System

Abstract

A system is provided.SOLUTION: A system comprising: means for utilizing a generative data model and a custom action to provide warranty and aftercare information from a user's purchase AI; means for analyzing the collected purchase and failure information to predict product failure rates and repair costs; and means for recommending an optimal aftercare service to the user based on the predicted failure rates and repair costs.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] When shopping online, after users purchase home appliances or electronic devices, managing warranty periods and after-sales care information often becomes complicated. Furthermore, when a product breaks down, it is difficult to decide whether or not to sign up for after-sales care services, which increases user stress. For this reason, there is a need for a system that allows users to easily access information related to product breakdowns and maintenance. Furthermore, there are problems with offering a uniform after-sales care service, such as low customer satisfaction, and personalized proposals being costly. It is necessary to solve these issues and create an environment in which users can shop online with peace of mind. [Means for solving the problem]

[0005] This invention is a system that utilizes generative AI models and custom actions to provide warranty and after-care information based on user purchase data. Specifically, it analyzes purchase data and failure information collected from local and all e-commerce platforms to provide a means for predicting product failure rates and repair costs. Furthermore, it provides a means for recommending optimal after-care services to users based on the predicted failure rates and repair costs. This allows users to retrieve purchase history data after login authentication, making warranty information management easier. Furthermore, personalized after-care service recommendations based on predicted failure rates and repair costs reduce user stress and increase customer satisfaction.

[0006] A "generative AI model" is an artificial intelligence model that analyzes user purchase data and failure information to predict and provide warranty and after-care information.

[0007] "Custom Actions" are customized functions that provide individual warranty and aftercare information to each user based on the analysis results of the generative AI model.

[0008] "User purchase data" refers to data including information about products purchased by users through online shopping, the purchase date and time, and the purchase price.

[0009] "Warranty information" refers to information such as the warranty period, warranty content, and details of after-care services provided for the product.

[0010] "After-sales information" refers to information about repair services, replacement services, support services, etc. that can be used in the event of a product failure.

[0011] "Failure rate" is an indicator that indicates the rate at which a particular product breaks down within a certain period of time.

[0012] "Repair cost" is information indicating the cost required to repair a product when it breaks down.

[0013] An "EC platform" is an e-commerce platform that sells products for online shopping.

[0014] "Prediction results" are predicted data on product failure rates and repair costs analyzed by the generative AI model.

[0015] "User authentication" is the authentication process used when a user logs into a system, and is done using a user ID and password.

[0016] "Database" refers to a storage device that stores and manages information such as user purchase data, warranty information, failure rates, and repair costs obtained within the system. [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] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and provides users with after-care services based on subsequent failure rates and repair costs. This system is characterized by the use of generative AI models and custom actions to quickly provide users with personalized information.

[0039] Explanation of program processing

[0040] 1. Acquiring purchase data

[0041] User: Logs into an online shopping site and enters their account information.

[0042] Terminal: Login information is sent to the authentication server and authenticated.

[0043] Server: After successful authentication, retrieve the purchase history from the EC platform based on the user ID.

[0044] Server: Store the acquired purchase history data in a database.

[0045] 2. Providing warranty information

[0046] User: Select the product for which you want to view warranty information.

[0047] Terminal: Sends the selected product information as a request to the server.

[0048] Server: Extracts the warranty information for the relevant product from the database.

[0049] Server: Returns the extracted warranty information to the device.

[0050] Device: Display the received warranty information on the screen.

[0051] 3. Failure rate and repair cost prediction

[0052] Server: Inputs purchase data and failure information collected from all e-commerce platforms into the generative AI model.

[0053] Server: Uses generative AI models to predict failure rates and repair costs for target products.

[0054] Server: Personalizes prediction results and stores them in a database for each user.

[0055] 4. Aftercare service advice

[0056] User: Clicks the Aftercare Recommendations button.

[0057] Server: Integrates purchase history and failure prediction data to assess the need for aftercare services.

[0058] Server: Sends aftercare recommendation results to the device.

[0059] On your device: Notify the user of the recommendation and display detailed information about it.

[0060] User: Review the details of the recommended aftercare service and take any necessary steps.

[0061] Specific examples

[0062] Example 1: Retrieving purchase data and displaying warranty information

[0063] 1. User: Purchases a home appliance "refrigerator" online and logs in to his / her account.

[0064] 2. Terminal: After logging in, the purchase history of "refrigerator" is sent from the e-commerce platform to the server.

[0065] 3. Server: Stores the purchase data in the database. At the same time, retrieves the refrigerator warranty information from the e-commerce platform and stores it in the database.

[0066] 4. User: If you want to check the warranty information, select "Refrigerator" on your device.

[0067] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "refrigerator" from the database.

[0068] 6. Terminal: Display the extracted warranty information on the user's screen.

[0069] Example 2: Predicting failure rates and repair costs and recommending aftercare

[0070] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of "refrigerators."

[0071] 2. Server: Based on the prediction results, evaluate the need for aftercare services for the user and store the recommendation results in the database.

[0072] 3. User: Click the "Aftercare Recommendations" button to view details of the recommended aftercare services.

[0073] 4. On the device: Notify the user of the recommended results and display details.

[0074] 5. User: Complete the recommended aftercare service enrollment process.

[0075] In this way, the system of the present invention centrally manages warranty and after-sales information for products purchased online, reducing stress for users when a product breaks down. It also improves customer satisfaction by recommending personalized after-sales services.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[0079] Step 2:

[0080] On the device: The login information entered by the user is sent to the authentication server.

[0081] Step 3:

[0082] Server: The authentication server verifies the user ID and password, and if authentication is successful, calls the EC platform API based on the user ID.

[0083] Step 4:

[0084] Server: Obtains user purchase history via the EC platform API and stores that data in the system database.

[0085] Step 5:

[0086] User: If they want to view warranty information for a specific product they purchased, they select that product in the system.

[0087] Step 6:

[0088] Terminal: Sends the selected product information as a request to the server.

[0089] Step 7:

[0090] Server: Extracts warranty information for the requested product from the database.

[0091] Step 8:

[0092] Server: Returns the extracted warranty information to the user's device.

[0093] Step 9:

[0094] Terminal: Display the returned warranty information on the user's screen.

[0095] Step 10:

[0096] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0097] Step 11:

[0098] Server: The generated failure rate and repair cost prediction results are personalized and stored in a database for each user.

[0099] Step 12:

[0100] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0101] Step 13:

[0102] Server: Runs an algorithm that combines purchase history and failure prediction data to assess the need for aftercare services.

[0103] Step 14:

[0104] Server: Sends the generated aftercare service recommendation results to the user device.

[0105] Step 15:

[0106] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[0107] Step 16:

[0108] User: Check the details of the recommended aftercare service and sign up if necessary.

[0109] Example 1

[0110] 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."

[0111] In today's online shopping environment, users must purchase a variety of home appliances and electronic devices and individually manage the associated warranty and after-care information, which is extremely time-consuming. Furthermore, insufficient information on product failure rates and repair costs after purchase makes it difficult for users to select the appropriate after-care service. Furthermore, the lack of personalized information reduces user convenience. Therefore, to solve these issues, a system is needed that can centrally manage purchase data and failure information and provide users with prompt and accurate warranty information and after-care services.

[0112] 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.

[0113] In this invention, the server includes: means for providing warranty and after-care information based on user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for logging in using the user's account information and acquiring the purchase history after authentication; means for saving the acquired purchase history data in a database; means for extracting warranty information for products selected by the user from the database and displaying it on the user's terminal; means for personalizing the prediction results and saving them in the database for each user; and means for evaluating the need for after-care services and displaying the results on the user's terminal. This allows users to centrally manage warranty and after-care information for home appliances and electronic devices purchased online, providing prompt and accurate information. Furthermore, personalized after-care service recommendations based on predicted failure rates and repair costs significantly improve user convenience.

[0114] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to make predictions and analyze data based on collected data.

[0115] A "custom action" is a special program or function designed to perform a specific task or operation.

[0116] "User purchasing data" refers to data including information about products purchased by users on online shopping platforms and their purchase history.

[0117] "Warranty Information" refers to information that describes the conditions and scope of repairs or replacements within a certain period from the date of purchase of the product.

[0118] "Aftercare information" refers to information regarding services such as repairs, maintenance, and support provided after the purchase of a product.

[0119] "Failure information" refers to data such as troubles and repair history when a product stops working properly.

[0120] "Failure rate" refers to the probability that a product will fail within a specific period of time.

[0121] "Repair costs" refers to the costs required to repair a product when it breaks down.

[0122] "Personalization" refers to the customization of information and services based on the characteristics and history of each individual user.

[0123] "Authentication token" refers to a security token used when exchanging user authentication information.

[0124] "Online platform" refers to a service provision infrastructure available on the Internet, including websites and applications.

[0125] A "database" refers to a dedicated system for efficiently storing, searching, and managing large amounts of data.

[0126] "User terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0127] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and quickly provides personalized information to users. This system uses generative AI models and custom actions to recommend the most suitable after-care services to users.

[0128] First, a user logs in to an online shopping site and enters their account information. The login information is sent from the terminal to the authentication server, which receives an authentication token. After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID and stores this purchase history data in a database.

[0129] Next, when the user selects the product for which they wish to check warranty information, the terminal sends a request to the server with the information about the selected product. The server extracts the warranty information for that product from the database and returns it to the terminal. The terminal then displays the received warranty information on its screen.

[0130] The server then inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The prediction results are personalized and stored in a database for each user.

[0131] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for aftercare service. The evaluation results are sent to the device, which notifies the user and displays detailed information. The user can then check the details of the recommended aftercare service and take the necessary steps.

[0132] This system uses various hardware and software. The server uses a high-performance database system (e.g., MySQL or PostgreSQL) and a machine learning framework such as PyTorch or TensorFlow to run the AI ​​model. The terminal is a device operated by the user, such as a computer or smartphone, which communicates with the server via a browser or dedicated application.

[0133] As a concrete example, a user purchases a home appliance "refrigerator" online and logs in to their account. After logging in, the e-commerce platform sends the purchase history for "refrigerator" to the server. The server saves the purchase data in a database and also retrieves and stores warranty information. If the user wants to check the warranty information, they select "refrigerator" on their device, and the server extracts and displays the warranty information. The generative AI model also predicts the failure rate and repair costs of the "refrigerator," and after-care services are recommended. The user clicks the "Recommend After-care" button, checks the recommended after-care services, and proceeds with the procedure.

[0134] An example of a prompt to input to a generative AI model is as follows:

[0135] Using purchase data and failure information as input, predict the failure rate and repair costs for the target product.

[0136] In this way, the system of the present invention can centrally manage warranty and after-sales information for products purchased by users through online shopping, enabling the provision of fast and accurate information. Furthermore, personalized after-sales service recommendations can significantly improve user convenience.

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

[0138] Step 1:

[0139] A user logs into an online shopping site and enters their account information, such as an email address and password, which is then processed on the device.

[0140] Input: User's email address and password

[0141] Output: Authentication request data

[0142] Step 2:

[0143] The terminal sends login information to the authentication server and receives an authentication token. The authentication server verifies the login information and issues an authentication token if it is valid.

[0144] Input: Authentication request data

[0145] Output: Authentication token

[0146] Step 3:

[0147] After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID. The server then uses the authentication token to retrieve the purchase history data from the EC platform via API.

[0148] Input: Authentication token and user ID

[0149] Output: Purchase history data

[0150] Step 4:

[0151] The server saves the acquired purchase history data in the database. The server formats the purchase history data into an appropriate format and saves it in the database using the INSERT statement.

