is a program or system that automatically generates text (e.g., product descriptions) using natural language processing technology.

[1288] An "AI analytics engine" is a program or system that uses machine learning and artificial intelligence techniques to analyze large amounts of data and extract insights.

[1289] An "emotion analysis engine" is a program or system that detects and analyzes a speaker's emotions (e.g., joy, anger, sadness, etc.) from text data.

[1290] "External Analytics Platform" means a third-party service or system used to collect, store and analyze website analytics data.

[1291] "External Image Processing Engine" means a third-party image editing service or system used to perform processing such as background removal, color adjustment, or resizing of product images.

[1292] An "external text generation engine" is a third-party service or system that automatically generates text based on product feature information, etc.

[1293] This invention is a system that improves the efficiency of EC site operations and reduces the burden on operators. Below, we will explain the main modules that make up this system and how to implement it in detail.

[1294] Product image automatic editing module

[1295] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them using an external image processing engine (e.g., Adobe Photoshop API).

[1296] Hardware and software used:

[1297] Terminals, servers, and image processing engines used by users

[1298] Data processing and calculation:

[1299] 1. The user uploads a product image from the EC management screen.

[1300] 2. The server receives the image and temporarily stores it.

[1301] 3. The server sends the image to the image processing engine for background removal. The image processing engine identifies and removes the background of the image.

[1302] 4. The server receives the image with the background removed and sends it back to the image processing engine, requesting color adjustment.

[1303] 5. The server receives the color-adjusted image and optimizes its size.

[1304] 6. The server saves the edited image in the database and reflects it on the product page of the e-commerce site.

[1305] Examples:

[1306] A user uploads a new product image. The server receives the image, and the Adobe Photoshop API automatically removes the background and performs color adjustments. Finally, the server optimizes the image size and saves it in a format suitable for display on the website.

[1307] Example prompt sentence:

[1308] "Remove the background of this image, adjust the color, and resize it to the optimal size for your e-commerce site."

[1309] Automatic copy generation module

[1310] The server uses AI to automatically generate attractive product descriptions based on detailed product information retrieved from a product database. This process uses an external text generation engine (e.g., OpenAI GPT-4).

[1311] Hardware and software used:

[1312] The terminal, server, and text generation engine used by the user

[1313] Data processing and calculation:

[1314] 1. The user enters new product information (features, size, material, etc.) on the EC management screen and saves it.

[1315] 2. The server saves the new product information in the database.

[1316] 3. The server sends the new product information to the text generation engine and requests it to generate a copy. The text generation engine analyzes the product's features and generates an attractive copy.

[1317] 4. The server receives the generated draft and stores it in a database.

[1318] 5. The server reflects the text on the product page of the e-commerce site.

[1319] Examples:

[1320] When a new product is added, the server sends the product's characteristics to OpenAI GPT-4, which then generates a summary such as, "This T-shirt is made of 100% cotton and is extremely comfortable. Its casual design makes it suitable for any occasion."

[1321] Example prompt sentence:

[1322] "Create a compelling product description based on this product's features, size, and materials."

[1323] Site analysis automation module

[1324] The server analyzes the Google Analytics data and reports specific improvements to the site. This analysis is performed using an external analysis platform (e.g., Google Cloud AI).

[1325] Hardware and software used:

[1326] Server, analysis platform

[1327] Data processing and calculation:

[1328] 1. The server retrieves site analytics data via the Google Analytics API.

[1329] 2. The server sends the analysis data to the analysis platform and requests data analysis.

[1330] 3. The server receives the analysis results and formats them into a report.

[1331] 4. The server notifies the operator of the generated report.

[1332] Examples:

[1333] Every week, the server retrieves data from Google Analytics, and Google Cloud AI generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site's design and content.

[1334] Example prompt sentence:

[1335] "Please analyze this Google Analytics data and let us know how we can improve it."

[1336] Customer support AI chatbot combined with emotion engine

[1337] The server uses an AI chatbot to respond to customer inquiries 24 hours a day, analyzes customer emotions using an emotion engine, and responds appropriately. This process uses an external emotion analysis engine (e.g., IBM Watson Tone Analyzer).

[1338] Hardware and software used:

[1339] User devices, chatbot servers, and emotion analysis engines

[1340] Data processing and calculation:

[1341] 1. A user (customer) makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[1342] 2. The chatbot server sends the received inquiry to the AI ​​engine and requests it to generate an answer.

[1343] 3. The emotion engine recognizes emotions from the customer's text and determines the appropriate response.

[1344] 4. The chatbot server sends the generated answer back to the user's device.

[1345] Examples:

[1346] If an operator introduces a chatbot and emotion engine and a customer asks, "Please tell me the stock status of product A," the AI ​​will respond, "Product A is in stock." If the customer expresses dissatisfaction, the AI ​​will respond by taking their feelings into consideration, such as, "We will do our best to respond quickly."

[1347] Example prompt sentence:

[1348] "Analyze customer sentiment and generate relevant, responsive responses."

[1349] This system reduces the burden on operators and makes it possible to run online shopping sites more efficiently.

[1350] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1351] Product image automatic editing module

[1352] Step 1:

[1353] The user selects a product image on the EC admin screen and clicks the upload button. The input is the image file selected by the user, and the output is the image data included in the HTTP POST request.

[1354] Step 2:

[1355] The server receives image data sent by the user and temporarily stores it. The input is the image data received via an HTTP POST request, and the output is an image file saved in a temporary folder on the server.

[1356] Step 3:

[1357] The server sends the image to the image processing engine and requests background removal. The input is the image file saved in the temporary folder, and the output is the image data sent in the HTTP request.

[1358] Step 4:

[1359] The server receives the background-removed image. The input is the HTTP response from the image processing engine, and the output is the background-removed image file saved in a temporary folder on the server.

[1360] Step 5:

[1361] The server sends the image with the background removed to the image processing engine again and requests color adjustment. The input is the image file with the background removed, and the output is the image data sent in the HTTP request.

[1362] Step 6:

[1363] The server receives the color-adjusted image. The input is the HTTP response from the image processing engine, and the output is the color-adjusted image file saved in a temporary folder on the server.

[1364] Step 7:

[1365] The server resizes the color-adjusted image to the optimal size. The input is the color-adjusted image file, and the output is the resized image file. Specifically, the resizing process is performed using an image processing library.

[1366] Step 8:

[1367] The server saves the resized image in a database. The input is the resized image file, and the output is the image data saved in the database.

[1368] Step 9:

[1369] The server reflects the image on the product page of the EC site. The input is the image data stored in the database, and the output is the image displayed on the product page of the EC site.

[1370] Automatic copy generation module

[1371] Step 1:

[1372] A user enters new product information (features, size, material, etc.) on the e-commerce management screen and clicks the save button. The input is the product information entered by the user, and the output is the product data included in the HTTP POST request.

[1373] Step 2:

[1374] The server saves the new product information to a database. The input is the product data received via an HTTP POST request, and the output is the product information saved in the database.

[1375] Step 3:

[1376] The server sends new product information to the text generation engine and requests it to generate text. The input is the product information stored in the database, and the output is the product data sent in the HTTP request.

[1377] Step 4:

[1378] The server receives the generated text from the text generation engine. The input is the HTTP response from the text generation engine, and the output is the generated text stored in the server's temporary memory.

[1379] Step 5:

[1380] The server stores the generated draft in a database. The input is the generated draft, and the output is the draft data stored in the database.

[1381] Step 6:

[1382] The server reflects the copy on the product page of the EC site. The input is the copy data stored in the database, and the output is the copy displayed on the product page of the EC site.

[1383] Site analysis automation module

[1384] Step 1:

[1385] The server periodically retrieves site analytics data via the Google Analytics API. The input is the API request, and the output is the retrieved site analytics data.

[1386] Step 2:

[1387] The server sends the acquired analysis data to the analysis platform and requests data analysis. The input is the acquired analysis data, and the output is the data sent in the HTTP request.

[1388] Step 3:

[1389] The server receives the analysis results from the analysis platform. The input is the HTTP response from the analysis platform, and the output is the analysis results stored in the server's temporary memory.

[1390] Step 4:

[1391] The server formats the analysis results it receives into a report format. The input is the analysis results, and the output is the formatted report data. Specifically, a report is created using a report generation tool.

[1392] Step 5:

[1393] The server notifies the operator of the generated report. The input is the formatted report data and the output is the notification sent to the operator.

[1394] Customer support AI chatbot combined with emotion engine

[1395] Step 1:

[1396] A user (customer) makes an inquiry to a chatbot on an e-commerce site. The input is the inquiry entered by the customer, and the output is chat data.

[1397] Step 2:

[1398] The chatbot server sends the received inquiry to the AI ​​engine and requests it to generate an answer. The input is chat data, and the output is the data sent in the HTTP request.

[1399] Step 3:

[1400] The emotion engine recognizes emotions from the customer's text and determines the appropriate response. The input is the customer's text data, and the output is the emotion analysis result.

[1401] Step 4:

[1402] The chatbot server receives the answer generated by the AI ​​engine. The input is the HTTP response from the AI ​​engine, and the output is the generated answer data.

[1403] Step 5:

[1404] The chatbot server sends the generated answer back to the user's device. The input is the generated answer data, and the output is the answer displayed in the customer's chat window.

[1405] This reduces the burden on operators and makes the operation of online shopping sites more efficient.

[1406] (Application example 2)

[1407] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1408] Managing product images and product descriptions on e-commerce sites, analyzing the site, and streamlining customer support are important, but these require a great deal of time and effort. Even in physical stores, product descriptions, inventory checks, and customer support must be carried out quickly and appropriately, but traditional methods place a heavy burden on staff. Furthermore, analyzing customer sentiment in real-time customer support can be difficult, making it difficult to provide an appropriate response.

[1409] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically removing background, adjusting color, and resizing to optimize product images; means for automatically generating attractive copy based on detailed product information; means for recognizing products using a device and displaying descriptions and inventory information in real time; means for generating appropriate responses to customer inquiries and analyzing and responding to customer emotions; and means for suggesting appropriate responses based on customer emotions. This improves operational efficiency at e-commerce sites and physical stores, reduces the burden on staff, and improves customer satisfaction.

[1410] "Product image optimization" refers to the process of automatically removing the background of product images, adjusting their color, and resizing them.

[1411] "Automatic copy generation" refers to the use of AI to automatically generate attractive product descriptions based on detailed product information.

[1412] "Device-based product recognition" refers to using a device such as smart glasses to scan products and recognize them in real time.

[1413] "Real-time display of product description and inventory information" refers to instantly displaying a product description and inventory information when a product is recognized.

[1414] "Generating appropriate responses to customer inquiries" refers to using AI to automatically generate appropriate responses based on the content of customer inquiries.

[1415] "Customer sentiment analysis" refers to analyzing the emotions expressed by customers' inquiries and comments and determining the appropriate response method.

[1416] "Emotion-based response suggestions" refers to suggesting appropriate response methods to staff based on the results of analyzing the customer's emotions.