[0152] Input: Purchase history data

[0153] Output: Purchase history stored in the database

[0154] Step 5:

[0155] The user selects the product for which they wish to check warranty information. After logging in, the user clicks on the product in question from the purchase history list on their My Page.

[0156] Input: User input (product selection)

[0157] Output: Product ID

[0158] Step 6:

[0159] The terminal sends the information about the selected product to the server as a request. The terminal uses AJAX to send a request including the product ID to the server.

[0160] Input: Product ID

[0161] Output: Product information request

[0162] Step 7:

[0163] The server extracts the warranty information for the relevant product from the database. The server retrieves the warranty information from the database using a SELECT statement based on the product ID.

[0164] Input: Product information request (product ID)

[0165] Output: Warranty information data

[0166] Step 8:

[0167] The server returns the extracted warranty information to the terminal, converts it into JSON format, and sends it to the terminal as an HTTP response.

[0168] Input: Warranty information data

[0169] Output: Warranty information response

[0170] Step 9:

[0171] The terminal displays the received warranty information on the screen. The terminal parses the received JSON data and dynamically generates and displays the warranty information in HTML.

[0172] Input: Warranty information response

[0173] Output: Warranty information displayed on screen

[0174] Step 10:

[0175] The server inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The server then formats the collected data into an appropriate format and inputs it into the generative AI model to make predictions.

[0176] Input: Purchase data and failure information

[0177] Output: Failure rate and repair cost prediction results

[0178] Step 11:

[0179] The server personalizes the prediction results and stores them in a database for each user. The server associates the prediction results with the user ID and inserts or updates them into the database.

[0180] Input: Failure rate and repair cost prediction results

[0181] Output: Personalized prediction data

[0182] Step 12:

[0183] The user clicks the "Aftercare Recommendations" button. The user clicks a button on the interface to trigger an event.

[0184] Input: User input (button click)

[0185] Output: Aftercare recommendation request

[0186] Step 13:

[0187] The server integrates the purchase history and failure prediction data to evaluate the need for after-sales service, analyzes the integrated data, and generates after-sales service recommendations based on an algorithm.

[0188] Input: Aftercare recommendation requests, purchase history, failure prediction data

[0189] Output: Aftercare recommendation results

[0190] Step 14:

[0191] The server sends the aftercare recommendation results to the device, converts the recommendation results into JSON format, and sends it to the device as an HTTP response.

[0192] Input: Aftercare recommendation results

[0193] Output: Aftercare recommended response

[0194] Step 15:

[0195] The device will notify the user of the recommended results and display detailed information. The device will parse the received JSON data and dynamically generate and display the recommended results in HTML.

[0196] Input: Aftercare recommendation response

[0197] Output: Aftercare recommendation results displayed on screen

[0198] Step 16:

[0199] The user checks the details of the recommended aftercare service and takes the necessary steps. The user clicks on the link for the recommended aftercare service to go to the details page and proceed with the necessary steps.

[0200] Input: Display aftercare recommendation results

[0201] Output: Aftercare service application procedure

[0202] (Application example 1)

[0203] 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."

[0204] Currently, it is difficult for users to individually manage warranty and after-sales care information for home appliances and electronic devices purchased online, which increases the amount of work required. In addition, since there is no prediction of failure rates or repair costs after purchase, users often miss opportunities to receive appropriate after-sales care services. This results in issues such as lower user satisfaction and lower customer retention rates.

[0205] 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.

[0206] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to users based on the predicted failure rates and repair costs; means for automatically acquiring purchase history from an e-commerce platform and centrally managing warranty information; and means for transmitting personalized after-care service recommendations based on the predicted data to a user terminal. This allows users to centrally manage warranty information and after-care information for purchased products and quickly receive optimal after-care services based on the predicted failure rates and repair costs.

[0207] A "generative AI model" is a type of artificial intelligence that uses purchase data and failure information to predict product failure rates and repair costs.

[0208] A "custom action" is a program that automatically performs specific actions or processes according to the user's needs.

[0209] "Purchase Data" refers to information about products purchased by a User through online shopping.

[0210] "Warranty information" refers to information regarding the warranty period and warranty details provided at the time of product purchase.

[0211] "Aftercare information" refers to information about services such as maintenance, repair, and replacement after purchasing a product.

[0212] "Failure information" refers to data regarding the circumstances and causes of a product failure.

[0213] "Failure rate" is an indicator that indicates the rate at which a certain number of products fail within a specific period of time.

[0214] "Repair costs" refers to the costs required to repair a broken product.

[0215] "Aftercare services" refers to support and maintenance services provided for products after purchase.

[0216] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[0217] "Personalized services" refer to services that are customized based on the characteristics and needs of individual users.

[0218] "Server" refers to a high-performance computer system that stores, manages, and processes data.

[0219] This invention is a system that uses generative AI models and custom actions to provide warranty and after-care information based on user purchase data. To implement this system, a program based on the following steps is required.

[0220] Hardware and software used:

[0221] Hardware:

[0222] server

[0223] User's device (smartphone, smart glasses, head-mounted display)

[0224] software:

[0225] Backend: Python, Flask

[0226] Frontend: React Native

[0227] Database: MongoDB

[0228] AI model: TensorFlow

[0229] Overview of what the system does:

[0230] Retrieving purchase data:

[0231] When a user logs in to the e-commerce platform, the terminal sends the login information to the server. The server obtains the authentication information and, after successful login, retrieves the user's purchase history data from the e-commerce platform. This data is stored in a MongoDB database.

[0232] Warranty information provided:

[0233] When a user selects a specific product in the application, the device requests information about that product from the server, which then retrieves the corresponding warranty information from the MongoDB database and returns it to the device, which then displays the warranty information on the user's screen.

[0234] Failure rate and repair cost forecast:

[0235] The server inputs the collected purchase data and failure information into a generative AI model built with TensorFlow, which predicts product failure rates and repair costs and stores the results in a personalized database.

[0236] Aftercare service advice:

[0237] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for the most appropriate aftercare service. The generated recommendation results are sent to the user's device, which notifies the user and displays detailed information. The user can then proceed with the subscription process for the recommended aftercare service.

[0238] Examples:

[0239] For example, when a user logs into the app on their smartphone, warranty information for a recently purchased refrigerator is automatically displayed. The aftercare screen displays information such as "Predicted failure rate: Low (less than 5%)" and "Predicted repair cost: Less than 5,000 yen." If necessary, the user can click the "Apply for aftercare service" button to proceed with the process.

[0240] Example prompt sentence:

[0241] I'd like to check the warranty information for my refrigerator. I'm also considering after-sales service. Could you please tell me what the warranty covers, the failure rate, and repair costs? Also, could you recommend any after-sales service?

[0242] This allows the system of the present invention to centrally manage and provide warranty and after-care information for products purchased online by users, enabling them to quickly receive optimal after-care service based on predicted failure rates and repair costs.

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] A user logs in to an e-commerce platform. The terminal sends the user's login information to the server. The server authenticates the login information and obtains the user's ID if successful.

[0246] Input: User login information

[0247] Output: User ID

[0248] Step 2:

[0249] The server retrieves purchase history data from the e-commerce platform based on the user's ID, and stores the data in a MongoDB database.

[0250] Input: User ID

[0251] Output: Purchase history data

[0252] Step 3:

[0253] When a user selects a specific product, the device sends a request to the server with information about the selected product. The server extracts the product's warranty information from the MongoDB database and returns it to the device. The device then displays the warranty information on its screen.

[0254] Input: User selected product information

[0255] Output: Warranty information for the product

[0256] Step 4:

[0257] The server inputs the collected purchase data and failure information into a TensorFlow generative AI model, which then predicts product failure rates and repair costs and stores the results in a personalized database.

[0258] Input: Purchase data and failure information

[0259] Output: Predicted failure rate and repair costs

[0260] Step 5:

[0261] When a user clicks the "Aftercare Recommendation" button, the device sends the information to the server. The server then combines the purchase history with the predicted data on failure rates and repair costs to evaluate the need for aftercare services. The generated recommendation results are sent to the user's device, which then notifies the user.

[0262] Input: Purchase history and predicted failure rate and repair cost data

[0263] Output: Aftercare service recommendation results

[0264] Step 6:

[0265] The user checks the details of the recommended aftercare service and completes the necessary procedures. The terminal sends the procedure completion information to the server, and the server updates the information in the database.

[0266] Input: User's aftercare service procedure information

[0267] Output: Updated database information

[0268] The above is a flow of specific processing steps for implementing this invention, with inputs and outputs clearly defined for each step. This processing flow allows users to centrally manage warranty and after-sales care information for purchased products, enabling them to quickly receive appropriate after-sales care service.

[0269] 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.

[0270] This invention utilizes generative AI models and custom actions to provide a system that provides warranty and after-care information based on user purchase data, and combines it with an emotion engine that recognizes user emotions to provide more personalized services. This system improves user satisfaction and reduces stress by providing warranty and after-care information and recommending after-care services based on the user's emotional data obtained by the emotion engine. It also includes a means for analyzing purchase data and failure information collected from e-commerce platforms to predict product failure rates and repair costs.

[0271] Explanation of program processing

[0272] 1. Acquiring purchase data

[0273] User: Logs into an online shopping site and enters their account information.

[0274] Terminal: Login information is sent to the authentication server and authenticated.

[0275] Server: After successful authentication, the EC platform API is called based on the user ID to retrieve the purchase history.

[0276] Server: Store the acquired purchase history data in a database.

[0277] 2. Acquiring Emotion Data

[0278] User: Provide real-time facial and voice data when checking warranty and aftercare information.

[0279] Device: Recognizes the user's facial expressions and voice and sends them to the emotion engine.

[0280] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[0281] 3. Providing warranty information

[0282] User: Select the product for which you want to view warranty information.

[0283] Terminal: Sends the selected product information as a request to the server.

[0284] Server: Extracts the warranty information for the relevant product from the database.

[0285] Server: Adjusts the extracted guarantee information based on the emotion data and returns it to the device.

[0286] Device: Display adjusted warranty information on the user's screen.

[0287] 4. Failure rate and repair cost prediction

[0288] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0289] Server: Personalizes prediction results and stores them in a database for each user.

[0290] 5. Aftercare service advice

[0291] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0292] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[0293] Server: Sends the recommendation results to the user's device.

[0294] Device: Notify the user of the recommendation and provide more information.

[0295] User: Check the details of the recommended aftercare service and sign up if necessary.

[0296] Specific examples

[0297] Example 1: Acquiring purchase data and utilizing sentiment data

[0298] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[0299] 2. Device: After logging in, the purchase history of the "smart band" is sent from the EC platform to the server.

[0300] 3. Server: Stores purchase data in a database and runs the emotion engine to obtain user emotion data.

[0301] 4. User: If you want to check the warranty information, select "Smart Band" on your device, and the emotion engine will analyze your emotion.

[0302] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "smart band" from the database.

[0303] 6. Server: Based on the analysis results of the emotion engine, adjust the guarantee information and send it back to the device.

[0304] 7. Device: Display the adjusted warranty information on the user's screen.

[0305] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[0306] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of the "smart band."

[0307] 2. Server: Based on the prediction results, it reflects the analysis results of the emotion engine and evaluates the need for aftercare services for the user.

[0308] 3. User: Click the "Aftercare Recommendations" button to see the recommendations based on your emotional data.

[0309] 4. On the device: Notify the user of the recommended results and display details.

[0310] 5. User: Check the details of the recommended aftercare service and sign up if necessary.

[0311] In this way, by combining an emotion engine, the present invention realizes the provision of warranty information and aftercare information that takes into account the user's emotional state, thereby reducing user stress and improving customer satisfaction.

[0312] The processing flow will be explained below.

[0313] Specific processing flow

[0314] 1. Acquiring purchase and sentiment data

[0315] Step 1:

[0316] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[0317] Step 2:

[0318] On the device: The login information entered by the user is sent to the authentication server.

[0319] Step 3:

[0320] Server: The authentication server verifies the user ID and password, and if authentication is successful, it calls the EC platform API based on the user ID to obtain the purchase history.

[0321] Step 4:

[0322] Server: Stores the acquired purchase history data in a database within the system.

[0323] Step 5:

[0324] User: Navigate through the site to select the product for which they want to check warranty and aftercare information.

[0325] Step 6:

[0326] Terminal: Sends the selected product information as a request to the server. At the same time, sends the user's facial expressions and voice to the emotion engine in real time.

[0327] Step 7:

[0328] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[0329] 2. Providing warranty information

[0330] Step 8:

[0331] Server: Extracts warranty information for the relevant product from the database and adjusts the information based on emotion data.

[0332] Step 9:

[0333] Server: Adjusts the extracted warranty information and returns it to the user's device.

[0334] Step 10:

[0335] Terminal: Display the returned warranty information on the user's screen.

[0336] 3. Failure rate and repair cost prediction

[0337] Step 11:

[0338] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0339] Step 12:

[0340] Server: Personalizes prediction results and stores them in a database for each user.

[0341] 4. Aftercare service advice

[0342] Step 13:

[0343] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0344] Step 14:

[0345] Server: Runs an algorithm that integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[0346] Step 15:

[0347] Server: Sends the generated aftercare service recommendation results to the user device.

[0348] Step 16:

[0349] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[0350] Step 17:

[0351] User: Check the details of the recommended aftercare service and sign up if necessary.

[0352] Example 2

[0353] 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."

[0354] Conventional systems for providing warranty and after-care information did not take into account the user's emotional state. This placed a heavy psychological burden on users, resulting in lower customer satisfaction. Furthermore, the accuracy of predictions based on purchase history and failure information was insufficient, resulting in problems with the after-care services provided not meeting the user's actual needs.

[0355] 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.

[0356] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing the collected purchase data and failure information and predicting product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for acquiring user emotional data and customizing the warranty information and after-care information based on the data; means for authenticating the user's login information and acquiring purchase history data from the EC platform; and means for storing the acquired purchase history data in a database, and, when the user selects a specific product, extracting the warranty information for that product from the database and adjusting and displaying it based on the emotional data. This makes it possible to provide warranty information and after-care information that takes the user's emotional state into consideration, thereby reducing the user's psychological burden and improving customer satisfaction.

[0357] A "generative AI model" is an artificial intelligence algorithm that is trained to make predictions or classifications based on specific input data.

[0358] A "custom action" is a unique process or operation that the system automatically performs in response to specific user actions or data input.

[0359] "User purchasing data" refers to the history of products purchased by a user on an online shopping site and information related to such purchases.

[0360] "Warranty Information" means information regarding the product warranty provided with the purchased product.

[0361] "Aftercare information" refers to information regarding support and services provided after purchasing a product.

[0362] "Failure information" refers to the product's failure history and data related to the failure.

[0363] "Emotional data" refers to information that indicates the emotional state of a user, such as information obtained from facial expressions or voice.

[0364] An "emotion engine" is software or a system for analyzing a user's emotional data and identifying the user's emotional state.

[0365] An "EC platform" is an e-commerce platform that allows you to sell and purchase products online.

[0366] An "authentication server" is a server that verifies a user's login information and performs authentication.

[0367] A "database" is a system that systematically organizes and stores information so that it can be searched and used as needed.

[0368] This invention relates to a system that utilizes generative AI models and custom actions to provide warranty and aftercare information based on user purchase data. This allows warranty and aftercare information to be customized based on user emotional data, thereby increasing user satisfaction and reducing stress.

[0369] The system utilizes the following major hardware and software components:

[0370] Server: A central computer system for processing and storing data, including the e-commerce platform API, authentication server, and emotion engine.

[0371] Terminal: A device used by a user (e.g., smartphone, PC) that displays the user interface and collects data using a camera and microphone.

[0372] Database: A system for storing acquired purchase history data and emotional data.

[0373] Emotion engine: Software that analyzes emotional data from a user's facial expressions and voice to identify their emotional state.

[0374] System Overview

[0375] Acquiring purchase data

[0376] User: Visits an online shopping site and logs in using their account information.

[0377] On your device: Send your login information to the authentication server.

[0378] Server: After successful authentication, the EC platform API is called based on the user ID, the purchase history is retrieved, and the history is saved in the database.

[0379] Acquiring emotion data

[0380] User: Provides real-time facial and audio feedback when checking warranty and aftercare information.

[0381] Device: Sends real-time data acquired by the camera and microphone to the emotion engine.

[0382] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[0383] Providing warranty information

[0384] User: Select the product on the device for which they want to check warranty information.

[0385] Terminal: Sends the selected product information as a request to the server.

[0386] Server: Extracts the warranty information for the relevant product from the database, customizes the warranty information based on the emotion data, and sends it to the terminal.

[0387] Device: Display customized warranty information to the user.

[0388] Failure rate and repair cost prediction

[0389] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0390] Server: Personalizes the prediction results and stores them in a database.

[0391] Aftercare service advice

[0392] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0393] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[0394] Server: Sends the recommendation results to the user's device.

[0395] Device: Notify the user of the recommendation and provide more information.

[0396] User: Check the details of the recommended aftercare service and sign up if necessary.

[0397] Specific examples

[0398] Example 1: Acquiring purchase data and utilizing sentiment data

[0399] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[0400] 2. Device: After logging in, it sends a request to the EC platform API and transmits the purchase history of the "smart band" to the server.

[0401] 3. Server: Stores purchase data in a database and launches an emotion engine to obtain the user's emotional state in real time.

[0402] 4. User: If you want to check the warranty information on your device, select "Smart Band."

[0403] 5. Terminal: Sends the selection information to the server, which extracts the product information from the database.

[0404] 6. Server: Adjusts the guarantee information based on the emotion data and returns it to the device.

[0405] 7. Device: Display the adjusted warranty information on the user's screen.

[0406] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[0407] 1. Server: Collects purchase data and failure information from each e-commerce platform and inputs it into the generative AI model.

[0408] 2. Server: Predict the failure rate and repair costs of a "smart band."

[0409] 3. Server: Reflects the user's emotional data and evaluates the need for aftercare.

[0410] 4. User: Click the "Aftercare Recommendations" button to see the recommendations based on the emotional data.

[0411] 5. On the device: Notify the user of the recommended results and display detailed information.

[0412] 6. User: Check the details of the recommended aftercare service and sign up if necessary.

[0413] Prompt Sentence Examples

[0414] "Please explain in detail the program that provides warranty information to users who purchase smart bands online based on their purchase history and real-time sentiment data."

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

[0416] Step 1:

[0417] A user accesses an online shopping site and logs in by entering their account information (user ID and password). This results in the acquisition of login information (input: user login information, output: transmission of login request).

[0418] Step 2:

[0419] The terminal sends login information to the authentication server (input: user login information, output: sent authentication request). The authentication server compares the received information with a database, and if the user is authenticated, issues an authentication token (input: authentication request, output: authentication token).

[0420] Step 3:

[0421] The terminal calls the EC platform API using the authentication token and sends a request to acquire the user's purchase history (input: authentication token, output: transmission of purchase history request).

[0422] The server saves the purchase history obtained from the EC platform in a database (input: purchase history data, output: saving to database).

[0423] Step 4:

[0424] When the user checks warranty information or aftercare information, real-time facial expressions and voice are provided (input: user's facial expressions and voice data, output: collection of emotion data).

[0425] The device sends data acquired by the user's camera and microphone to the emotion engine (input: facial expression and voice data, output: sent to the emotion engine).

[0426] Step 5:

[0427] The server's emotion engine analyzes the user's emotions and generates emotion data (input: facial expression and voice data, output: emotion data). Machine learning models and voice analysis algorithms are used for the analysis.

[0428] Step 6:

[0429] When a user selects a specific product and wants to check its warranty information, he or she selects the product on the terminal (input: product selection information, output: request sent to server).

[0430] The terminal sends information about the selected product to the server (input: product ID, output: sending purchase history).

[0431] Step 7:

[0432] The server extracts the warranty information of the relevant product from the database (input: product ID, output: extracted warranty information). The extracted warranty information is adjusted based on the emotion data (input: warranty information, emotion data / output: adjusted warranty information).

[0433] The server sends the adjusted warranty information to the terminal (input: adjusted warranty information, output: transmission to terminal).

[0434] Step 8:

[0435] The terminal displays the adjusted warranty information on the user's screen (input: adjusted warranty information, output: display on user's screen).

[0436] Step 9:

[0437] The server inputs purchasing data and failure information collected from all e-commerce platforms into a generative AI model to predict product failure rates and repair costs (input: purchasing data, failure information; output: predicted failure rates and repair costs).

[0438] Step 10:

[0439] The server personalizes the prediction results and stores them in a database for each user (input: prediction results, output: storage of prediction results).

[0440] Step 11:

[0441] The user clicks the "Recommend Aftercare" button to see the recommendation results (Input: User click information, Output: Submit recommendation request).

[0442] The server integrates the purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services (input: purchase history, prediction data, emotion data; output: aftercare recommendation results).

[0443] Step 12:

[0444] The server sends the recommendation results to the user terminal (input: recommendation results, output: transmission to user terminal).

[0445] The terminal notifies the user of the recommended results and displays detailed information (input: recommended results, output: notification to user, display of detailed information).

[0446] Step 13:

[0447] The user checks the details of the recommended aftercare service and completes the subscription procedure if necessary (input: recommendation result, output: subscription procedure).

[0448] (Application example 2)

[0449] 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."

[0450] Conventional systems for providing warranty and after-care information provide uniform information regardless of the user's emotions, which has the problem of not sufficiently improving user satisfaction or reducing stress.In addition, after-care service proposals based on product failure rates and repair cost predictions are insufficient, making it difficult to provide advice appropriate to each user's individual situation.

[0451] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0452] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; and means for acquiring user emotion data, recognizing emotions using an emotion engine, and personalizing warranty information and after-care information based on the emotion data. This makes it possible to provide personalized warranty information and after-care information that reflects the user's emotions, thereby achieving user satisfaction and stress reduction.

[0453] A "generative AI model" is an artificial intelligence model that analyzes user purchase data and failure information and provides warranty and after-care information.

[0454] A "custom action" is a set of actions that executes personalized warranty information or aftercare services for a specific user based on a generative AI model.

[0455] "Purchase Data" refers to historical information about products purchased by a user on e-commerce platforms and other online shopping sites.

[0456] "Failure information" refers to information such as the failure history and repair history of each product, and failure rate data provided by the manufacturer.

[0457] "Failure rate" is an indicator of the probability that a particular product will fail within a certain period of time.

[0458] "Repair costs" are the costs required to repair a broken product.

[0459] "Aftercare services" are services such as repairs, maintenance, and warranty extensions provided after a product is purchased.

[0460] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, voice, and other physiological data.

[0461] The "emotion engine" is an engine that analyzes the user's emotional data and recognizes their emotional state.

[0462] "Personalization" means customizing information and services to suit the individual preferences and feelings of each user.

[0463] An "EC platform" is an online system for conducting electronic commerce, where users can search for and purchase products.

[0464] The present invention is a system that utilizes generative AI models and custom actions to provide warranty and after-care information based on user purchase data. By combining this system with an emotion engine, the system provides personalized services that take user emotions into account. Below, we will explain in detail the various functions of the system and its implementation.

[0465] Hardware and Software Use

[0466] This system is realized using the following hardware and software.