[1417] A system embodying the present invention includes the following configuration: a server provides means for automatically removing backgrounds, adjusting colors, and resizing product images to optimize them; a server also includes means for automatically generating attractive copy based on detailed product information; a server also includes means for recognizing products using a device and displaying product descriptions and inventory information in real time; a server also includes means for generating appropriate responses to customer inquiries, analyzing and responding to customer sentiment, and suggesting appropriate responses based on the customer sentiment.

[1418] A specific embodiment of the system will now be described.

[1419] Hardware:

[1420] Smart glasses: Built-in camera, display, and microphone.

[1421] Server: Runs the AI ​​image processing engine, AI text generation engine, and sentiment analysis engine.

[1422] Device (smart glasses)

[1423] software:

[1424] Python: Used to implement the program.

[1425] OpenCV: Used for image processing.

[1426] Transformers (Hugging Face): Used for text generation using GPT-3.

[1427] SentimentAnalyzer (custom module): Used for voice sentiment analysis.

[1428] InventoryChecker (custom module): Used to check inventory.

[1429] Data processing and calculation:

[1430] The server receives product images taken by the smart glasses' camera and sends them to the image processing engine. The image processing engine recognizes the product, removes the background, adjusts the color, and resizes it. Based on the recognized product ID, detailed product information is obtained and input as a prompt to the generative AI model. The generated text (product description) and stock information are displayed in real time on the smart glasses.

[1431] When a customer makes an inquiry, the server receives the voice data, analyzes the voice, and analyzes the emotions expressed. Based on the results of the emotion analysis, the server suggests an appropriate response.

[1432] Examples:

[1433] Product Recognition Prompt:

[1434] Product information: Brand: Example Brand, Model: 12345, Material: 100% Cotton, Color: Blue, Size: M. Please create a description based on this.

[1435] Customer Sentiment Analysis Prompt:

[1436] Customer inquiry: "I think the price of this product is too high."

[1437] Please suggest an appropriate response to this.

[1438] This will improve operational efficiency on e-commerce sites and in physical stores. Not only will staff be able to explain products, check inventory, and respond to customers quickly and appropriately, but customer satisfaction will also increase as they will be able to respond with consideration for customer feelings.

[1439] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1440] Step 1:

[1441] A user uses smart glasses to scan an image of a product.

[1442] Specific operation: The camera in the smart glasses captures product images and sends the image data to the server.

[1443] Input: Product image

[1444] Output: Product image sent to the server

[1445] Step 2:

[1446] The server receives the product images and sends them to the image processing engine.

[1447] Specific operation: The received image data is processed using OpenCV to remove background, adjust color, and resize.

[1448] Input: Product image data

[1449] Output: Optimized product images

[1450] Step 3:

[1451] The server sends the optimized product images to an AI image processing engine, which recognizes the products.

[1452] Specific operation: The AI ​​image processing engine analyzes the image and identifies the product ID.

[1453] Input: Optimized product images

[1454] Output: Product ID

[1455] Step 4:

[1456] The server retrieves the product details from the database based on the product ID.

[1457] Specific behavior: Executes a database query to retrieve product-related information (features, materials, price, etc.).

[1458] Input: Product ID

[1459] Output: Product details

[1460] Step 5:

[1461] The detailed information obtained by the server is input into the generative AI model as a prompt sentence to generate a product description.

[1462] Specific operation: A prompt sentence is input into a generative AI model (e.g., GPT-3) to generate an attractive product description.

[1463] Input: Product details

[1464] Output: Product description

[1465] Step 6:

[1466] The server sends the generated product description and inventory information to the smart glasses.

[1467] Specific operation: Product description and stock information are displayed in text format on the smart glasses display.

[1468] Input: Product description, stock information

[1469] Output: Product description and stock information displayed on smart glasses

[1470] Step 7:

[1471] The user receives an inquiry from a customer and transmits voice data to the server through the smart glasses.

[1472] Specific operation: The smart glasses capture audio data and send it to the server.

[1473] Input: Customer inquiry voice data

[1474] Output: Audio data sent to the server

[1475] Step 8:

[1476] The server analyzes the voice data, converts the customer's inquiry into text, and analyzes emotions.

[1477] How it works: The speech analysis engine converts speech data into text, and the sentiment analysis engine identifies customer sentiment from the text.

[1478] Input: Customer inquiry voice data

[1479] Output: Customer sentiment analysis results

[1480] Step 9:

[1481] Based on the results of the sentiment analysis, the server generates an appropriate response method and displays it as a suggestion on the smart glasses.

[1482] Specific operation: The generative AI model creates prompts based on the results of sentiment analysis and generates responses, which are displayed on the smart glasses.

[1483] Input: Customer sentiment analysis results

[1484] Output: Suggested actions displayed on the smart glasses

[1485] This allows users to quickly provide product descriptions and inventory information, enabling them to respond appropriately to customers.

[1486] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1487] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1488] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1489] [Third embodiment]

[1490] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1491] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1492] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1493] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1494] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1495] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1496] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1497] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1498] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1499] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1500] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1501] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1502] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[1503] 1. Product image automatic editing module

[1504] overview:

[1505] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[1506] What happens:

[1507] The user uploads a product image on the EC management screen.

[1508] The server receives the uploaded image and temporarily stores it.

[1509] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[1510] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[1511] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[1512] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[1513] Examples:

[1514] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[1515] 2. Automatic copy generation module

[1516] overview:

[1517] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[1518] What happens:

[1519] The user enters and saves new product information (features, size, material, etc.).

[1520] The server stores the new product information in a database.

[1521] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[1522] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1523] Examples:

[1524] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[1525] 3. Site Analysis Automation Module

[1526] overview:

[1527] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[1528] What happens:

[1529] The server periodically retrieves site analytics data via the Google Analytics API.

[1530] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement.

[1531] The server converts the received analysis results into a report format and notifies the operator of the generated report.

[1532] Examples:

[1533] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[1534] 4. Customer Support AI Chatbot

[1535] overview:

[1536] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[1537] What happens:

[1538] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[1539] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's sentiment to determine how to respond.

[1540] The chatbot server returns the generated answer to the customer.

[1541] Examples:

[1542] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[1543] In this way, a system is provided that automates various tasks related to operating an e-commerce site and reduces the burden on operators.

[1544] The processing flow will be explained below.

[1545] Product image automatic editing module

[1546] Processing Steps:

[1547] Step 1:

[1548] The user uploads a product image on the EC management screen.

[1549] Step 2:

[1550] The server receives the uploaded image and temporarily stores it.

[1551] Step 3:

[1552] The server sends the image to the AI ​​image processing engine and requests a background removal task.

[1553] Step 4:

[1554] The AI ​​image processing engine identifies the background of the image and removes it.

[1555] Step 5:

[1556] The AI ​​image processing engine returns the image with the background removed to the server.

[1557] Step 6:

[1558] The server requests a color adjustment task and sends the background-removed image back to the AI ​​image processing engine.

[1559] Step 7:

[1560] The AI ​​image processing engine adjusts the color tone of the image to create attractive colors.

[1561] Step 8:

[1562] The AI ​​image processing engine sends the color-adjusted image back to the server.

[1563] Step 9:

[1564] The server receives the color-adjusted image and resizes it to the optimal image size.

[1565] Step 10:

[1566] The server saves the final edited image in a database and reflects it on the product page of the e-commerce site.

[1567] Automatic copy generation module

[1568] Processing Steps:

[1569] Step 1:

[1570] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[1571] Step 2:

[1572] The server stores the new product information in a database.

[1573] Step 3:

[1574] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[1575] Step 4:

[1576] The AI ​​text generation engine analyzes the product's features and generates compelling copy.

[1577] Step 5:

[1578] The AI ​​text generation engine sends the generated text back to the server.

[1579] Step 6:

[1580] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1581] Site analysis automation module

[1582] Processing Steps:

[1583] Step 1:

[1584] The server uses the Google Analytics API to retrieve site analytics data periodically (e.g. daily, weekly).

[1585] Step 2:

[1586] The server sends the acquired analysis data to the AI ​​analysis engine.

[1587] Step 3:

[1588] An AI analytics engine analyzes traffic patterns and user behavior.

[1589] Step 4:

[1590] The AI ​​analysis engine extracts areas for improvement on the site and generates specific improvement suggestions.

[1591] Step 5:

[1592] The improvement suggestions generated by the AI ​​analysis engine are sent back to the server.

[1593] Step 6:

[1594] The server formats the analysis results it receives into a report format.

[1595] Step 7:

[1596] The server will then email the generated report to the site operator or display it in the admin panel.

[1597] Customer Support AI Chatbot

[1598] Processing Steps:

[1599] Step 1:

[1600] A user (customer) makes an inquiry to a chatbot on an e-commerce site.

[1601] Step 2:

[1602] The customer terminal sends the inquiry to the chatbot server.

[1603] Step 3:

[1604] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[1605] Step 4:

[1606] The AI ​​engine analyzes the inquiry and generates an appropriate answer.

[1607] Step 5:

[1608] The AI ​​engine analyzes the sentiment from the customer's text and determines the best way to respond.

[1609] Step 6:

[1610] The chatbot server returns the generated answer to the user's terminal.

[1611] Step 7:

[1612] The user (customer) receives the answer and takes the next action (e.g., purchase, ask additional questions).

[1613] The above are the specific processing steps in each module.

[1614] Example 1

[1615] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1616] Traditional e-commerce site operations required a great deal of time and effort to edit product images, create product descriptions, analyze the site, and respond to customers. Performing these tasks manually increased the burden on operators and hindered efficient operations. Furthermore, responding in a way that takes customer feelings into consideration required advanced expertise, making it difficult to respond quickly and appropriately.

[1617] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1618] In this invention, the server includes means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating product descriptions based on detailed product information, means for acquiring analytical data, analyzing website improvements, and generating improvement proposals, means for generating appropriate responses to customer inquiries, and analyzing and responding to customer sentiments, means for receiving product images and saving them in a temporary storage area, means for sending product images to an AI image processing engine and requesting a background removal task, means for sending the image with the background removed to the AI ​​image processing engine and requesting a color adjustment task, means for resizing the color-adjusted image, and means for storing the edited image in a database. and reflecting it on the product page, means for inputting and saving product features, means for saving the saved product information in a database, means for sending the product features to an AI text generation engine and generating a product description, means for saving the generated product description in a database and reflecting it on the product page, means for acquiring data from an analysis platform, means for sending the data to an AI analysis engine and extracting improvements, means for formatting the generated improvement proposals into a report and notifying an operator, means for sending the inquiry content to a chatbot server and requesting an answer generation task, and means for responding to the customer with an answer and sending an additional message that takes emotions into consideration. This makes it possible to significantly reduce the time and effort required to operate an e-commerce site and reduce the burden on the operator.

[1619] "Product Image" means a digital image uploaded to an e-commerce site for the visual representation of a product.

[1620] "Background removal" is the process of identifying and removing unnecessary background parts from product images.

[1621] "Color adjustment" is the process of adjusting the color tone, brightness, contrast, etc. of a product image to an optimal state.

[1622] "Resize" is the operation of converting the size of a product image to the optimal dimensions for display or storage.

[1623] "Detailed product information" is data that includes specific information such as product features, size, material, and price.

[1624] A "product description" is automatically generated text that describes a product in an attractive way.