[0467] Smartphone camera and microphone: Used to capture the user's facial expressions and voice.

[0468] Device: A device used by a user, such as a smartphone or tablet.

[0469] Server: Stores user authentication information, purchase history data, sentiment data, and runs generative AI models.

[0470] Emotional Engine: Analyzes user emotional data using a virtual module called "Emotional Analysis."

[0471] Generative AI model: A virtual module called "AIPredictor" is used to provide warranty and after-care information.

[0472] Acquiring purchase and sentiment data

[0473] A user logs in to an online shopping site and enters their account information into the device. The device sends the login information to the server, which then authenticates them. If authentication is successful, the server retrieves the user's purchase history data from the e-commerce platform via API and stores it in a database.

[0474] Next, when the user selects a product for which they wish to check warranty or after-sales information, the device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine, which then analyzes the user's emotions in real time and generates emotion data.

[0475] Providing warranty and aftercare information

[0476] When the device selects a specific product, the server retrieves the product's warranty information from the database. The warranty information is then analyzed by a generative AI model and personalized based on emotional data from the emotion engine. That is, if the user is stressed, a message that provides reassurance is added; if the user is satisfied, a message that emphasizes further comfort is added. The adjusted warranty information is then sent back to the device and displayed on the user's screen.

[0477] Prediction of failure rates and repair costs, and recommendations for aftercare services

[0478] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The prediction results are then analyzed along with emotional data to recommend optimal after-sales services to users.

[0479] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can check the details of the recommended aftercare service and, if necessary, complete the subscription procedure.

[0480] Examples of specific examples and prompts

[0481] For example, if a user is watching video content on a smartphone app and the emotion engine detects a stressed state, a personalized message such as "This product's warranty is very reassuring" will be displayed when providing warranty information.

[0482] An example of a prompt for a generative AI model is:

[0483] "A user is concerned about the possibility of their recently purchased smartphone breaking down. Please predict the failure rate and repair costs based on the selected product ID and the user's purchase history data."

[0484] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0485] Step 1:

[0486] A user logs in to an online shopping site and enters their account information. The device sends this login information to the server, which then requests authentication from the authentication server. If authentication is successful, the server calls the EC platform API based on the user ID and obtains the user's purchase history data. The obtained purchase history data is stored in a database.

[0487] Input: User login information

[0488] Output: User purchase history data (stored in database)

[0489] Step 2:

[0490] The user selects the product for which they want to check warranty and after-sales information. The device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine. The emotion engine analyzes the user's emotions in real time and generates emotion data.

[0491] Input: User's facial expression data, voice data

[0492] Output: Parsed emotion data

[0493] Step 3:

[0494] When a device selects a specific product, it sends that information as a request to the server. The server extracts the product's warranty information from the database and analyzes it using a generative AI model. A personalized message based on emotional data is added to the analyzed warranty information, generating an adjusted warranty.

[0495] Input: Product selection information, emotion data

[0496] Output: Adjusted warranty information

[0497] Step 4:

[0498] The server returns the adjusted warranty information to the terminal, which displays it on the user's screen. The user then checks the displayed warranty information.

[0499] Input: Adjusted warranty information

[0500] Output: What is displayed to the user

[0501] Step 5:

[0502] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The predicted failure rates and repair costs are then analyzed along with emotional data to recommend optimal after-sales services to users.

[0503] Input: Purchase data, failure information

[0504] Output: Failure rate prediction data, repair cost prediction data

[0505] Step 6:

[0506] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can then check the details of the recommended aftercare service and, if necessary, apply for it.

[0507] Input: purchase history, failure prediction data, emotion data

[0508] Output: Display of aftercare service recommendation results and detailed information

[0509] 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.

[0510] 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.

[0511] 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.

[0512] [Second embodiment]

[0513] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0514] 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.

[0515] 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).

[0516] 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.

[0517] 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.

[0518] 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).

[0519] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0520] 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.

[0521] 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.

[0522] 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.

[0523] 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.

[0524] 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."

[0525] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and provides users with after-care services based on subsequent failure rates and repair costs. This system is characterized by the use of generative AI models and custom actions to quickly provide users with personalized information.

[0526] Explanation of program processing

[0527] 1. Acquiring purchase data

[0528] User: Logs into an online shopping site and enters their account information.

[0529] Terminal: Login information is sent to the authentication server and authenticated.

[0530] Server: After successful authentication, retrieve the purchase history from the EC platform based on the user ID.

[0531] Server: Store the acquired purchase history data in a database.

[0532] 2. Providing warranty information

[0533] User: Select the product for which you want to view warranty information.

[0534] Terminal: Sends the selected product information as a request to the server.

[0535] Server: Extracts the warranty information for the relevant product from the database.

[0536] Server: Returns the extracted warranty information to the device.

[0537] Device: Display the received warranty information on the screen.

[0538] 3. Failure rate and repair cost prediction

[0539] Server: Inputs purchase data and failure information collected from all e-commerce platforms into the generative AI model.

[0540] Server: Uses generative AI models to predict failure rates and repair costs for target products.

[0541] Server: Personalizes prediction results and stores them in a database for each user.

[0542] 4. Aftercare service advice

[0543] User: Clicks the Aftercare Recommendations button.

[0544] Server: Integrates purchase history and failure prediction data to assess the need for aftercare services.

[0545] Server: Sends aftercare recommendation results to the device.

[0546] On your device: Notify the user of the recommendation and display detailed information about it.

[0547] User: Review the details of the recommended aftercare service and take any necessary steps.

[0548] Specific examples

[0549] Example 1: Retrieving purchase data and displaying warranty information

[0550] 1. User: Purchases a home appliance "refrigerator" online and logs in to his / her account.

[0551] 2. Terminal: After logging in, the purchase history of "refrigerator" is sent from the e-commerce platform to the server.

[0552] 3. Server: Stores the purchase data in the database. At the same time, retrieves the refrigerator warranty information from the e-commerce platform and stores it in the database.

[0553] 4. User: If you want to check the warranty information, select "Refrigerator" on your device.

[0554] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "refrigerator" from the database.

[0555] 6. Terminal: Display the extracted warranty information on the user's screen.

[0556] Example 2: Predicting failure rates and repair costs and recommending aftercare

[0557] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of "refrigerators."

[0558] 2. Server: Based on the prediction results, evaluate the need for aftercare services for the user and store the recommendation results in the database.

[0559] 3. User: Click the "Aftercare Recommendations" button to view details of the recommended aftercare services.

[0560] 4. On the device: Notify the user of the recommended results and display details.

[0561] 5. User: Complete the recommended aftercare service enrollment process.

[0562] In this way, the system of the present invention centrally manages warranty and after-sales information for products purchased online, reducing stress for users when a product breaks down. It also improves customer satisfaction by recommending personalized after-sales services.

[0563] The processing flow will be explained below.

[0564] Step 1:

[0565] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[0566] Step 2:

[0567] On the device: The login information entered by the user is sent to the authentication server.

[0568] Step 3:

[0569] Server: The authentication server verifies the user ID and password, and if authentication is successful, calls the EC platform API based on the user ID.

[0570] Step 4:

[0571] Server: Obtains user purchase history via the EC platform API and stores that data in the system database.

[0572] Step 5:

[0573] User: If they want to view warranty information for a specific product they purchased, they select that product in the system.

[0574] Step 6:

[0575] Terminal: Sends the selected product information as a request to the server.

[0576] Step 7:

[0577] Server: Extracts warranty information for the requested product from the database.

[0578] Step 8:

[0579] Server: Returns the extracted warranty information to the user's device.

[0580] Step 9:

[0581] Terminal: Display the returned warranty information on the user's screen.

[0582] Step 10:

[0583] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0584] Step 11:

[0585] Server: The generated failure rate and repair cost prediction results are personalized and stored in a database for each user.

[0586] Step 12:

[0587] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0588] Step 13:

[0589] Server: Runs an algorithm that combines purchase history and failure prediction data to assess the need for aftercare services.

[0590] Step 14:

[0591] Server: Sends the generated aftercare service recommendation results to the user device.

[0592] Step 15:

[0593] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[0594] Step 16:

[0595] User: Check the details of the recommended aftercare service and sign up if necessary.

[0596] Example 1

[0597] 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."

[0598] In today's online shopping environment, users must purchase a variety of home appliances and electronic devices and individually manage the associated warranty and after-care information, which is extremely time-consuming. Furthermore, insufficient information on product failure rates and repair costs after purchase makes it difficult for users to select the appropriate after-care service. Furthermore, the lack of personalized information reduces user convenience. Therefore, to solve these issues, a system is needed that can centrally manage purchase data and failure information and provide users with prompt and accurate warranty information and after-care services.

[0599] 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.

[0600] In this invention, the server includes: means for providing warranty and after-care information based on user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for logging in using the user's account information and acquiring the purchase history after authentication; means for saving the acquired purchase history data in a database; means for extracting warranty information for products selected by the user from the database and displaying it on the user's terminal; means for personalizing the prediction results and saving them in the database for each user; and means for evaluating the need for after-care services and displaying the results on the user's terminal. This allows users to centrally manage warranty and after-care information for home appliances and electronic devices purchased online, providing prompt and accurate information. Furthermore, personalized after-care service recommendations based on predicted failure rates and repair costs significantly improve user convenience.

[0601] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to make predictions and analyze data based on collected data.

[0602] A "custom action" is a special program or function designed to perform a specific task or operation.

[0603] "User purchasing data" refers to data including information about products purchased by users on online shopping platforms and their purchase history.

[0604] "Warranty Information" refers to information that describes the conditions and scope of repairs or replacements within a certain period from the date of purchase of the product.

[0605] "Aftercare information" refers to information regarding services such as repairs, maintenance, and support provided after the purchase of a product.

[0606] "Failure information" refers to data such as troubles and repair history when a product stops working properly.

[0607] "Failure rate" refers to the probability that a product will fail within a specific period of time.

[0608] "Repair costs" refers to the costs required to repair a product when it breaks down.

[0609] "Personalization" refers to the customization of information and services based on the characteristics and history of each individual user.

[0610] "Authentication token" refers to a security token used when exchanging user authentication information.

[0611] "Online platform" refers to a service provision infrastructure available on the Internet, including websites and applications.

[0612] A "database" refers to a dedicated system for efficiently storing, searching, and managing large amounts of data.

[0613] "User terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0614] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and quickly provides personalized information to users. This system uses generative AI models and custom actions to recommend the most suitable after-care services to users.

[0615] First, a user logs in to an online shopping site and enters their account information. The login information is sent from the terminal to the authentication server, which receives an authentication token. After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID and stores this purchase history data in a database.

[0616] Next, when the user selects the product for which they wish to check warranty information, the terminal sends a request to the server with the information about the selected product. The server extracts the warranty information for that product from the database and returns it to the terminal. The terminal then displays the received warranty information on its screen.

[0617] The server then inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The prediction results are personalized and stored in a database for each user.

[0618] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for aftercare service. The evaluation results are sent to the device, which notifies the user and displays detailed information. The user can then check the details of the recommended aftercare service and take the necessary steps.

[0619] This system uses various hardware and software. The server uses a high-performance database system (e.g., MySQL or PostgreSQL) and a machine learning framework such as PyTorch or TensorFlow to run the AI ​​model. The terminal is a device operated by the user, such as a computer or smartphone, which communicates with the server via a browser or dedicated application.

[0620] As a concrete example, a user purchases a home appliance "refrigerator" online and logs in to their account. After logging in, the e-commerce platform sends the purchase history for "refrigerator" to the server. The server saves the purchase data in a database and also retrieves and stores warranty information. If the user wants to check the warranty information, they select "refrigerator" on their device, and the server extracts and displays the warranty information. The generative AI model also predicts the failure rate and repair costs of the "refrigerator," and after-care services are recommended. The user clicks the "Recommend After-care" button, checks the recommended after-care services, and proceeds with the procedure.

[0621] An example of a prompt to input to a generative AI model is as follows:

[0622] Using purchase data and failure information as input, predict the failure rate and repair costs for the target product.

[0623] In this way, the system of the present invention can centrally manage warranty and after-sales information for products purchased by users through online shopping, enabling the provision of fast and accurate information. Furthermore, personalized after-sales service recommendations can significantly improve user convenience.

[0624] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0625] Step 1:

[0626] A user logs into an online shopping site and enters their account information, such as an email address and password, which is then processed on the device.

[0627] Input: User's email address and password

[0628] Output: Authentication request data

[0629] Step 2:

[0630] The terminal sends login information to the authentication server and receives an authentication token. The authentication server verifies the login information and issues an authentication token if it is valid.

[0631] Input: Authentication request data

[0632] Output: Authentication token

[0633] Step 3:

[0634] After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID. The server then uses the authentication token to retrieve the purchase history data from the EC platform via API.

[0635] Input: Authentication token and user ID

[0636] Output: Purchase history data

[0637] Step 4:

[0638] The server saves the acquired purchase history data in the database. The server formats the purchase history data into an appropriate format and saves it in the database using the INSERT statement.

[0639] Input: Purchase history data

[0640] Output: Purchase history stored in the database

[0641] Step 5:

[0642] The user selects the product for which they wish to check warranty information. After logging in, the user clicks on the product in question from the purchase history list on their My Page.

[0643] Input: User input (product selection)

[0644] Output: Product ID

[0645] Step 6:

[0646] The terminal sends the information about the selected product to the server as a request. The terminal uses AJAX to send a request including the product ID to the server.

[0647] Input: Product ID

[0648] Output: Product information request

[0649] Step 7:

[0650] The server extracts the warranty information for the relevant product from the database. The server retrieves the warranty information from the database using a SELECT statement based on the product ID.

[0651] Input: Product information request (product ID)

[0652] Output: Warranty information data

[0653] Step 8:

[0654] The server returns the extracted warranty information to the terminal, converts it into JSON format, and sends it to the terminal as an HTTP response.

[0655] Input: Warranty information data

[0656] Output: Warranty information response

[0657] Step 9:

[0658] The terminal displays the received warranty information on the screen. The terminal parses the received JSON data and dynamically generates and displays the warranty information in HTML.

[0659] Input: Warranty information response

[0660] Output: Warranty information displayed on screen

[0661] Step 10:

[0662] The server inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The server then formats the collected data into an appropriate format and inputs it into the generative AI model to make predictions.

[0663] Input: Purchase data and failure information

[0664] Output: Failure rate and repair cost prediction results

[0665] Step 11:

[0666] The server personalizes the prediction results and stores them in a database for each user. The server associates the prediction results with the user ID and inserts or updates them into the database.

[0667] Input: Failure rate and repair cost prediction results

[0668] Output: Personalized prediction data

[0669] Step 12:

[0670] The user clicks the "Aftercare Recommendations" button. The user clicks a button on the interface to trigger an event.

[0671] Input: User input (button click)

[0672] Output: Aftercare recommendation request

[0673] Step 13:

[0674] The server integrates the purchase history and failure prediction data to evaluate the need for after-sales service, analyzes the integrated data, and generates after-sales service recommendations based on an algorithm.

[0675] Input: Aftercare recommendation requests, purchase history, failure prediction data

[0676] Output: Aftercare recommendation results

[0677] Step 14:

[0678] The server sends the aftercare recommendation results to the device, converts the recommendation results into JSON format, and sends it to the device as an HTTP response.

[0679] Input: Aftercare recommendation results

[0680] Output: Aftercare recommended response

[0681] Step 15:

[0682] The device will notify the user of the recommended results and display detailed information. The device will parse the received JSON data and dynamically generate and display the recommended results in HTML.

[0683] Input: Aftercare recommendation response

[0684] Output: Aftercare recommendation results displayed on screen

[0685] Step 16:

[0686] The user checks the details of the recommended aftercare service and takes the necessary steps. The user clicks on the link for the recommended aftercare service to go to the details page and proceed with the necessary steps.

[0687] Input: Display aftercare recommendation results

[0688] Output: Aftercare service application procedure

[0689] (Application example 1)

[0690] 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."

[0691] Currently, it is difficult for users to individually manage warranty and after-sales care information for home appliances and electronic devices purchased online, which increases the amount of work required. In addition, since there is no prediction of failure rates or repair costs after purchase, users often miss opportunities to receive appropriate after-sales care services. This results in issues such as lower user satisfaction and lower customer retention rates.

[0692] 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.

[0693] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to users based on the predicted failure rates and repair costs; means for automatically acquiring purchase history from an e-commerce platform and centrally managing warranty information; and means for transmitting personalized after-care service recommendations based on the predicted data to a user terminal. This allows users to centrally manage warranty information and after-care information for purchased products and quickly receive optimal after-care services based on the predicted failure rates and repair costs.

[0694] A "generative AI model" is a type of artificial intelligence that uses purchase data and failure information to predict product failure rates and repair costs.

[0695] A "custom action" is a program that automatically performs specific actions or processes according to the user's needs.

[0696] "Purchase Data" refers to information about products purchased by a User through online shopping.

[0697] "Warranty information" refers to information regarding the warranty period and warranty details provided at the time of product purchase.

[0698] "Aftercare information" refers to information about services such as maintenance, repair, and replacement after purchasing a product.

[0699] "Failure information" refers to data regarding the circumstances and causes of a product failure.

[0700] "Failure rate" is an indicator that indicates the rate at which a certain number of products fail within a specific period of time.

[0701] "Repair costs" refers to the costs required to repair a broken product.

[0702] "Aftercare services" refers to support and maintenance services provided for products after purchase.

[0703] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[0704] "Personalized services" refer to services that are customized based on the characteristics and needs of individual users.

[0705] "Server" refers to a high-performance computer system that stores, manages, and processes data.

[0706] This invention is a system that uses generative AI models and custom actions to provide warranty and after-care information based on user purchase data. To implement this system, a program based on the following steps is required.

[0707] Hardware and software used:

[0708] Hardware:

[0709] server

[0710] User's device (smartphone, smart glasses, head-mounted display)

[0711] software:

[0712] Backend: Python, Flask

[0713] Frontend: React Native

[0714] Database: MongoDB

[0715] AI model: TensorFlow

[0716] Overview of what the system does:

[0717] Retrieving purchase data:

[0718] When a user logs in to the e-commerce platform, the terminal sends the login information to the server. The server obtains the authentication information and, after successful login, retrieves the user's purchase history data from the e-commerce platform. This data is stored in a MongoDB database.

[0719] Warranty information provided:

[0720] When a user selects a specific product in the application, the device requests information about that product from the server, which then retrieves the corresponding warranty information from the MongoDB database and returns it to the device, which then displays the warranty information on the user's screen.

[0721] Failure rate and repair cost forecast:

[0722] The server inputs the collected purchase data and failure information into a generative AI model built with TensorFlow, which predicts product failure rates and repair costs and stores the results in a personalized database.

[0723] Aftercare service advice:

[0724] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for the most appropriate aftercare service. The generated recommendation results are sent to the user's device, which notifies the user and displays detailed information. The user can then proceed with the subscription process for the recommended aftercare service.

[0725] Examples:

[0726] For example, when a user logs into the app on their smartphone, warranty information for a recently purchased refrigerator is automatically displayed. The aftercare screen displays information such as "Predicted failure rate: Low (less than 5%)" and "Predicted repair cost: Less than 5,000 yen." If necessary, the user can click the "Apply for aftercare service" button to proceed with the process.

[0727] Example prompt sentence:

[0728] I'd like to check the warranty information for my refrigerator. I'm also considering after-sales service. Could you please tell me what the warranty covers, the failure rate, and repair costs? Also, could you recommend any after-sales service?

[0729] This allows the system of the present invention to centrally manage and provide warranty and after-care information for products purchased online by users, enabling them to quickly receive optimal after-care service based on predicted failure rates and repair costs.

[0730] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0731] Step 1:

[0732] A user logs in to an e-commerce platform. The terminal sends the user's login information to the server. The server authenticates the login information and obtains the user's ID if successful.

[0733] Input: User login information

[0734] Output: User ID

[0735] Step 2:

[0736] The server retrieves purchase history data from the e-commerce platform based on the user's ID, and stores the data in a MongoDB database.

[0737] Input: User ID

[0738] Output: Purchase history data

[0739] Step 3:

[0740] When a user selects a specific product, the device sends a request to the server with information about the selected product. The server extracts the product's warranty information from the MongoDB database and returns it to the device. The device then displays the warranty information on its screen.

[0741] Input: User selected product information

[0742] Output: Warranty information for the product

[0743] Step 4:

[0744] The server inputs the collected purchase data and failure information into a TensorFlow generative AI model, which then predicts product failure rates and repair costs and stores the results in a personalized database.

[0745] Input: Purchase data and failure information

[0746] Output: Predicted failure rate and repair costs

[0747] Step 5:

[0748] When a user clicks the "Aftercare Recommendation" button, the device sends the information to the server. The server then combines the purchase history with the predicted data on failure rates and repair costs to evaluate the need for aftercare services. The generated recommendation results are sent to the user's device, which then notifies the user.

[0749] Input: Purchase history and predicted failure rate and repair cost data

[0750] Output: Aftercare service recommendation results

[0751] Step 6:

[0752] The user checks the details of the recommended aftercare service and completes the necessary procedures. The terminal sends the procedure completion information to the server, and the server updates the information in the database.

[0753] Input: User's aftercare service procedure information

[0754] Output: Updated database information

[0755] The above is a flow of specific processing steps for implementing this invention, with inputs and outputs clearly defined for each step. This processing flow allows users to centrally manage warranty and after-sales care information for purchased products, enabling them to quickly receive appropriate after-sales care service.

[0756] 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.

[0757] This invention utilizes generative AI models and custom actions to provide a system that provides warranty and after-care information based on user purchase data, and combines it with an emotion engine that recognizes user emotions to provide more personalized services. This system improves user satisfaction and reduces stress by providing warranty and after-care information and recommending after-care services based on the user's emotional data obtained by the emotion engine. It also includes a means for analyzing purchase data and failure information collected from e-commerce platforms to predict product failure rates and repair costs.

[0758] Explanation of program processing

[0759] 1. Acquiring purchase data

[0760] User: Logs into an online shopping site and enters their account information.

[0761] Terminal: Login information is sent to the authentication server and authenticated.

[0762] Server: After successful authentication, the EC platform API is called based on the user ID to retrieve the purchase history.

[0763] Server: Store the acquired purchase history data in a database.

[0764] 2. Acquiring Emotion Data

[0765] User: Provide real-time facial and voice data when checking warranty and aftercare information.

[0766] Device: Recognizes the user's facial expressions and voice and sends them to the emotion engine.

[0767] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[0768] 3. Providing warranty information

[0769] User: Select the product for which you want to view warranty information.

[0770] Terminal: Sends the selected product information as a request to the server.

[0771] Server: Extracts the warranty information for the relevant product from the database.

[0772] Server: Adjusts the extracted guarantee information based on the emotion data and returns it to the device.

[0773] Device: Display adjusted warranty information on the user's screen.

[0774] 4. Failure rate and repair cost prediction

[0775] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0776] Server: Personalizes prediction results and stores them in a database for each user.

[0777] 5. Aftercare service advice

[0778] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0779] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[0780] Server: Sends the recommendation results to the user's device.