[1625] "Analytics Data" is a collection of information about website usage and user behavior.

[1626] "Improvements" are specific changes or actions you take to improve your website's performance.

[1627] An "inquiry" is a question or request that a customer makes to the operator regarding a product or service.

[1628] "Analyzing sentiment" is the act of identifying and evaluating the emotions and tone that customers express through their inquiries and feedback.

[1629] A "server" is a computer system that processes, stores, and provides network services.

[1630] An "AI image processing engine" is a software system that uses artificial intelligence technology to automatically edit images.

[1631] An "AI text generation engine" is a software system that uses artificial intelligence technology to automatically generate text in natural language.

[1632] A "report" is a document that organizes analysis results and improvement proposals and provides them to operators.

[1633] A "chatbot server" is a server system that automatically responds to inquiries from customers.

[1634] "Transmission" is the act of moving data or information from one system to another.

[1635] A "task" is an individual process or unit of work that a system executes.

[1636] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[1637] Product image automatic editing module

[1638] overview:

[1639] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[1640] Hardware and software:

[1641] Server: Manages image processing tasks and interacts with the database.

[1642] AI image processing engine: Image processing software such as Adobe Photoshop API and CorelDRAW API.

[1643] Database: Stores and manages image data.

[1644] explanation:

[1645] The user uploads a product image on the e-commerce management screen. The server receives the uploaded image and temporarily stores it. Next, the server sends the image to the AI ​​image processing engine and requests a background removal task. The AI ​​image processing engine identifies and removes the background from the image. The server then sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. After the color-adjusted image is received by the server, it is resized to the appropriate size. Finally, the edited image is saved in the database and reflected on the product page of the e-commerce site.

[1646] Examples:

[1647] When a user uploads a new product image, the server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the server optimizes the image size and saves it in the format that will be displayed on the website.

[1648] Example prompt:

[1649] "New product image uploaded. Remove background, adjust color, and resize for optimal fit."

[1650] Automatic copy generation module

[1651] overview:

[1652] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[1653] Hardware and software:

[1654] Server: Manages product data and copy generation tasks.

[1655] AI text generation engines: Text generation software such as GPT-3 and BERT.

[1656] Database: Stores and manages product information.

[1657] explanation:

[1658] The user enters and saves new product information (features, size, material, etc.). The server saves the new product information in a database. The server then sends the new product information to an AI text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates appealing copy. The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1659] Examples:

[1660] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[1661] Example prompt:

[1662] "Generate an attractive product description of 100 characters or less based on the new product information."

[1663] Site analysis automation module

[1664] overview:

[1665] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[1666] Hardware and software:

[1667] Server: Acquires and manages analysis data.

[1668] AI analytics engine: Data analytics software such as BigQuery and Data Studio.

[1669] Database: Stores and manages analysis results.

[1670] explanation:

[1671] The server periodically obtains website analysis data via the Google Analytics API. The server then sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior and identifies areas for improvement. The server then formats the analysis results into a report and notifies the operator.

[1672] Examples:

[1673] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[1674] Example prompt:

[1675] "Generate a report with site improvements based on this week's Google Analytics data."

[1676] Customer Support AI Chatbot

[1677] overview:

[1678] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[1679] Hardware and software:

[1680] Server: Responsible for query management and response generation.

[1681] AI engine: Chatbot software such as Dialogflow, IBM Watson, etc.

[1682] Database: Stores and manages inquiry details and response records.

[1683] explanation:

[1684] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server. The chatbot server then sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's emotions to determine how to respond. The chatbot server then returns the generated answer to the customer.

[1685] Examples:

[1686] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[1687] Example prompt:

[1688] "Use sentiment analysis to generate appropriate answers to questions that customers express emotions about."

[1689] In this way, each module works together to automate the operation of the e-commerce site, realizing a system that reduces the burden on operators.

[1690] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1691] Product image automatic editing module

[1692] Step 1:

[1693] The user uploads a product image on the EC management screen.

[1694] Input: The user specifies the image file for the product and clicks the upload button.

[1695] Specific operation: Product images are sent from the user's device to the server.

[1696] Output: Product images are temporarily saved on the server.

[1697] Step 2:

[1698] The server receives the uploaded product images and stores them in a temporary storage area.

[1699] Input: Product image file sent from the user's device.

[1700] Specific operation: The server stores the product image in a temporary storage area.

[1701] Output: Product image files saved in temporary storage area.

[1702] Step 3:

[1703] The server retrieves the product image from the temporary storage area and requests the background removal task from the AI ​​image processing engine.

[1704] Input: Product image file saved in temporary storage area.

[1705] Specific operation: The server sends the image to an AI image processing engine (e.g., Adobe Photoshop API) and instructs it to perform the background removal task.

[1706] Output: Product image files with background removed.

[1707] Step 4:

[1708] The server sends the background-removed image to the AI ​​image processing engine and requests a color adjustment task.

[1709] Input: Background removed product image file.

[1710] Specific operation: The server again sends the image to the AI ​​image processing engine and instructs it to perform color adjustment tasks.

[1711] Output: Color-adjusted product image files.

[1712] Step 5:

[1713] The server resizes the color-adjusted image.

[1714] Input: Color adjusted product image files.

[1715] What happens: The server resizes the image using a built-in image processing library (e.g., Pillow).

[1716] Output: Resized product image files.

[1717] Step 6:

[1718] The server saves the edited product images in a database and reflects them on the product page of the e-commerce site.

[1719] Input: Resized product image files.

[1720] Specific operation: The server saves the image in the database and reflects the image URL on the product page.

[1721] Output: Optimized product images that are displayed on the product page of your ecommerce site.

[1722] Automatic copy generation module

[1723] Step 1:

[1724] The user enters and saves new product information (features, size, material, etc.).

[1725] Input: The user enters details about the new product into an input form.

[1726] Specific operation: Information entered from the user's terminal is sent to the server.

[1727] Output: New product information is saved on the server.

[1728] Step 2:

[1729] The server stores the new product information in a database.

[1730] Input: New product information submitted by the user.

[1731] Specific operation: The server stores the new product information in the database.

[1732] Output: New product information stored in the database.

[1733] Step 3:

[1734] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[1735] Input: New product information stored in the database.

[1736] Specific operation: The server sends product information to an AI text generation engine (e.g., GPT-3) and instructs it to generate a copy.

[1737] Output: The generated product description.

[1738] Step 4:

[1739] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1740] Input: The generated product description.

[1741] Specific operation: The server saves the product description in the database and reflects it on the product page.

[1742] Output: Product description displayed on the product page of the e-commerce site.

[1743] Site analysis automation module

[1744] Step 1:

[1745] The server periodically retrieves site analytics data via the Google Analytics API.

[1746] Input: Analytics data obtained from Google Analytics.

[1747] Specific operation: The server connects to the Google Analytics API and retrieves analytics data.

[1748] Output: The acquired analysis data.

[1749] Step 2:

[1750] The server sends the analysis data to the AI ​​analysis engine and requests a data analysis task.

[1751] Input: Acquired analytical data.

[1752] Specific operation: The server sends the analysis data to an AI analysis engine (e.g., BigQuery, Data Studio) and instructs it to analyze the data.

[1753] Output: Improvements extracted through data analysis.

[1754] Step 3:

[1755] The server formats the analysis results it receives into a report format and notifies the operator.

[1756] Input: Improvements extracted through data analysis.

[1757] Specific operation: The server prepares the analysis results in a report format (e.g., Excel, PDF).

[1758] Output: Report notifying operators.

[1759] Customer Support AI Chatbot

[1760] Step 1:

[1761] A user makes an inquiry to a chatbot on an e-commerce site.

[1762] Input: The query that the user types into the chatbot widget.

[1763] Specific operation: The user's inquiry is sent from the customer terminal to the chatbot server.

[1764] Output: The query received by the chatbot server.

[1765] Step 2:

[1766] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[1767] Input: The received inquiry.

[1768] Specific operation: The server sends the query content to an AI engine (e.g., Dialogflow, IBM Watson) and instructs it to generate an answer.

[1769] Output: The generated answer.

[1770] Step 3:

[1771] The chatbot server returns the generated answer to the customer.

[1772] Input: The generated answer.

[1773] Specific operation: The server sends the answer to the customer's terminal and displays it to the customer.

[1774] Output: The answer that is shown to the customer.

[1775] Step 4:

[1776] The chatbot server analyzes the customer's emotions and generates and sends additional messages that take their emotions into consideration.

[1777] Input: Customer sentiment data.

[1778] Specific operation: The server uses an AI engine to perform sentiment analysis and generate additional messages appropriate to the situation.

[1779] Output: Additional sentiment-sensitive messages sent to customers.

[1780] (Application example 1)

[1781] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1782] In operating an e-commerce site, tasks such as editing product images, generating product descriptions, analyzing site analytics data, and responding to customer inquiries require a lot of time and effort. Performing these tasks manually places a heavy burden on operators, hindering efficient operation. Furthermore, there is a need for an approach that allows these operations to be easily performed via smart devices.

[1783] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1784] In this invention, the server is a system including means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating attractive copy based on detailed product information, means for acquiring website analysis data, analyzing site improvements, and generating specific improvement proposals, and means for generating appropriate responses to customer inquiries and analyzing customer sentiments to respond accordingly, and the system is equipped with means for controlling these means via a smart device application, means for generating prompts for removing backgrounds, adjusting colors, and resizing product images, means for generating copy generation prompts based on detailed product information, and means for generating prompts for site improvement based on web analysis data. This automates various tasks involved in operating an e-commerce site, significantly reducing the burden on operators and enabling them to easily perform operations via smart devices.

[1785] "Optimizing product images" means removing the background from product images, adjusting the color, and resizing them to an appropriate size.

[1786] "Background removal" refers to identifying and removing background areas from product images.

[1787] "Color adjustment" refers to adjusting the color, brightness, etc. to improve the appearance of a product.

[1788] "Resizing" refers to resizing the product image to an appropriate size.

[1789] "Detailed product information" refers to information about the product, such as its features, size, and material.

[1790] "Automatically generating copy" refers to the use of artificial intelligence technology to automatically create attractive and appropriate product descriptions based on detailed product information.

[1791] "Website Analytics Data" refers to data such as website traffic, user behavior, and conversion rates.

[1792] "Site Improvements" means any changes or modifications needed to improve the performance and user experience of the Website.

[1793] "Specific improvement suggestions" refers to providing specific action plans and revisions based on areas for improvement on the site.

[1794] "Customer inquiries" refers to questions and requests from customers using the e-commerce site regarding product information, stock availability, returns and exchanges, etc.

[1795] "Generating appropriate responses" refers to automatically creating accurate and effective responses to customer inquiries.

[1796] "Analyzing customer emotions" refers to analyzing and understanding the customer's emotional state based on the content of their inquiry and their reaction.

[1797] "Smart device applications" refers to application software that can be used on smart devices such as smartphones and tablets.

[1798] A "prompt" refers to an input sentence used to give instructions or ask questions to artificial intelligence technology.

[1799] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate and analyze text.

[1800] This invention provides a series of automated systems to streamline e-commerce site operations and reduce the burden on operators. This system edits product images, generates product descriptions, analyzes websites, and responds to customer inquiries through smart device applications.