[0781] Device: Notify the user of the recommendation and provide more information.

[0782] User: Check the details of the recommended aftercare service and sign up if necessary.

[0783] Specific examples

[0784] Example 1: Acquiring purchase data and utilizing sentiment data

[0785] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[0786] 2. Device: After logging in, the purchase history of the "smart band" is sent from the EC platform to the server.

[0787] 3. Server: Stores purchase data in a database and runs the emotion engine to obtain user emotion data.

[0788] 4. User: If you want to check the warranty information, select "Smart Band" on your device, and the emotion engine will analyze your emotion.

[0789] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "smart band" from the database.

[0790] 6. Server: Based on the analysis results of the emotion engine, adjust the guarantee information and send it back to the device.

[0791] 7. Device: Display the adjusted warranty information on the user's screen.

[0792] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[0793] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of the "smart band."

[0794] 2. Server: Based on the prediction results, it reflects the analysis results of the emotion engine and evaluates the need for aftercare services for the user.

[0795] 3. User: Click the "Aftercare Recommendations" button to see the recommendations based on your emotional data.

[0796] 4. On the device: Notify the user of the recommended results and display details.

[0797] 5. User: Check the details of the recommended aftercare service and sign up if necessary.

[0798] In this way, by combining an emotion engine, the present invention realizes the provision of warranty information and aftercare information that takes into account the user's emotional state, thereby reducing user stress and improving customer satisfaction.

[0799] The processing flow will be explained below.

[0800] Specific processing flow

[0801] 1. Acquiring purchase and sentiment data

[0802] Step 1:

[0803] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[0804] Step 2:

[0805] On the device: The login information entered by the user is sent to the authentication server.

[0806] Step 3:

[0807] Server: The authentication server verifies the user ID and password, and if authentication is successful, it calls the EC platform API based on the user ID to obtain the purchase history.

[0808] Step 4:

[0809] Server: Stores the acquired purchase history data in a database within the system.

[0810] Step 5:

[0811] User: Navigate through the site to select the product for which they want to check warranty and aftercare information.

[0812] Step 6:

[0813] Terminal: Sends the selected product information as a request to the server. At the same time, sends the user's facial expressions and voice to the emotion engine in real time.

[0814] Step 7:

[0815] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[0816] 2. Providing warranty information

[0817] Step 8:

[0818] Server: Extracts warranty information for the relevant product from the database and adjusts the information based on emotion data.

[0819] Step 9:

[0820] Server: Adjusts the extracted warranty information and returns it to the user's device.

[0821] Step 10:

[0822] Terminal: Display the returned warranty information on the user's screen.

[0823] 3. Failure rate and repair cost prediction

[0824] Step 11:

[0825] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0826] Step 12:

[0827] Server: Personalizes prediction results and stores them in a database for each user.

[0828] 4. Aftercare service advice

[0829] Step 13:

[0830] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0831] Step 14:

[0832] Server: Runs an algorithm that integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[0833] Step 15:

[0834] Server: Sends the generated aftercare service recommendation results to the user device.

[0835] Step 16:

[0836] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[0837] Step 17:

[0838] User: Check the details of the recommended aftercare service and sign up if necessary.

[0839] Example 2

[0840] 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."

[0841] Conventional systems for providing warranty and after-care information did not take into account the user's emotional state. This placed a heavy psychological burden on users, resulting in lower customer satisfaction. Furthermore, the accuracy of predictions based on purchase history and failure information was insufficient, resulting in problems with the after-care services provided not meeting the user's actual needs.

[0842] 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.

[0843] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing the collected purchase data and failure information and predicting product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for acquiring user emotional data and customizing the warranty information and after-care information based on the data; means for authenticating the user's login information and acquiring purchase history data from the EC platform; and means for storing the acquired purchase history data in a database, and, when the user selects a specific product, extracting the warranty information for that product from the database and adjusting and displaying it based on the emotional data. This makes it possible to provide warranty information and after-care information that takes the user's emotional state into consideration, thereby reducing the user's psychological burden and improving customer satisfaction.

[0844] A "generative AI model" is an artificial intelligence algorithm that is trained to make predictions or classifications based on specific input data.

[0845] A "custom action" is a unique process or operation that the system automatically performs in response to specific user actions or data input.

[0846] "User purchasing data" refers to the history of products purchased by a user on an online shopping site and information related to such purchases.

[0847] "Warranty Information" means information regarding the product warranty provided with the purchased product.

[0848] "Aftercare information" refers to information regarding support and services provided after purchasing a product.

[0849] "Failure information" refers to the product's failure history and data related to the failure.

[0850] "Emotional data" refers to information that indicates the emotional state of a user, such as information obtained from facial expressions or voice.

[0851] An "emotion engine" is software or a system for analyzing a user's emotional data and identifying the user's emotional state.

[0852] An "EC platform" is an e-commerce platform that allows you to sell and purchase products online.

[0853] An "authentication server" is a server that verifies a user's login information and performs authentication.

[0854] A "database" is a system that systematically organizes and stores information so that it can be searched and used as needed.

[0855] This invention relates to a system that utilizes generative AI models and custom actions to provide warranty and aftercare information based on user purchase data. This allows warranty and aftercare information to be customized based on user emotional data, thereby increasing user satisfaction and reducing stress.

[0856] The system utilizes the following major hardware and software components:

[0857] Server: A central computer system for processing and storing data, including the e-commerce platform API, authentication server, and emotion engine.

[0858] Terminal: A device used by a user (e.g., smartphone, PC) that displays the user interface and collects data using a camera and microphone.

[0859] Database: A system for storing acquired purchase history data and emotional data.

[0860] Emotion engine: Software that analyzes emotional data from a user's facial expressions and voice to identify their emotional state.

[0861] System Overview

[0862] Acquiring purchase data

[0863] User: Visits an online shopping site and logs in using their account information.

[0864] On your device: Send your login information to the authentication server.

[0865] Server: After successful authentication, the EC platform API is called based on the user ID, the purchase history is retrieved, and the history is saved in the database.

[0866] Acquiring emotion data

[0867] User: Provides real-time facial and audio feedback when checking warranty and aftercare information.

[0868] Device: Sends real-time data acquired by the camera and microphone to the emotion engine.

[0869] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[0870] Providing warranty information

[0871] User: Select the product on the device for which they want to check warranty information.

[0872] Terminal: Sends the selected product information as a request to the server.

[0873] Server: Extracts the warranty information for the relevant product from the database, customizes the warranty information based on the emotion data, and sends it to the terminal.

[0874] Device: Display customized warranty information to the user.

[0875] Failure rate and repair cost prediction

[0876] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[0877] Server: Personalizes the prediction results and stores them in a database.

[0878] Aftercare service advice

[0879] User: Click the "Aftercare Recommendations" button to see the recommendations.

[0880] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[0881] Server: Sends the recommendation results to the user's device.

[0882] Device: Notify the user of the recommendation and provide more information.

[0883] User: Check the details of the recommended aftercare service and sign up if necessary.

[0884] Specific examples

[0885] Example 1: Acquiring purchase data and utilizing sentiment data

[0886] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[0887] 2. Device: After logging in, it sends a request to the EC platform API and transmits the purchase history of the "smart band" to the server.

[0888] 3. Server: Stores purchase data in a database and launches an emotion engine to obtain the user's emotional state in real time.

[0889] 4. User: If you want to check the warranty information on your device, select "Smart Band."

[0890] 5. Terminal: Sends the selection information to the server, which extracts the product information from the database.

[0891] 6. Server: Adjusts the guarantee information based on the emotion data and returns it to the device.

[0892] 7. Device: Display the adjusted warranty information on the user's screen.

[0893] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[0894] 1. Server: Collects purchase data and failure information from each e-commerce platform and inputs it into the generative AI model.

[0895] 2. Server: Predict the failure rate and repair costs of a "smart band."

[0896] 3. Server: Reflects the user's emotional data and evaluates the need for aftercare.

[0897] 4. User: Click the "Aftercare Recommendations" button to see the recommendations based on the emotional data.

[0898] 5. On the device: Notify the user of the recommended results and display detailed information.

[0899] 6. User: Check the details of the recommended aftercare service and sign up if necessary.

[0900] Prompt Sentence Examples

[0901] "Please explain in detail the program that provides warranty information to users who purchase smart bands online based on their purchase history and real-time sentiment data."

[0902] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0903] Step 1:

[0904] A user accesses an online shopping site and logs in by entering their account information (user ID and password). This results in the acquisition of login information (input: user login information, output: transmission of login request).

[0905] Step 2:

[0906] The terminal sends login information to the authentication server (input: user login information, output: sent authentication request). The authentication server compares the received information with a database, and if the user is authenticated, issues an authentication token (input: authentication request, output: authentication token).

[0907] Step 3:

[0908] The terminal calls the EC platform API using the authentication token and sends a request to acquire the user's purchase history (input: authentication token, output: transmission of purchase history request).

[0909] The server saves the purchase history obtained from the EC platform in a database (input: purchase history data, output: saving to database).

[0910] Step 4:

[0911] When the user checks warranty information or aftercare information, real-time facial expressions and voice are provided (input: user's facial expressions and voice data, output: collection of emotion data).

[0912] The device sends data acquired by the user's camera and microphone to the emotion engine (input: facial expression and voice data, output: sent to the emotion engine).

[0913] Step 5:

[0914] The server's emotion engine analyzes the user's emotions and generates emotion data (input: facial expression and voice data, output: emotion data). Machine learning models and voice analysis algorithms are used for the analysis.

[0915] Step 6:

[0916] When a user selects a specific product and wants to check its warranty information, he or she selects the product on the terminal (input: product selection information, output: request sent to server).

[0917] The terminal sends information about the selected product to the server (input: product ID, output: sending purchase history).

[0918] Step 7:

[0919] The server extracts the warranty information of the relevant product from the database (input: product ID, output: extracted warranty information). The extracted warranty information is adjusted based on the emotion data (input: warranty information, emotion data / output: adjusted warranty information).

[0920] The server sends the adjusted warranty information to the terminal (input: adjusted warranty information, output: transmission to terminal).

[0921] Step 8:

[0922] The terminal displays the adjusted warranty information on the user's screen (input: adjusted warranty information, output: display on user's screen).

[0923] Step 9:

[0924] The server inputs purchasing data and failure information collected from all e-commerce platforms into a generative AI model to predict product failure rates and repair costs (input: purchasing data, failure information; output: predicted failure rates and repair costs).

[0925] Step 10:

[0926] The server personalizes the prediction results and stores them in a database for each user (input: prediction results, output: storage of prediction results).

[0927] Step 11:

[0928] The user clicks the "Recommend Aftercare" button to see the recommendation results (Input: User click information, Output: Submit recommendation request).

[0929] The server integrates the purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services (input: purchase history, prediction data, emotion data; output: aftercare recommendation results).

[0930] Step 12:

[0931] The server sends the recommendation results to the user terminal (input: recommendation results, output: transmission to user terminal).

[0932] The terminal notifies the user of the recommended results and displays detailed information (input: recommended results, output: notification to user, display of detailed information).

[0933] Step 13:

[0934] The user checks the details of the recommended aftercare service and completes the subscription procedure if necessary (input: recommendation result, output: subscription procedure).

[0935] (Application example 2)

[0936] 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."

[0937] Conventional systems for providing warranty and after-care information provide uniform information regardless of the user's emotions, which has the problem of not sufficiently improving user satisfaction or reducing stress.In addition, after-care service proposals based on product failure rates and repair cost predictions are insufficient, making it difficult to provide advice appropriate to each user's individual situation.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0939] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; and means for acquiring user emotion data, recognizing emotions using an emotion engine, and personalizing warranty information and after-care information based on the emotion data. This makes it possible to provide personalized warranty information and after-care information that reflects the user's emotions, thereby achieving user satisfaction and stress reduction.