[1801] 1. Product image automatic editing module

[1802] When a user uploads a product image via a smart device application, the server receives and temporarily stores the image, then sends it to an AI image processing engine (such as TensorFlow or OpenCV) for background removal, color adjustment, and resizing.

[1803] Example: When you upload a picture of a new pair of sneakers, it will automatically have its background removed, its colors adjusted (whites are emphasized), and it will be resized to 200x200 pixels.

[1804] Example prompt:

[1805] Remove the background from your product images, adjust the colors, and resize them to the optimal size.

[1806] 2. Automatic copy generation module

[1807] When a user enters product information, the application sends the data to the server, which then requests an AI text generation engine (e.g., GPT-3) to generate a text based on the product information. The generated text is stored in a database and reflected on the e-commerce site.

[1808] Example: Enter the details of a new backpack and the following text is generated: "This backpack is made from durable materials and is comfortable to wear."

[1809] Example prompt:

[1810] "Generate compelling descriptions based on new product information."

[1811] 3. Site Analysis Automation Module

[1812] The server periodically retrieves website analytics data via APIs such as Google Analytics, sends it to an AI analytics engine, which analyzes traffic patterns and user behavior, and generates a report containing suggestions for improvement and notifies the website operator.

[1813] Example: A report includes a specific suggestion for improvement: "Page B has a low conversion rate and needs improvement."

[1814] Example prompt:

[1815] "Identify areas for improvement on your website based on Google Analytics data."

[1816] 4. AI Customer Support Chatbots

[1817] When a user makes an inquiry via a smart device application, the chatbot server receives the inquiry and sends it to the AI ​​engine to generate an appropriate answer. It also performs sentiment analysis and determines how to respond.

[1818] Example: When a customer asks, "What's the status of my order?", the chatbot responds, "Your order is currently being prepared for shipping." If a customer expresses dissatisfaction, the chatbot responds, "Sorry for the wait. We'll get back to you as soon as possible."

[1819] Example prompt:

[1820] "Generate appropriate responses to customer queries and respond emotionally if necessary."

[1821] In this way, the system of the present invention utilizes smart device applications to make the operation of an EC site more efficient and reduce the burden on the operator.

[1822] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1823] Step 1:

[1824] The user takes or selects and uploads a product image through a smart device application.

[1825] Input: Product image file.

[1826] How it works: The application transfers the image to a cloud server.

[1827] Output: Raw images uploaded to the server.

[1828] Step 2:

[1829] The server temporarily stores the received product image.

[1830] Input: Product image sent from a smart device.

[1831] How it works: The server stores image files in a dedicated directory.

[1832] Output: Temporarily saved product image files.

[1833] Step 3:

[1834] The server sends the image to an AI image processing engine (e.g., TensorFlow or OpenCV) and requests background removal.

[1835] Input: Temporarily saved product image file.

[1836] How it works: The server generates a prompt to the AI ​​engine and requests an image processing task.

[1837] Output: Product image with background removed.

[1838] Step 4:

[1839] The server sends the background-removed image back to the AI ​​image processing engine, requesting color adjustment and resizing.

[1840] Input: Product image with background removed.

[1841] How it works: The server generates a prompt for color adjustment and resizing and requests the AI ​​engine to process it.

[1842] Output: Color adjusted and resized product images.

[1843] Step 5:

[1844] The server saves the processed product images in a database and reflects them on the product page of the e-commerce site.

[1845] Input: Optimized product images.

[1846] Operation: The server saves the image to the database and updates the page on the e-commerce site.

[1847] Output: Updated e-commerce product page.

[1848] Step 6:

[1849] The user enters detailed product information into a smart device application and submits it.

[1850] Input: Product details (features, size, material, etc.).

[1851] Action: The application transfers the input data to the server.

[1852] Output: Product details received by the server.

[1853] Step 7:

[1854] The server sends the received product details to an AI text generation engine (e.g., GPT-3) and requests it to generate a product description.

[1855] Input: Product details.

[1856] How it works: The server generates a prompt to the AI ​​engine and asks it to perform a text generation task.

[1857] Output: The generated product description.

[1858] Step 8:

[1859] The server saves the generated product description in a database and reflects it on the product page of the e-commerce site.

[1860] Input: Product description.

[1861] What happens: The server saves the text to a database and updates the page on the e-commerce site.

[1862] Output: Updated e-commerce product page.

[1863] Step 9:

[1864] The server periodically collects analytics data such as Google Analytics.

[1865] Input: Web analytics data.

[1866] How it works: The server calls the analytics platform's API to retrieve data.

[1867] Output: Captured web analytics data.

[1868] Step 10:

[1869] The server sends the acquired analytical data to the AI ​​analysis engine, requesting it to analyze areas for improvement and generate a report.

[1870] Input: Web analytics data.

[1871] How it works: The server generates a prompt to the AI ​​analytics engine, requesting a data analysis task.

[1872] Output: A report containing generated improvement suggestions.

[1873] Step 11:

[1874] The server notifies the operator of the improvement proposal.

[1875] Input: Report with improvement suggestions.

[1876] Operation: The server notifies the operator of the report to his / her smart device.

[1877] Output: Report notified to the operator.

[1878] Step 12:

[1879] Users and customers make inquiries via smart device applications.

[1880] Input: Enquiry details.

[1881] How it works: The application sends the query data to the chatbot server.

[1882] Output: The query received by the server.

[1883] Step 13:

[1884] The chatbot server sends the received inquiry to the AI ​​engine, requesting answer generation and sentiment analysis.

[1885] Input: Enquiry details.

[1886] How it works: The server generates prompts for the AI ​​engine and assigns it answer generation and sentiment analysis tasks.

[1887] Output: Generated answers and sentiment analysis results.

[1888] Step 14:

[1889] The chatbot server responds to the customer with the generated answer and takes appropriate action based on the results of sentiment analysis.

[1890] Input: Generated answers and sentiment analysis results.

[1891] What it does: The server sends a response and, if necessary, responds based on the emotion.

[1892] Output: Answers returned to the customer and appropriate responses.

[1893] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1894] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[1895] 1. Product image automatic editing module

[1896] overview:

[1897] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[1898] What happens:

[1899] The user uploads a product image on the EC management screen.

[1900] The server receives the uploaded image and temporarily stores it.

[1901] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[1902] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[1903] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[1904] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[1905] Examples:

[1906] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[1907] 2. Automatic copy generation module

[1908] overview:

[1909] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[1910] What happens:

[1911] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[1912] The server stores the new product information in a database.

[1913] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[1914] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1915] Examples:

[1916] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[1917] 3. Site Analysis Automation Module

[1918] overview:

[1919] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[1920] What happens:

[1921] The server periodically retrieves site analytics data via the Google Analytics API.

[1922] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement.

[1923] The server converts the received analysis results into a report format and notifies the operator of the generated report.

[1924] Examples:

[1925] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[1926] 4. Customer Support AI Chatbots Combined with Emotion Engines

[1927] overview:

[1928] The AI ​​chatbot responds to customer inquiries 24 hours a day, using an emotion engine to analyze customer emotions and provide appropriate responses.

[1929] What happens:

[1930] A user (customer) makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[1931] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the sentiment.

[1932] The emotion engine recognizes emotions from customer text and determines the appropriate response.

[1933] The chatbot server returns the generated answer to the user's terminal.

[1934] Examples:

[1935] If an operator introduces a chatbot and emotion engine and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's emotions, such as, "We will do our best to respond quickly."

[1936] In this way, a system is provided that automates various tasks related to operating an e-commerce site and reduces the burden on operators.

[1937] The processing flow will be explained below.

[1938] Product image automatic editing module

[1939] Processing Steps:

[1940] Step 1:

[1941] The user uploads a product image on the EC management screen.

[1942] Step 2:

[1943] The server receives the uploaded image and temporarily stores it.

[1944] Step 3:

[1945] The server sends the image to the AI ​​image processing engine and requests a background removal task.

[1946] Step 4:

[1947] The AI ​​image processing engine identifies the background of the image and removes it.

[1948] Step 5:

[1949] The AI ​​image processing engine returns the image with the background removed to the server.

[1950] Step 6:

[1951] The server requests a color adjustment task and sends the background-removed image back to the AI ​​image processing engine.

[1952] Step 7:

[1953] The AI ​​image processing engine adjusts the color tone of the image to create attractive colors.

[1954] Step 8:

[1955] The AI ​​image processing engine sends the color-adjusted image back to the server.

[1956] Step 9:

[1957] The server receives the color-adjusted image and resizes it to the optimal image size.

[1958] Step 10:

[1959] The server saves the final edited image in a database and reflects it on the product page of the e-commerce site.

[1960] Automatic copy generation module

[1961] Processing Steps:

[1962] Step 1:

[1963] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[1964] Step 2:

[1965] The server stores the new product information in a database.

[1966] Step 3:

[1967] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[1968] Step 4:

[1969] The AI ​​text generation engine analyzes the product's features and generates compelling copy.

[1970] Step 5:

[1971] The AI ​​text generation engine sends the generated text back to the server.

[1972] Step 6:

[1973] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[1974] Site analysis automation module

[1975] Processing Steps:

[1976] Step 1:

[1977] The server uses the Google Analytics API to retrieve site analytics data periodically (e.g. daily, weekly).

[1978] Step 2:

[1979] The server sends the acquired analysis data to the AI ​​analysis engine.

[1980] Step 3:

[1981] An AI analytics engine analyzes traffic patterns and user behavior.

[1982] Step 4:

[1983] The AI ​​analysis engine extracts areas for improvement on the site and generates specific improvement suggestions.

[1984] Step 5:

[1985] The improvement suggestions generated by the AI ​​analysis engine are sent back to the server.

[1986] Step 6:

[1987] The server formats the analysis results it receives into a report format.

[1988] Step 7:

[1989] The server will then email the generated report to the site operator or display it in the admin panel.

[1990] Customer support AI chatbot combined with emotion engine

[1991] Processing Steps:

[1992] Step 1:

[1993] A user (customer) makes an inquiry to a chatbot on an e-commerce site.

[1994] Step 2:

[1995] The customer terminal sends the inquiry to the chatbot server.

[1996] Step 3:

[1997] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[1998] Step 4:

[1999] The AI ​​engine analyzes the inquiry and generates an appropriate answer.

[2000] Step 5:

[2001] The emotion engine recognizes emotions from customer text and determines the appropriate response.

[2002] Step 6:

[2003] The chatbot server returns the generated answer to the user's terminal.

[2004] Step 7:

[2005] The user (customer) receives the answer and takes the next action (e.g., purchase, ask additional questions).

[2006] Example 2

[2007] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2008] On online shopping sites, managing the quality of product images, creating attractive product descriptions, improving website usability, and streamlining customer support are major burdens for operators. While automating these tasks would be desirable to reduce operational costs and improve user experience, there are still not enough systems available to achieve this.

[2009] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2010] In this invention, the server includes means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating attractive copy based on detailed product information, means for acquiring website analysis data, analyzing site improvements, and generating specific improvement proposals, means for generating appropriate responses to customer inquiries and analyzing and responding to customer sentiment, means for utilizing an external image processing engine, means for utilizing an external text generation engine, means for utilizing an external analysis platform, and means for analyzing customer sentiment using an external sentiment analysis engine and generating appropriate responses. This reduces the burden on operators and makes it possible to operate online shopping sites more efficiently.

[2011] "Product image optimization" means automatically removing backgrounds, adjusting colors, and resizing images to make them suitable for e-commerce sites.

[2012] "Background removal" is a process that removes the background from the product image, focusing only on the product.

[2013] "Color adjustment" is the process of adjusting the color tone, brightness, and contrast of product images to make them appear clearer and more attractive.

[2014] "Resizing" is the process of resizing the dimensions of product images to a size suitable for an e-commerce site.

[2015] "Automatic copy generation" refers to the automatic creation of attractive and purchasing-motivating text based on detailed product information.

[2016] "Website analytics data" refers to data on user behavior, such as the number of visitors to a website, the number of page views, the length of stay, and the bounce rate.

[2017] "Site Improvements" are areas that need to be fixed or changed to improve the website's usability or conversion rate.

[2018] An "AI image processing engine" is a program or system that uses machine learning and artificial intelligence technology to perform image editing processes (background removal, color adjustment, resizing, etc.).

[2019] An "AI text generation engine" is a program or system that automatically generates text (e.g., product descriptions) using natural language processing technology.

[2020] An "AI analytics engine" is a program or system that uses machine learning and artificial intelligence techniques to analyze large amounts of data and extract insights.

[2021] An "emotion analysis engine" is a program or system that detects and analyzes a speaker's emotions (e.g., joy, anger, sadness, etc.) from text data.

[2022] "External Analytics Platform" means a third-party service or system used to collect, store and analyze website analytics data.

[2023] "External Image Processing Engine" means a third-party image editing service or system used to perform processing such as background removal, color adjustment, or resizing of product images.

[2024] An "external text generation engine" is a third-party service or system that automatically generates text based on product feature information, etc.

[2025] This invention is a system that improves the efficiency of EC site operations and reduces the burden on operators. Below, we will explain the main modules that make up this system and how to implement it in detail.

[2026] Product image automatic editing module

[2027] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them using an external image processing engine (e.g., Adobe Photoshop API).

[2028] Hardware and software used:

[2029] Terminals, servers, and image processing engines used by users

[2030] Data processing and calculation:

[2031] 1. The user uploads a product image from the EC management screen.

[2032] 2. The server receives the image and temporarily stores it.

[2033] 3. The server sends the image to the image processing engine for background removal. The image processing engine identifies and removes the background of the image.

[2034] 4. The server receives the image with the background removed and sends it back to the image processing engine, requesting color adjustment.

[2035] 5. The server receives the color-adjusted image and optimizes its size.

[2036] 6. The server saves the edited image in the database and reflects it on the product page of the e-commerce site.

[2037] Examples:

[2038] A user uploads a new product image. The server receives the image, and the Adobe Photoshop API automatically removes the background and performs color adjustments. Finally, the server optimizes the image size and saves it in a format suitable for display on the website.

[2039] Example prompt sentence:

[2040] "Remove the background of this image, adjust the color, and resize it to the optimal size for your e-commerce site."

[2041] Automatic copy generation module

[2042] The server uses AI to automatically generate attractive product descriptions based on detailed product information retrieved from a product database. This process uses an external text generation engine (e.g., OpenAI GPT-4).

[2043] Hardware and software used:

[2044] The terminal, server, and text generation engine used by the user

[2045] Data processing and calculation:

[2046] 1. The user enters new product information (features, size, material, etc.) on the EC management screen and saves it.

[2047] 2. The server saves the new product information in the database.

[2048] 3. The server sends the new product information to the text generation engine and requests it to generate a copy. The text generation engine analyzes the product's features and generates an attractive copy.

[2049] 4. The server receives the generated draft and stores it in a database.

[2050] 5. The server reflects the text on the product page of the e-commerce site.

[2051] Examples:

[2052] When a new product is added, the server sends the product's characteristics to OpenAI GPT-4, which then generates a summary such as, "This T-shirt is made of 100% cotton and is extremely comfortable. Its casual design makes it suitable for any occasion."

[2053] Example prompt sentence:

[2054] "Create a compelling product description based on this product's features, size, and materials."

[2055] Site analysis automation module

[2056] The server analyzes the Google Analytics data and reports specific improvements to the site. This analysis is performed using an external analysis platform (e.g., Google Cloud AI).

[2057] Hardware and software used:

[2058] Server, analysis platform

[2059] Data processing and calculation:

[2060] 1. The server retrieves site analytics data via the Google Analytics API.

[2061] 2. The server sends the analysis data to the analysis platform and requests data analysis.

[2062] 3. The server receives the analysis results and formats them into a report.

[2063] 4. The server notifies the operator of the generated report.

[2064] Examples:

[2065] Every week, the server retrieves data from Google Analytics, and Google Cloud AI generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site's design and content.

[2066] Example prompt sentence:

[2067] "Please analyze this Google Analytics data and let us know how we can improve it."

[2068] Customer support AI chatbot combined with emotion engine

[2069] The server uses an AI chatbot to respond to customer inquiries 24 hours a day, analyzes customer emotions using an emotion engine, and responds appropriately. This process uses an external emotion analysis engine (e.g., IBM Watson Tone Analyzer).

[2070] Hardware and software used:

[2071] User devices, chatbot servers, and emotion analysis engines

[2072] Data processing and calculation:

[2073] 1. A user (customer) makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[2074] 2. The chatbot server sends the received inquiry to the AI ​​engine and requests it to generate an answer.

[2075] 3. The emotion engine recognizes emotions from the customer's text and determines the appropriate response.

[2076] 4. The chatbot server sends the generated answer back to the user's device.

[2077] Examples:

[2078] If an operator introduces a chatbot and emotion engine and a customer asks, "Please tell me the stock status of product A," the AI ​​will respond, "Product A is in stock." If the customer expresses dissatisfaction, the AI ​​will respond by taking their feelings into consideration, such as, "We will do our best to respond quickly."

[2079] Example prompt sentence:

[2080] "Analyze customer sentiment and generate relevant, responsive responses."

[2081] This system reduces the burden on operators and makes it possible to run online shopping sites more efficiently.

[2082] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2083] Product image automatic editing module

[2084] Step 1:

[2085] The user selects a product image on the EC admin screen and clicks the upload button. The input is the image file selected by the user, and the output is the image data included in the HTTP POST request.

[2086] Step 2:

[2087] The server receives image data sent by the user and temporarily stores it. The input is the image data received via an HTTP POST request, and the output is an image file saved in a temporary folder on the server.

[2088] Step 3:

[2089] The server sends the image to the image processing engine and requests background removal. The input is the image file saved in the temporary folder, and the output is the image data sent in the HTTP request.

[2090] Step 4:

[2091] The server receives the background-removed image. The input is the HTTP response from the image processing engine, and the output is the background-removed image file saved in a temporary folder on the server.

[2092] Step 5:

[2093] The server sends the image with the background removed to the image processing engine again and requests color adjustment. The input is the image file with the background removed, and the output is the image data sent in the HTTP request.

[2094] Step 6:

[2095] The server receives the color-adjusted image. The input is the HTTP response from the image processing engine, and the output is the color-adjusted image file saved in a temporary folder on the server.

[2096] Step 7:

[2097] The server resizes the color-adjusted image to the optimal size. The input is the color-adjusted image file, and the output is the resized image file. Specifically, the resizing process is performed using an image processing library.

[2098] Step 8:

[2099] The server saves the resized image in a database. The input is the resized image file, and the output is the image data saved in the database.

[2100] Step 9:

[2101] The server reflects the image on the product page of the EC site. The input is the image data stored in the database, and the output is the image displayed on the product page of the EC site.

[2102] Automatic copy generation module

[2103] Step 1:

[2104] A user enters new product information (features, size, material, etc.) on the e-commerce management screen and clicks the save button. The input is the product information entered by the user, and the output is the product data included in the HTTP POST request.

[2105] Step 2:

[2106] The server saves the new product information to a database. The input is the product data received via an HTTP POST request, and the output is the product information saved in the database.

[2107] Step 3:

[2108] The server sends new product information to the text generation engine and requests it to generate text. The input is the product information stored in the database, and the output is the product data sent in the HTTP request.

[2109] Step 4:

[2110] The server receives the generated text from the text generation engine. The input is the HTTP response from the text generation engine, and the output is the generated text stored in the server's temporary memory.

[2111] Step 5:

[2112] The server stores the generated draft in a database. The input is the generated draft, and the output is the draft data stored in the database.

[2113] Step 6:

[2114] The server reflects the copy on the product page of the EC site. The input is the copy data stored in the database, and the output is the copy displayed on the product page of the EC site.

[2115] Site analysis automation module

[2116] Step 1:

[2117] The server periodically retrieves site analytics data via the Google Analytics API. The input is the API request, and the output is the retrieved site analytics data.

[2118] Step 2:

[2119] The server sends the acquired analysis data to the analysis platform and requests data analysis. The input is the acquired analysis data, and the output is the data sent in the HTTP request.

[2120] Step 3:

[2121] The server receives the analysis results from the analysis platform. The input is the HTTP response from the analysis platform, and the output is the analysis results stored in the server's temporary memory.

[2122] Step 4:

[2123] The server formats the analysis results it receives into a report format. The input is the analysis results, and the output is the formatted report data. Specifically, a report is created using a report generation tool.

[2124] Step 5:

[2125] The server notifies the operator of the generated report. The input is the formatted report data and the output is the notification sent to the operator.

[2126] Customer support AI chatbot combined with emotion engine

[2127] Step 1:

[2128] A user (customer) makes an inquiry to a chatbot on an e-commerce site. The input is the inquiry entered by the customer, and the output is chat data.

[2129] Step 2:

[2130] The chatbot server sends the received inquiry to the AI ​​engine and requests it to generate an answer. The input is chat data, and the output is the data sent in the HTTP request.

[2131] Step 3:

[2132] The emotion engine recognizes emotions from the customer's text and determines the appropriate response. The input is the customer's text data, and the output is the emotion analysis result.

[2133] Step 4:

[2134] The chatbot server receives the answer generated by the AI ​​engine. The input is the HTTP response from the AI ​​engine, and the output is the generated answer data.

[2135] Step 5:

[2136] The chatbot server sends the generated answer back to the user's device. The input is the generated answer data, and the output is the answer displayed in the customer's chat window.

[2137] This reduces the burden on operators and makes the operation of online shopping sites more efficient.

[2138] (Application example 2)

[2139] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2140] Managing product images and product descriptions on e-commerce sites, analyzing the site, and streamlining customer support are important, but these require a great deal of time and effort. Even in physical stores, product descriptions, inventory checks, and customer support must be carried out quickly and appropriately, but traditional methods place a heavy burden on staff. Furthermore, analyzing customer sentiment in real-time customer support can be difficult, making it difficult to provide an appropriate response.