[0940] A "generative AI model" is an artificial intelligence model that analyzes user purchase data and failure information and provides warranty and after-care information.

[0941] A "custom action" is a set of actions that executes personalized warranty information or aftercare services for a specific user based on a generative AI model.

[0942] "Purchase Data" refers to historical information about products purchased by a user on e-commerce platforms and other online shopping sites.

[0943] "Failure information" refers to information such as the failure history and repair history of each product, and failure rate data provided by the manufacturer.

[0944] "Failure rate" is an indicator of the probability that a particular product will fail within a certain period of time.

[0945] "Repair costs" are the costs required to repair a broken product.

[0946] "Aftercare services" are services such as repairs, maintenance, and warranty extensions provided after a product is purchased.

[0947] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, voice, and other physiological data.

[0948] The "emotion engine" is an engine that analyzes the user's emotional data and recognizes their emotional state.

[0949] "Personalization" means customizing information and services to suit the individual preferences and feelings of each user.

[0950] An "EC platform" is an online system for conducting electronic commerce, where users can search for and purchase products.

[0951] The present invention is a system that utilizes generative AI models and custom actions to provide warranty and after-care information based on user purchase data. By combining this system with an emotion engine, the system provides personalized services that take user emotions into account. Below, we will explain in detail the various functions of the system and its implementation.

[0952] Hardware and Software Use

[0953] This system is realized using the following hardware and software.

[0954] Smartphone camera and microphone: Used to capture the user's facial expressions and voice.

[0955] Device: A device used by a user, such as a smartphone or tablet.

[0956] Server: Stores user credentials, purchase history data, sentiment data, and runs generative AI models.

[0957] Emotional Engine: Analyzes user emotional data using a virtual module called "Emotional Analysis."

[0958] Generative AI model: A virtual module called "AIPredictor" is used to provide warranty and aftercare information.

[0959] Acquiring purchase and sentiment data

[0960] A user logs in to an online shopping site and enters their account information into the device. The device sends the login information to the server, which then authenticates them. If authentication is successful, the server retrieves the user's purchase history data from the e-commerce platform via API and stores it in a database.

[0961] Next, when the user selects a product for which they wish to check warranty or after-sales information, the device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine, which then analyzes the user's emotions in real time and generates emotion data.

[0962] Providing warranty and aftercare information

[0963] When the device selects a specific product, the server retrieves the product's warranty information from the database. The warranty information is then analyzed by a generative AI model and personalized based on emotional data from the emotion engine. That is, if the user is stressed, a message that provides reassurance is added; if the user is satisfied, a message that emphasizes further comfort is added. The adjusted warranty information is then sent back to the device and displayed on the user's screen.

[0964] Prediction of failure rates and repair costs, and recommendations for aftercare services

[0965] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The prediction results are then analyzed along with emotional data to recommend optimal after-sales services to users.

[0966] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can check the details of the recommended aftercare service and, if necessary, complete the subscription procedure.

[0967] Examples of specific examples and prompts

[0968] For example, if a user is watching video content on a smartphone app and the emotion engine detects a stressed state, a personalized message such as "This product's warranty is very reassuring" will be displayed when providing warranty information.

[0969] An example of a prompt for a generative AI model is:

[0970] "A user is concerned about the possibility of their recently purchased smartphone breaking down. Please predict the failure rate and repair costs based on the selected product ID and the user's purchase history data."

[0971] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0972] Step 1:

[0973] A user logs in to an online shopping site and enters their account information. The device sends this login information to the server, which then requests authentication from the authentication server. If authentication is successful, the server calls the EC platform API based on the user ID and obtains the user's purchase history data. The obtained purchase history data is stored in a database.

[0974] Input: User login information

[0975] Output: User purchase history data (stored in database)

[0976] Step 2:

[0977] The user selects the product for which they want to check warranty and after-sales information. The device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine. The emotion engine analyzes the user's emotions in real time and generates emotion data.

[0978] Input: User's facial expression data, voice data

[0979] Output: Parsed emotion data

[0980] Step 3:

[0981] When a device selects a specific product, it sends that information as a request to the server. The server extracts the product's warranty information from the database and analyzes it using a generative AI model. A personalized message based on emotional data is added to the analyzed warranty information, generating an adjusted warranty.

[0982] Input: Product selection information, emotion data

[0983] Output: Adjusted warranty information

[0984] Step 4:

[0985] The server returns the adjusted warranty information to the terminal, which displays it on the user's screen. The user then checks the displayed warranty information.

[0986] Input: Adjusted warranty information

[0987] Output: What is displayed to the user

[0988] Step 5:

[0989] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The predicted failure rates and repair costs are then analyzed along with emotional data to recommend optimal after-sales services to users.

[0990] Input: Purchase data, failure information

[0991] Output: Failure rate prediction data, repair cost prediction data

[0992] Step 6:

[0993] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can then check the details of the recommended aftercare service and, if necessary, apply for it.

[0994] Input: purchase history, failure prediction data, emotion data

[0995] Output: Display of aftercare service recommendation results and detailed information

[0996] 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.

[0997] 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.

[0998] 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.

[0999] [Third embodiment]

[1000] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1001] 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.

[1002] 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).

[1003] 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.

[1004] 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.

[1005] 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).

[1006] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1007] 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.

[1008] 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.

[1009] 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.

[1010] 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.

[1011] 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."

[1012] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and provides users with after-care services based on subsequent failure rates and repair costs. This system is characterized by the use of generative AI models and custom actions to quickly provide users with personalized information.

[1013] Explanation of program processing

[1014] 1. Acquiring purchase data

[1015] User: Logs into an online shopping site and enters their account information.

[1016] Terminal: Login information is sent to the authentication server and authenticated.

[1017] Server: After successful authentication, retrieve the purchase history from the EC platform based on the user ID.

[1018] Server: Store the acquired purchase history data in a database.

[1019] 2. Providing warranty information

[1020] User: Select the product for which you want to view warranty information.

[1021] Terminal: Sends the selected product information as a request to the server.

[1022] Server: Extracts the warranty information for the relevant product from the database.

[1023] Server: Returns the extracted warranty information to the device.

[1024] Device: Display the received warranty information on the screen.

[1025] 3. Failure rate and repair cost prediction

[1026] Server: Inputs purchase data and failure information collected from all e-commerce platforms into the generative AI model.

[1027] Server: Uses generative AI models to predict failure rates and repair costs for target products.

[1028] Server: Personalizes prediction results and stores them in a database for each user.

[1029] 4. Aftercare service advice

[1030] User: Clicks the Aftercare Recommendations button.

[1031] Server: Integrates purchase history and failure prediction data to assess the need for aftercare services.

[1032] Server: Sends aftercare recommendation results to the device.

[1033] On your device: Notify the user of the recommendation and display detailed information about it.

[1034] User: Review the details of the recommended aftercare service and take any necessary steps.

[1035] Specific examples

[1036] Example 1: Retrieving purchase data and displaying warranty information

[1037] 1. User: Purchases a home appliance "refrigerator" online and logs in to his / her account.

[1038] 2. Terminal: After logging in, the purchase history of "refrigerator" is sent from the e-commerce platform to the server.

[1039] 3. Server: Stores the purchase data in the database. At the same time, retrieves the refrigerator warranty information from the e-commerce platform and stores it in the database.

[1040] 4. User: If you want to check the warranty information, select "Refrigerator" on your device.

[1041] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "refrigerator" from the database.

[1042] 6. Terminal: Display the extracted warranty information on the user's screen.

[1043] Example 2: Predicting failure rates and repair costs and recommending aftercare

[1044] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of "refrigerators."

[1045] 2. Server: Based on the prediction results, evaluate the need for aftercare services for the user and store the recommendation results in the database.

[1046] 3. User: Click the "Aftercare Recommendations" button to view details of the recommended aftercare services.

[1047] 4. On the device: Notify the user of the recommended results and display details.

[1048] 5. User: Complete the recommended aftercare service enrollment process.

[1049] In this way, the system of the present invention centrally manages warranty and after-sales information for products purchased online, reducing stress for users when a product breaks down. It also improves customer satisfaction by recommending personalized after-sales services.

[1050] The processing flow will be explained below.

[1051] Step 1:

[1052] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[1053] Step 2:

[1054] On the device: The login information entered by the user is sent to the authentication server.

[1055] Step 3:

[1056] Server: The authentication server verifies the user ID and password, and if authentication is successful, calls the EC platform API based on the user ID.

[1057] Step 4:

[1058] Server: Obtains user purchase history via the EC platform API and stores that data in the system database.

[1059] Step 5:

[1060] User: If they want to view warranty information for a specific product they purchased, they select that product in the system.

[1061] Step 6:

[1062] Terminal: Sends the selected product information as a request to the server.

[1063] Step 7:

[1064] Server: Extracts warranty information for the requested product from the database.

[1065] Step 8:

[1066] Server: Returns the extracted warranty information to the user's device.

[1067] Step 9:

[1068] Terminal: Display the returned warranty information on the user's screen.

[1069] Step 10:

[1070] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1071] Step 11:

[1072] Server: The generated failure rate and repair cost prediction results are personalized and stored in a database for each user.

[1073] Step 12:

[1074] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1075] Step 13:

[1076] Server: Runs an algorithm that combines purchase history and failure prediction data to assess the need for aftercare services.

[1077] Step 14:

[1078] Server: Sends the generated aftercare service recommendation results to the user device.

[1079] Step 15:

[1080] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[1081] Step 16:

[1082] User: Check the details of the recommended aftercare service and sign up if necessary.

[1083] Example 1

[1084] 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."

[1085] In today's online shopping environment, users must purchase a variety of home appliances and electronic devices and individually manage the associated warranty and after-care information, which is extremely time-consuming. Furthermore, insufficient information on product failure rates and repair costs after purchase makes it difficult for users to select the appropriate after-care service. Furthermore, the lack of personalized information reduces user convenience. Therefore, to solve these issues, a system is needed that can centrally manage purchase data and failure information and provide users with prompt and accurate warranty information and after-care services.

[1086] 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.

[1087] In this invention, the server includes: means for providing warranty and after-care information based on user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for logging in using the user's account information and acquiring the purchase history after authentication; means for saving the acquired purchase history data in a database; means for extracting warranty information for products selected by the user from the database and displaying it on the user's terminal; means for personalizing the prediction results and saving them in the database for each user; and means for evaluating the need for after-care services and displaying the results on the user's terminal. This allows users to centrally manage warranty and after-care information for home appliances and electronic devices purchased online, providing prompt and accurate information. Furthermore, personalized after-care service recommendations based on predicted failure rates and repair costs significantly improve user convenience.

[1088] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to make predictions and analyze data based on collected data.

[1089] A "custom action" is a special program or function designed to perform a specific task or operation.

[1090] "User purchasing data" refers to data including information about products purchased by users on online shopping platforms and their purchase history.

[1091] "Warranty Information" refers to information that describes the conditions and scope of repairs or replacements within a certain period from the date of purchase of the product.

[1092] "Aftercare information" refers to information regarding services such as repairs, maintenance, and support provided after the purchase of a product.

[1093] "Failure information" refers to data such as troubles and repair history when a product stops working properly.

[1094] "Failure rate" refers to the probability that a product will fail within a specific period of time.

[1095] "Repair costs" refers to the costs required to repair a product when it breaks down.

[1096] "Personalization" refers to the customization of information and services based on the characteristics and history of each individual user.

[1097] "Authentication token" refers to a security token used when exchanging user authentication information.