[2141] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically removing background, adjusting color, and resizing to optimize product images; means for automatically generating attractive copy based on detailed product information; means for recognizing products using a device and displaying descriptions and inventory information in real time; means for generating appropriate responses to customer inquiries and analyzing and responding to customer emotions; and means for suggesting appropriate responses based on customer emotions. This improves operational efficiency at e-commerce sites and physical stores, reduces the burden on staff, and improves customer satisfaction.

[2142] "Product image optimization" refers to the process of automatically removing the background of product images, adjusting their color, and resizing them.

[2143] "Automatic copy generation" refers to the use of AI to automatically generate attractive product descriptions based on detailed product information.

[2144] "Device-based product recognition" refers to using a device such as smart glasses to scan products and recognize them in real time.

[2145] "Real-time display of product description and inventory information" refers to instantly displaying a product description and inventory information when a product is recognized.

[2146] "Generating appropriate responses to customer inquiries" refers to using AI to automatically generate appropriate responses based on the content of customer inquiries.

[2147] "Customer sentiment analysis" refers to analyzing the emotions expressed by customers' inquiries and comments and determining the appropriate response method.

[2148] "Emotion-based response suggestions" refers to suggesting appropriate response methods to staff based on the results of analyzing the customer's emotions.

[2149] A system embodying the present invention includes the following configuration: a server provides means for automatically removing backgrounds, adjusting colors, and resizing product images to optimize them; a server also includes means for automatically generating attractive copy based on detailed product information; a server also includes means for recognizing products using a device and displaying product descriptions and inventory information in real time; a server also includes means for generating appropriate responses to customer inquiries, analyzing and responding to customer sentiment, and suggesting appropriate responses based on the customer sentiment.

[2150] A specific embodiment of the system will now be described.

[2151] Hardware:

[2152] Smart glasses: Built-in camera, display, and microphone.

[2153] Server: Runs the AI ​​image processing engine, AI text generation engine, and sentiment analysis engine.

[2154] Device (smart glasses)

[2155] software:

[2156] Python: Used to implement the program.

[2157] OpenCV: Used for image processing.

[2158] Transformers (Hugging Face): Used for text generation using GPT-3.

[2159] SentimentAnalyzer (custom module): Used for voice sentiment analysis.

[2160] InventoryChecker (custom module): Used to check inventory.

[2161] Data processing and calculation:

[2162] The server receives product images taken by the smart glasses' camera and sends them to the image processing engine. The image processing engine recognizes the product, removes the background, adjusts the color, and resizes it. Based on the recognized product ID, detailed product information is obtained and input as a prompt to the generative AI model. The generated text (product description) and stock information are displayed in real time on the smart glasses.

[2163] When a customer makes an inquiry, the server receives the voice data, analyzes the voice, and analyzes the emotions expressed. Based on the results of the emotion analysis, the server suggests an appropriate response.

[2164] Examples:

[2165] Product Recognition Prompt:

[2166] Product information: Brand: Example Brand, Model: 12345, Material: 100% Cotton, Color: Blue, Size: M. Please create a description based on this.

[2167] Customer Sentiment Analysis Prompt:

[2168] Customer inquiry: "I think the price of this product is too high."

[2169] Please suggest an appropriate response to this.

[2170] This will improve operational efficiency on e-commerce sites and in physical stores. Not only will staff be able to explain products, check inventory, and respond to customers quickly and appropriately, but customer satisfaction will also increase as they will be able to respond with consideration for customer feelings.

[2171] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2172] Step 1:

[2173] A user uses smart glasses to scan an image of a product.

[2174] Specific operation: The camera in the smart glasses captures product images and sends the image data to the server.

[2175] Input: Product image

[2176] Output: Product image sent to the server

[2177] Step 2:

[2178] The server receives the product images and sends them to the image processing engine.

[2179] Specific operation: The received image data is processed using OpenCV to remove background, adjust color, and resize.

[2180] Input: Product image data

[2181] Output: Optimized product images

[2182] Step 3:

[2183] The server sends the optimized product images to an AI image processing engine, which recognizes the products.

[2184] Specific operation: The AI ​​image processing engine analyzes the image and identifies the product ID.

[2185] Input: Optimized product images

[2186] Output: Product ID

[2187] Step 4:

[2188] The server retrieves the product details from the database based on the product ID.

[2189] Specific behavior: Executes a database query to retrieve product-related information (features, materials, price, etc.).

[2190] Input: Product ID

[2191] Output: Product details

[2192] Step 5:

[2193] The detailed information obtained by the server is input into the generative AI model as a prompt sentence to generate a product description.

[2194] Specific operation: A prompt sentence is input into a generative AI model (e.g., GPT-3) to generate an attractive product description.

[2195] Input: Product details

[2196] Output: Product description

[2197] Step 6:

[2198] The server sends the generated product description and inventory information to the smart glasses.

[2199] Specific operation: Product description and stock information are displayed in text format on the smart glasses display.

[2200] Input: Product description, stock information

[2201] Output: Product description and stock information displayed on smart glasses

[2202] Step 7:

[2203] The user receives an inquiry from a customer and transmits voice data to the server through the smart glasses.

[2204] Specific operation: The smart glasses capture audio data and send it to the server.

[2205] Input: Customer inquiry voice data

[2206] Output: Audio data sent to the server

[2207] Step 8:

[2208] The server analyzes the voice data, converts the customer's inquiry into text, and analyzes emotions.

[2209] How it works: The speech analysis engine converts speech data into text, and the sentiment analysis engine identifies customer sentiment from the text.

[2210] Input: Customer inquiry voice data

[2211] Output: Customer sentiment analysis results

[2212] Step 9:

[2213] Based on the results of the sentiment analysis, the server generates an appropriate response method and displays it as a suggestion on the smart glasses.

[2214] Specific operation: The generative AI model creates prompts based on the results of sentiment analysis and generates responses, which are displayed on the smart glasses.

[2215] Input: Customer sentiment analysis results

[2216] Output: Suggested actions displayed on the smart glasses

[2217] This allows users to quickly provide product descriptions and inventory information, enabling them to respond appropriately to customers.

[2218] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[2219] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2220] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[2221] [Fourth embodiment]

[2222] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2223] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[2224] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[2225] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[2226] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[2227] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[2228] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2229] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[2230] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[2231] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[2232] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[2233] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[2234] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2235] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[2236] 1. Product image automatic editing module

[2237] overview:

[2238] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[2239] What happens:

[2240] The user uploads a product image on the EC management screen.

[2241] The server receives the uploaded image and temporarily stores it.

[2242] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[2243] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[2244] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[2245] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[2246] Examples:

[2247] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[2248] 2. Automatic copy generation module

[2249] overview:

[2250] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[2251] What happens:

[2252] The user enters and saves new product information (features, size, material, etc.).

[2253] The server stores the new product information in a database.

[2254] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[2255] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[2256] Examples:

[2257] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[2258] 3. Site Analysis Automation Module

[2259] overview:

[2260] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[2261] What happens:

[2262] The server periodically retrieves site analytics data via the Google Analytics API.

[2263] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement.

[2264] The server converts the received analysis results into a report format and notifies the operator of the generated report.

[2265] Examples:

[2266] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[2267] 4. Customer Support AI Chatbot

[2268] overview:

[2269] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[2270] What happens:

[2271] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server.

[2272] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's sentiment to determine how to respond.

[2273] The chatbot server returns the generated answer to the customer.

[2274] Examples:

[2275] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[2276] In this way, a system is provided that automates various tasks related to operating an e-commerce site and reduces the burden on operators.

[2277] The processing flow will be explained below.

[2278] Product image automatic editing module

[2279] Processing Steps:

[2280] Step 1:

[2281] The user uploads a product image on the EC management screen.

[2282] Step 2:

[2283] The server receives the uploaded image and temporarily stores it.

[2284] Step 3:

[2285] The server sends the image to the AI ​​image processing engine and requests a background removal task.

[2286] Step 4:

[2287] The AI ​​image processing engine identifies the background of the image and removes it.

[2288] Step 5:

[2289] The AI ​​image processing engine returns the image with the background removed to the server.

[2290] Step 6:

[2291] The server requests a color adjustment task and sends the background-removed image back to the AI ​​image processing engine.

[2292] Step 7:

[2293] The AI ​​image processing engine adjusts the color tone of the image to create attractive colors.

[2294] Step 8:

[2295] The AI ​​image processing engine sends the color-adjusted image back to the server.

[2296] Step 9:

[2297] The server receives the color-adjusted image and resizes it to the optimal image size.

[2298] Step 10:

[2299] The server saves the final edited image in a database and reflects it on the product page of the e-commerce site.

[2300] Automatic copy generation module

[2301] Processing Steps:

[2302] Step 1:

[2303] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[2304] Step 2:

[2305] The server stores the new product information in a database.

[2306] Step 3:

[2307] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[2308] Step 4:

[2309] The AI ​​text generation engine analyzes the product's features and generates compelling copy.

[2310] Step 5:

[2311] The AI ​​text generation engine sends the generated text back to the server.

[2312] Step 6:

[2313] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[2314] Site analysis automation module

[2315] Processing Steps:

[2316] Step 1:

[2317] The server uses the Google Analytics API to retrieve site analytics data periodically (e.g. daily, weekly).

[2318] Step 2:

[2319] The server sends the acquired analysis data to the AI ​​analysis engine.

[2320] Step 3:

[2321] An AI analytics engine analyzes traffic patterns and user behavior.

[2322] Step 4:

[2323] The AI ​​analysis engine extracts areas for improvement on the site and generates specific improvement suggestions.

[2324] Step 5:

[2325] The improvement suggestions generated by the AI ​​analysis engine are sent back to the server.

[2326] Step 6:

[2327] The server formats the analysis results it receives into a report format.

[2328] Step 7:

[2329] The server will then email the generated report to the site operator or display it in the admin panel.

[2330] Customer Support AI Chatbot

[2331] Processing Steps:

[2332] Step 1:

[2333] A user (customer) makes an inquiry to a chatbot on an e-commerce site.

[2334] Step 2:

[2335] The customer terminal sends the inquiry to the chatbot server.

[2336] Step 3:

[2337] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[2338] Step 4:

[2339] The AI ​​engine analyzes the inquiry and generates an appropriate answer.

[2340] Step 5:

[2341] The AI ​​engine analyzes the sentiment from the customer's text and determines the best way to respond.

[2342] Step 6:

[2343] The chatbot server returns the generated answer to the user's terminal.

[2344] Step 7:

[2345] The user (customer) receives the answer and takes the next action (e.g., purchase, ask additional questions).

[2346] The above are the specific processing steps in each module.

[2347] Example 1

[2348] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2349] Traditional e-commerce site operations required a great deal of time and effort to edit product images, create product descriptions, analyze the site, and respond to customers. Performing these tasks manually increased the burden on operators and hindered efficient operations. Furthermore, responding in a way that takes customer feelings into consideration required advanced expertise, making it difficult to respond quickly and appropriately.

[2350] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2351] In this invention, the server includes means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating product descriptions based on detailed product information, means for acquiring analytical data, analyzing website improvements, and generating improvement proposals, means for generating appropriate responses to customer inquiries, and analyzing and responding to customer sentiments, means for receiving product images and saving them in a temporary storage area, means for sending product images to an AI image processing engine and requesting a background removal task, means for sending the image with the background removed to the AI ​​image processing engine and requesting a color adjustment task, means for resizing the color-adjusted image, and means for storing the edited image in a database. and reflecting it on the product page, means for inputting and saving product features, means for saving the saved product information in a database, means for sending the product features to an AI text generation engine and generating a product description, means for saving the generated product description in a database and reflecting it on the product page, means for acquiring data from an analysis platform, means for sending the data to an AI analysis engine and extracting improvements, means for formatting the generated improvement proposals into a report and notifying an operator, means for sending the inquiry content to a chatbot server and requesting an answer generation task, and means for responding to the customer with an answer and sending an additional message that takes emotions into consideration. This makes it possible to significantly reduce the time and effort required to operate an e-commerce site and reduce the burden on the operator.

[2352] "Product Image" means a digital image uploaded to an e-commerce site for the visual representation of a product.

[2353] "Background removal" is the process of identifying and removing unnecessary background parts from product images.

[2354] "Color adjustment" is the process of adjusting the color tone, brightness, contrast, etc. of a product image to an optimal state.

[2355] "Resize" is the operation of converting the size of a product image to the optimal dimensions for display or storage.

[2356] "Detailed product information" is data that includes specific information such as product features, size, material, and price.

[2357] A "product description" is automatically generated text that describes a product in an attractive way.

[2358] "Analytics Data" is a collection of information about website usage and user behavior.

[2359] "Improvements" are specific changes or actions you take to improve your website's performance.

[2360] An "inquiry" is a question or request that a customer makes to the operator regarding a product or service.

[2361] "Analyzing sentiment" is the act of identifying and evaluating the emotions and tone that customers express through their inquiries and feedback.

[2362] A "server" is a computer system that processes, stores, and provides network services.

[2363] An "AI image processing engine" is a software system that uses artificial intelligence technology to automatically edit images.

[2364] An "AI text generation engine" is a software system that uses artificial intelligence technology to automatically generate text in natural language.

[2365] A "report" is a document that organizes analysis results and improvement proposals and provides them to operators.

[2366] A "chatbot server" is a server system that automatically responds to inquiries from customers.

[2367] "Transmission" is the act of moving data or information from one system to another.

[2368] A "task" is an individual process or unit of work that a system executes.

[2369] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[2370] Product image automatic editing module

[2371] overview:

[2372] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[2373] Hardware and software:

[2374] Server: Manages image processing tasks and interacts with the database.

[2375] AI image processing engine: Image processing software such as Adobe Photoshop API and CorelDRAW API.

[2376] Database: Stores and manages image data.

[2377] explanation:

[2378] The user uploads a product image on the e-commerce management screen. The server receives the uploaded image and temporarily stores it. Next, the server sends the image to the AI ​​image processing engine and requests a background removal task. The AI ​​image processing engine identifies and removes the background from the image. The server then sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. After the color-adjusted image is received by the server, it is resized to the appropriate size. Finally, the edited image is saved in the database and reflected on the product page of the e-commerce site.

[2379] Examples:

[2380] When a user uploads a new product image, the server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the server optimizes the image size and saves it in the format that will be displayed on the website.

[2381] Example prompt:

[2382] "New product image uploaded. Remove background, adjust color, and resize for optimal fit."

[2383] Automatic copy generation module

[2384] overview:

[2385] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[2386] Hardware and software:

[2387] Server: Manages product data and copy generation tasks.

[2388] AI text generation engines: Text generation software such as GPT-3 and BERT.

[2389] Database: Stores and manages product information.

[2390] explanation:

[2391] The user enters and saves new product information (features, size, material, etc.). The server saves the new product information in a database. The server then sends the new product information to an AI text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates appealing copy. The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[2392] Examples:

[2393] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[2394] Example prompt:

[2395] "Generate an attractive product description of 100 characters or less based on the new product information."

[2396] Site analysis automation module

[2397] overview:

[2398] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[2399] Hardware and software:

[2400] Server: Acquires and manages analysis data.

[2401] AI analytics engine: Data analytics software such as BigQuery and Data Studio.

[2402] Database: Stores and manages analysis results.

[2403] explanation:

[2404] The server periodically obtains website analysis data via the Google Analytics API. The server then sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior and identifies areas for improvement. The server then formats the analysis results into a report and notifies the operator.

[2405] Examples:

[2406] Every week, the server retrieves data from Google Analytics, and the AI ​​analysis engine generates a report with suggestions for improvement, such as "Page A has a high bounce rate, so it needs to be improved." Based on this report, operators can improve the site design and content.

[2407] Example prompt:

[2408] "Generate a report with site improvements based on this week's Google Analytics data."

[2409] Customer Support AI Chatbot

[2410] overview:

[2411] AI chatbots respond to customer inquiries 24 / 7 and improve customer satisfaction through sentiment analysis.

[2412] Hardware and software:

[2413] Server: Responsible for query management and response generation.

[2414] AI engine: Chatbot software such as Dialogflow, IBM Watson, etc.

[2415] Database: Stores and manages inquiry details and response records.

[2416] explanation:

[2417] A user makes an inquiry to a chatbot on an e-commerce site. The customer's device sends the inquiry to the chatbot server. The chatbot server then sends the received inquiry to the AI ​​engine and requests an answer generation task. The AI ​​engine generates an appropriate answer and analyzes the customer's emotions to determine how to respond. The chatbot server then returns the generated answer to the customer.

[2418] Examples:

[2419] If an operator introduces a chatbot and a customer inquires, "Please tell me the stock status of product A," the chatbot server will respond, "Product A is in stock." If the customer expresses dissatisfaction, the chatbot server will respond with a response that takes into consideration the customer's feelings, such as, "We will do our best to respond quickly."

[2420] Example prompt:

[2421] "Use sentiment analysis to generate appropriate answers to questions that customers express emotions about."

[2422] In this way, each module works together to automate the operation of the e-commerce site, realizing a system that reduces the burden on operators.

[2423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2424] Product image automatic editing module

[2425] Step 1:

[2426] The user uploads a product image on the EC management screen.

[2427] Input: The user specifies the image file for the product and clicks the upload button.

[2428] Specific operation: Product images are sent from the user's device to the server.

[2429] Output: Product images are temporarily saved on the server.

[2430] Step 2:

[2431] The server receives the uploaded product images and stores them in a temporary storage area.

[2432] Input: Product image file sent from the user's device.

[2433] Specific operation: The server stores the product image in a temporary storage area.

[2434] Output: Product image files saved in temporary storage area.

[2435] Step 3:

[2436] The server retrieves the product image from the temporary storage area and requests the background removal task from the AI ​​image processing engine.

[2437] Input: Product image file saved in temporary storage area.

[2438] Specific operation: The server sends the image to an AI image processing engine (e.g., Adobe Photoshop API) and instructs it to perform the background removal task.

[2439] Output: Product image files with background removed.

[2440] Step 4:

[2441] The server sends the background-removed image to the AI ​​image processing engine and requests a color adjustment task.

[2442] Input: Background removed product image file.

[2443] Specific operation: The server again sends the image to the AI ​​image processing engine and instructs it to perform color adjustment tasks.

[2444] Output: Color-adjusted product image files.

[2445] Step 5:

[2446] The server resizes the color-adjusted image.

[2447] Input: Color adjusted product image files.

[2448] What happens: The server resizes the image using a built-in image processing library (e.g., Pillow).

[2449] Output: Resized product image files.

[2450] Step 6:

[2451] The server saves the edited product images in a database and reflects them on the product page of the e-commerce site.

[2452] Input: Resized product image files.

[2453] Specific operation: The server saves the image in the database and reflects the image URL on the product page.

[2454] Output: Optimized product images that are displayed on the product page of your ecommerce site.

[2455] Automatic copy generation module

[2456] Step 1:

[2457] The user enters and saves new product information (features, size, material, etc.).

[2458] Input: The user enters details about the new product into an input form.

[2459] Specific operation: Information entered from the user's terminal is sent to the server.

[2460] Output: New product information is saved on the server.

[2461] Step 2:

[2462] The server stores the new product information in a database.

[2463] Input: New product information submitted by the user.

[2464] Specific operation: The server stores the new product information in the database.

[2465] Output: New product information stored in the database.

[2466] Step 3:

[2467] The server sends new product information to the AI ​​text generation engine and requests a copy generation task.

[2468] Input: New product information stored in the database.

[2469] Specific operation: The server sends product information to an AI text generation engine (e.g., GPT-3) and instructs it to generate a copy.

[2470] Output: The generated product description.

[2471] Step 4:

[2472] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[2473] Input: The generated product description.

[2474] Specific operation: The server saves the product description in the database and reflects it on the product page.

[2475] Output: Product description displayed on the product page of the e-commerce site.

[2476] Site analysis automation module

[2477] Step 1:

[2478] The server periodically retrieves site analytics data via the Google Analytics API.

[2479] Input: Analytics data obtained from Google Analytics.

[2480] Specific operation: The server connects to the Google Analytics API and retrieves analytics data.

[2481] Output: The acquired analysis data.

[2482] Step 2:

[2483] The server sends the analysis data to the AI ​​analysis engine and requests a data analysis task.

[2484] Input: Acquired analytical data.

[2485] Specific operation: The server sends the analysis data to an AI analysis engine (e.g., BigQuery, Data Studio) and instructs it to analyze the data.

[2486] Output: Improvements extracted through data analysis.

[2487] Step 3:

[2488] The server formats the analysis results it receives into a report format and notifies the operator.

[2489] Input: Improvements extracted through data analysis.

[2490] Specific operation: The server prepares the analysis results in a report format (e.g., Excel, PDF).

[2491] Output: Report notifying operators.

[2492] Customer Support AI Chatbot

[2493] Step 1:

[2494] A user makes an inquiry to a chatbot on an e-commerce site.

[2495] Input: The query that the user types into the chatbot widget.

[2496] Specific operation: The user's inquiry is sent from the customer terminal to the chatbot server.

[2497] Output: The query received by the chatbot server.

[2498] Step 2:

[2499] The chatbot server sends the received inquiry to the AI ​​engine and requests an answer generation task.

[2500] Input: The received inquiry.

[2501] Specific operation: The server sends the query content to an AI engine (e.g., Dialogflow, IBM Watson) and instructs it to generate an answer.

[2502] Output: The generated answer.

[2503] Step 3:

[2504] The chatbot server returns the generated answer to the customer.

[2505] Input: The generated answer.

[2506] Specific operation: The server sends the answer to the customer's terminal and displays it to the customer.

[2507] Output: The answer that is shown to the customer.

[2508] Step 4:

[2509] The chatbot server analyzes the customer's emotions and generates and sends additional messages that take their emotions into consideration.

[2510] Input: Customer sentiment data.

[2511] Specific operation: The server uses an AI engine to perform sentiment analysis and generate additional messages appropriate to the situation.

[2512] Output: Additional sentiment-sensitive messages sent to customers.

[2513] (Application example 1)

[2514] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2515] In operating an e-commerce site, tasks such as editing product images, generating product descriptions, analyzing site analytics data, and responding to customer inquiries require a lot of time and effort. Performing these tasks manually places a heavy burden on operators, hindering efficient operation. Furthermore, there is a need for an approach that allows these operations to be easily performed via smart devices.

[2516] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2517] In this invention, the server is a system including means for automatically removing backgrounds, adjusting colors, and resizing to optimize product images, means for automatically generating attractive copy based on detailed product information, means for acquiring website analysis data, analyzing site improvements, and generating specific improvement proposals, and means for generating appropriate responses to customer inquiries and analyzing customer sentiments to respond accordingly, and the system is equipped with means for controlling these means via a smart device application, means for generating prompts for removing backgrounds, adjusting colors, and resizing product images, means for generating copy generation prompts based on detailed product information, and means for generating prompts for site improvement based on web analysis data. This automates various tasks involved in operating an e-commerce site, significantly reducing the burden on operators and enabling them to easily perform operations via smart devices.

[2518] "Optimizing product images" means removing the background from product images, adjusting the color, and resizing them to an appropriate size.

[2519] "Background removal" refers to identifying and removing background areas from product images.

[2520] "Color adjustment" refers to adjusting the color, brightness, etc. to improve the appearance of a product.

[2521] "Resizing" refers to resizing the product image to an appropriate size.

[2522] "Detailed product information" refers to information about the product, such as its features, size, and material.

[2523] "Automatically generating copy" refers to the use of artificial intelligence technology to automatically create attractive and appropriate product descriptions based on detailed product information.

[2524] "Website Analytics Data" refers to data such as website traffic, user behavior, and conversion rates.

[2525] "Site Improvements" means any changes or modifications needed to improve the performance and user experience of the Website.

[2526] "Specific improvement suggestions" refers to providing specific action plans and revisions based on areas for improvement on the site.

[2527] "Customer inquiries" refers to questions and requests from customers using the e-commerce site regarding product information, stock availability, returns and exchanges, etc.

[2528] "Generating appropriate responses" refers to automatically creating accurate and effective responses to customer inquiries.

[2529] "Analyzing customer emotions" refers to analyzing and understanding the customer's emotional state based on the content of their inquiry and their reaction.

[2530] "Smart device applications" refers to application software that can be used on smart devices such as smartphones and tablets.

[2531] A "prompt" refers to an input sentence used to give instructions or ask questions to artificial intelligence technology.

[2532] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate and analyze text.

[2533] This invention provides a series of automated systems to streamline e-commerce site operations and reduce the burden on operators. This system edits product images, generates product descriptions, analyzes websites, and responds to customer inquiries through smart device applications.

[2534] 1. Product image automatic editing module

[2535] When a user uploads a product image via a smart device application, the server receives and temporarily stores the image, then sends it to an AI image processing engine (such as TensorFlow or OpenCV) for background removal, color adjustment, and resizing.

[2536] Example: When you upload a picture of a new pair of sneakers, it will automatically have its background removed, its colors adjusted (whites are emphasized), and it will be resized to 200x200 pixels.

[2537] Example prompt:

[2538] Remove the background from your product images, adjust the colors, and resize them to the optimal size.

[2539] 2. Automatic copy generation module

[2540] When a user enters product information, the application sends the data to the server, which then requests an AI text generation engine (e.g., GPT-3) to generate a text based on the product information. The generated text is stored in a database and reflected on the e-commerce site.

[2541] Example: Enter the details of a new backpack and the following text is generated: "This backpack is made from durable materials and is comfortable to wear."

[2542] Example prompt:

[2543] "Generate compelling descriptions based on new product information."

[2544] 3. Site Analysis Automation Module

[2545] The server periodically retrieves website analytics data via APIs such as Google Analytics, sends it to an AI analytics engine, which analyzes traffic patterns and user behavior, and generates a report containing suggestions for improvement and notifies the website operator.

[2546] Example: A report includes a specific suggestion for improvement: "Page B has a low conversion rate and needs improvement."

[2547] Example prompt:

[2548] "Identify areas for improvement on your website based on Google Analytics data."

[2549] 4. AI Customer Support Chatbots

[2550] When a user makes an inquiry via a smart device application, the chatbot server receives the inquiry and sends it to the AI ​​engine to generate an appropriate answer. It also performs sentiment analysis and determines how to respond.

[2551] Example: When a customer asks, "What's the status of my order?", the chatbot responds, "Your order is currently being prepared for shipping." If a customer expresses dissatisfaction, the chatbot responds, "Sorry for the wait. We'll get back to you as soon as possible."

[2552] Example prompt:

[2553] "Generate appropriate responses to customer queries and respond emotionally if necessary."

[2554] In this way, the system of the present invention utilizes smart device applications to make the operation of an EC site more efficient and reduce the burden on the operator.

[2555] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2556] Step 1:

[2557] The user takes or selects and uploads a product image through a smart device application.

[2558] Input: Product image file.

[2559] How it works: The application transfers the image to a cloud server.

[2560] Output: Raw images uploaded to the server.

[2561] Step 2:

[2562] The server temporarily stores the received product image.

[2563] Input: Product image sent from a smart device.

[2564] How it works: The server stores image files in a dedicated directory.

[2565] Output: Temporarily saved product image files.

[2566] Step 3:

[2567] The server sends the image to an AI image processing engine (e.g., TensorFlow or OpenCV) and requests background removal.

[2568] Input: Temporarily saved product image file.

[2569] How it works: The server generates a prompt to the AI ​​engine and requests an image processing task.

[2570] Output: Product image with background removed.

[2571] Step 4:

[2572] The server sends the background-removed image back to the AI ​​image processing engine, requesting color adjustment and resizing.

[2573] Input: Product image with background removed.

[2574] How it works: The server generates a prompt for color adjustment and resizing and requests the AI ​​engine to process it.

[2575] Output: Color adjusted and resized product images.

[2576] Step 5:

[2577] The server saves the processed product images in a database and reflects them on the product page of the e-commerce site.

[2578] Input: Optimized product images.

[2579] Operation: The server saves the image to the database and updates the page on the e-commerce site.

[2580] Output: Updated e-commerce product page.

[2581] Step 6:

[2582] The user enters detailed product information into a smart device application and submits it.

[2583] Input: Product details (features, size, material, etc.).

[2584] Action: The application transfers the input data to the server.

[2585] Output: Product details received by the server.

[2586] Step 7:

[2587] The server sends the received product details to an AI text generation engine (e.g., GPT-3) and requests it to generate a product description.

[2588] Input: Product details.

[2589] How it works: The server generates a prompt to the AI ​​engine and asks it to perform a text generation task.

[2590] Output: The generated product description.

[2591] Step 8:

[2592] The server saves the generated product description in a database and reflects it on the product page of the e-commerce site.

[2593] Input: Product description.

[2594] What happens: The server saves the text to a database and updates the page on the e-commerce site.

[2595] Output: Updated e-commerce product page.

[2596] Step 9:

[2597] The server periodically collects analytics data such as Google Analytics.

[2598] Input: Web analytics data.

[2599] How it works: The server calls the analytics platform's API to retrieve data.

[2600] Output: Captured web analytics data.

[2601] Step 10:

[2602] The server sends the acquired analytical data to the AI ​​analysis engine, requesting it to analyze areas for improvement and generate a report.

[2603] Input: Web analytics data.

[2604] How it works: The server generates a prompt to the AI ​​analytics engine, requesting a data analysis task.

[2605] Output: A report containing generated improvement suggestions.

[2606] Step 11:

[2607] The server notifies the operator of the improvement proposal.

[2608] Input: Report with improvement suggestions.

[2609] Operation: The server notifies the operator of the report to his / her smart device.

[2610] Output: Report notified to the operator.

[2611] Step 12:

[2612] Users and customers make inquiries via smart device applications.

[2613] Input: Enquiry details.

[2614] How it works: The application sends the query data to the chatbot server.

[2615] Output: The query received by the server.

[2616] Step 13:

[2617] The chatbot server sends the received inquiry to the AI ​​engine, requesting answer generation and sentiment analysis.

[2618] Input: Enquiry details.

[2619] How it works: The server generates prompts for the AI ​​engine and assigns it answer generation and sentiment analysis tasks.

[2620] Output: Generated answers and sentiment analysis results.

[2621] Step 14:

[2622] The chatbot server responds to the customer with the generated answer and takes appropriate action based on the results of sentiment analysis.

[2623] Input: Generated answers and sentiment analysis results.

[2624] What it does: The server sends a response and, if necessary, responds based on the emotion.

[2625] Output: Answers returned to the customer and appropriate responses.

[2626] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2627] The present invention provides a series of automated systems for improving the efficiency of e-commerce site operations and reducing the burden on operators. The main modules that make up this system and their specific implementation methods are described below.

[2628] 1. Product image automatic editing module

[2629] overview:

[2630] The server receives product images uploaded to the e-commerce site and automatically removes backgrounds, adjusts colors, and resizes them.

[2631] What happens:

[2632] The user uploads a product image on the EC management screen.

[2633] The server receives the uploaded image and temporarily stores it.

[2634] The server sends the image to the AI ​​image processing engine and requests a background removal task, which then identifies and removes the background of the image.

[2635] The server sends the image with the background removed to the AI ​​image processing engine again and requests a color adjustment task. The color-adjusted image is then sent back to the server.

[2636] The server resizes the color-adjusted image received and adjusts it to the optimal size.

[2637] The server saves the edited image in a database and reflects it on the product page of the e-commerce site.

[2638] Examples:

[2639] A user uploads a new product image. The server receives the image, and the AI ​​image processing engine automatically removes the background and adjusts the color. Finally, the image is optimized for size and saved in a format suitable for display on the website.

[2640] 2. Automatic copy generation module

[2641] overview:

[2642] The server uses AI to automatically generate attractive product descriptions based on detailed product information obtained from a product database.

[2643] What happens:

[2644] The user enters and saves new product information (features, size, material, etc.) on the EC management screen.

[2645] The server stores the new product information in a database.

[2646] The server sends new product information to the AI ​​text generation engine and requests a copy generation task. The AI ​​text generation engine analyzes the product's features and generates an attractive copy.

[2647] The server saves the generated copy in a database and reflects it on the product page of the e-commerce site.

[2648] Examples:

[2649] When a new product is added, the server sends the product's features to the AI, which then generates a description such as, "This T-shirt is made of 100% cotton and is extremely comfortable to wear. Its casual design makes it perfect for any occasion."

[2650] 3. Site Analysis Automation Module

[2651] overview:

[2652] AI analyzes Google Analytics data and reports specific areas for improvement on your site.

[2653] What happens:

[2654] The server periodically retrieves site analytics data via the Google Analytics API.

[2655] The server sends the analysis data to the AI ​​analysis engine and requests data analysis tasks. The AI ​​analysis engine analyzes traffic patterns and user behavior to identify areas for improvement. ...

Claims

1. Automated background removal, color adjustment, and resizing for optimized product images. A means to automatically generate attractive copy based on detailed product information, A means for obtaining website analysis data, analyzing the site's improvements, and generating specific improvement proposals; A system that generates appropriate responses to customer inquiries and includes a means of analyzing and responding to customer sentiment.

2. 10. The system of claim 1, further comprising artificial intelligence techniques for performing background removal of product images.

3. The system of claim 1, further comprising means for linking with an external analytics platform to automatically obtain analytics data for the site.

Images