[1098] "Online platform" refers to a service provision infrastructure available on the Internet, including websites and applications.

[1099] A "database" refers to a dedicated system for efficiently storing, searching, and managing large amounts of data.

[1100] "User terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[1101] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and quickly provides personalized information to users. This system uses generative AI models and custom actions to recommend the most suitable after-care services to users.

[1102] First, a user logs in to an online shopping site and enters their account information. The login information is sent from the terminal to the authentication server, which receives an authentication token. After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID and stores this purchase history data in a database.

[1103] Next, when the user selects the product for which they wish to check warranty information, the terminal sends a request to the server with the information about the selected product. The server extracts the warranty information for that product from the database and returns it to the terminal. The terminal then displays the received warranty information on its screen.

[1104] The server then inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The prediction results are personalized and stored in a database for each user.

[1105] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for aftercare service. The evaluation results are sent to the device, which notifies the user and displays detailed information. The user can then check the details of the recommended aftercare service and take the necessary steps.

[1106] This system uses various hardware and software. The server uses a high-performance database system (e.g., MySQL or PostgreSQL) and a machine learning framework such as PyTorch or TensorFlow to run the AI ​​model. The terminal is a device operated by the user, such as a computer or smartphone, which communicates with the server via a browser or dedicated application.

[1107] As a concrete example, a user purchases a home appliance "refrigerator" online and logs in to their account. After logging in, the e-commerce platform sends the purchase history for "refrigerator" to the server. The server saves the purchase data in a database and also retrieves and stores warranty information. If the user wants to check the warranty information, they select "refrigerator" on their device, and the server extracts and displays the warranty information. The generative AI model also predicts the failure rate and repair costs of the "refrigerator," and after-care services are recommended. The user clicks the "Recommend After-care" button, checks the recommended after-care services, and proceeds with the procedure.

[1108] An example of a prompt to input to a generative AI model is as follows:

[1109] Using purchase data and failure information as input, predict the failure rate and repair costs for the target product.

[1110] In this way, the system of the present invention can centrally manage warranty and after-sales information for products purchased by users through online shopping, enabling the provision of fast and accurate information. Furthermore, personalized after-sales service recommendations can significantly improve user convenience.

[1111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1112] Step 1:

[1113] A user logs into an online shopping site and enters their account information, such as an email address and password, which is then processed on the device.

[1114] Input: User's email address and password

[1115] Output: Authentication request data

[1116] Step 2:

[1117] The terminal sends login information to the authentication server and receives an authentication token. The authentication server verifies the login information and issues an authentication token if it is valid.

[1118] Input: Authentication request data

[1119] Output: Authentication token

[1120] Step 3:

[1121] After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID. The server then uses the authentication token to retrieve the purchase history data from the EC platform via API.

[1122] Input: Authentication token and user ID

[1123] Output: Purchase history data

[1124] Step 4:

[1125] The server saves the acquired purchase history data in the database. The server formats the purchase history data into an appropriate format and saves it in the database using the INSERT statement.

[1126] Input: Purchase history data

[1127] Output: Purchase history stored in the database

[1128] Step 5:

[1129] The user selects the product for which they wish to check warranty information. After logging in, the user clicks on the product in question from the purchase history list on their My Page.

[1130] Input: User input (product selection)

[1131] Output: Product ID

[1132] Step 6:

[1133] The terminal sends the information about the selected product to the server as a request. The terminal uses AJAX to send a request including the product ID to the server.

[1134] Input: Product ID

[1135] Output: Product information request

[1136] Step 7:

[1137] The server extracts the warranty information for the relevant product from the database. The server retrieves the warranty information from the database using a SELECT statement based on the product ID.

[1138] Input: Product information request (product ID)

[1139] Output: Warranty information data

[1140] Step 8:

[1141] The server returns the extracted warranty information to the terminal, converts it into JSON format, and sends it to the terminal as an HTTP response.

[1142] Input: Warranty information data

[1143] Output: Warranty information response

[1144] Step 9:

[1145] The terminal displays the received warranty information on the screen. The terminal parses the received JSON data and dynamically generates and displays the warranty information in HTML.

[1146] Input: Warranty information response

[1147] Output: Warranty information displayed on screen

[1148] Step 10:

[1149] The server inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The server then formats the collected data into an appropriate format and inputs it into the generative AI model to make predictions.

[1150] Input: Purchase data and failure information

[1151] Output: Failure rate and repair cost prediction results

[1152] Step 11:

[1153] The server personalizes the prediction results and stores them in a database for each user. The server associates the prediction results with the user ID and inserts or updates them into the database.

[1154] Input: Failure rate and repair cost prediction results

[1155] Output: Personalized prediction data

[1156] Step 12:

[1157] The user clicks the "Aftercare Recommendations" button. The user clicks a button on the interface to trigger an event.

[1158] Input: User input (button click)

[1159] Output: Aftercare recommendation request

[1160] Step 13:

[1161] The server integrates the purchase history and failure prediction data to evaluate the need for after-sales service, analyzes the integrated data, and generates after-sales service recommendations based on an algorithm.

[1162] Input: Aftercare recommendation requests, purchase history, failure prediction data

[1163] Output: Aftercare recommendation results

[1164] Step 14:

[1165] The server sends the aftercare recommendation results to the device, converts the recommendation results into JSON format, and sends it to the device as an HTTP response.

[1166] Input: Aftercare recommendation results

[1167] Output: Aftercare recommended response

[1168] Step 15:

[1169] The device will notify the user of the recommended results and display detailed information. The device will parse the received JSON data and dynamically generate and display the recommended results in HTML.

[1170] Input: Aftercare recommendation response

[1171] Output: Aftercare recommendation results displayed on screen

[1172] Step 16:

[1173] The user checks the details of the recommended aftercare service and takes the necessary steps. The user clicks on the link for the recommended aftercare service to go to the details page and proceed with the necessary steps.

[1174] Input: Display aftercare recommendation results

[1175] Output: Aftercare service application procedure

[1176] (Application example 1)

[1177] 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."

[1178] Currently, it is difficult for users to individually manage warranty and after-sales care information for home appliances and electronic devices purchased online, which increases the amount of work required. In addition, since there is no prediction of failure rates or repair costs after purchase, users often miss opportunities to receive appropriate after-sales care services. This results in issues such as lower user satisfaction and lower customer retention rates.

[1179] 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.

[1180] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to users based on the predicted failure rates and repair costs; means for automatically acquiring purchase history from an e-commerce platform and centrally managing warranty information; and means for transmitting personalized after-care service recommendations based on the predicted data to a user terminal. This allows users to centrally manage warranty information and after-care information for purchased products and quickly receive optimal after-care services based on the predicted failure rates and repair costs.

[1181] A "generative AI model" is a type of artificial intelligence that uses purchase data and failure information to predict product failure rates and repair costs.

[1182] A "custom action" is a program that automatically performs specific actions or processes according to the user's needs.

[1183] "Purchase Data" refers to information about products purchased by a User through online shopping.

[1184] "Warranty information" refers to information regarding the warranty period and warranty details provided at the time of product purchase.

[1185] "Aftercare information" refers to information about services such as maintenance, repair, and replacement after purchasing a product.

[1186] "Failure information" refers to data regarding the circumstances and causes of a product failure.

[1187] "Failure rate" is an indicator that indicates the rate at which a certain number of products fail within a specific period of time.

[1188] "Repair costs" refers to the costs required to repair a broken product.

[1189] "Aftercare services" refers to support and maintenance services provided for products after purchase.

[1190] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[1191] "Personalized services" refer to services that are customized based on the characteristics and needs of individual users.

[1192] "Server" refers to a high-performance computer system that stores, manages, and processes data.

[1193] This invention is a system that uses generative AI models and custom actions to provide warranty and after-care information based on user purchase data. To implement this system, a program based on the following steps is required.

[1194] Hardware and software used:

[1195] Hardware:

[1196] server

[1197] User's device (smartphone, smart glasses, head-mounted display)

[1198] software:

[1199] Backend: Python, Flask

[1200] Frontend: React Native

[1201] Database: MongoDB

[1202] AI model: TensorFlow

[1203] Overview of what the system does:

[1204] Retrieving purchase data:

[1205] When a user logs in to the e-commerce platform, the terminal sends the login information to the server. The server obtains the authentication information and, after successful login, retrieves the user's purchase history data from the e-commerce platform. This data is stored in a MongoDB database.

[1206] Warranty information provided:

[1207] When a user selects a specific product in the application, the device requests information about that product from the server, which then retrieves the corresponding warranty information from the MongoDB database and returns it to the device, which then displays the warranty information on the user's screen.

[1208] Failure rate and repair cost forecast:

[1209] The server inputs the collected purchase data and failure information into a generative AI model built with TensorFlow, which predicts product failure rates and repair costs and stores the results in a personalized database.

[1210] Aftercare service advice:

[1211] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for the most appropriate aftercare service. The generated recommendation results are sent to the user's device, which notifies the user and displays detailed information. The user can then proceed with the subscription process for the recommended aftercare service.

[1212] Examples:

[1213] For example, when a user logs into the app on their smartphone, warranty information for a recently purchased refrigerator is automatically displayed. The aftercare screen displays information such as "Predicted failure rate: Low (less than 5%)" and "Predicted repair cost: Less than 5,000 yen." If necessary, the user can click the "Apply for aftercare service" button to proceed with the process.

[1214] Example prompt sentence:

[1215] I'd like to check the warranty information for my refrigerator. I'm also considering after-sales service. Could you please tell me what the warranty covers, the failure rate, and repair costs? Also, could you recommend any after-sales service?

[1216] This allows the system of the present invention to centrally manage and provide warranty and after-care information for products purchased online by users, enabling them to quickly receive optimal after-care service based on predicted failure rates and repair costs.

[1217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1218] Step 1:

[1219] A user logs in to an e-commerce platform. The terminal sends the user's login information to the server. The server authenticates the login information and obtains the user's ID if successful.

[1220] Input: User login information

[1221] Output: User ID

[1222] Step 2:

[1223] The server retrieves purchase history data from the e-commerce platform based on the user's ID, and stores the data in a MongoDB database.

[1224] Input: User ID

[1225] Output: Purchase history data

[1226] Step 3:

[1227] When a user selects a specific product, the device sends a request to the server with information about the selected product. The server extracts the product's warranty information from the MongoDB database and returns it to the device. The device then displays the warranty information on its screen.

[1228] Input: User selected product information

[1229] Output: Warranty information for the product

[1230] Step 4:

[1231] The server inputs the collected purchase data and failure information into a TensorFlow generative AI model, which then predicts product failure rates and repair costs and stores the results in a personalized database.

[1232] Input: Purchase data and failure information

[1233] Output: Predicted failure rate and repair costs

[1234] Step 5:

[1235] When a user clicks the "Aftercare Recommendation" button, the device sends the information to the server. The server then combines the purchase history with the predicted data on failure rates and repair costs to evaluate the need for aftercare services. The generated recommendation results are sent to the user's device, which then notifies the user.

[1236] Input: Purchase history and predicted failure rate and repair cost data

[1237] Output: Aftercare service recommendation results

[1238] Step 6:

[1239] The user checks the details of the recommended aftercare service and completes the necessary procedures. The terminal sends the procedure completion information to the server, and the server updates the information in the database.

[1240] Input: User's aftercare service procedure information

[1241] Output: Updated database information

[1242] The above is a flow of specific processing steps for implementing this invention, with inputs and outputs clearly defined for each step. This processing flow allows users to centrally manage warranty and after-sales care information for purchased products, enabling them to quickly receive appropriate after-sales care service.

[1243] 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.

[1244] This invention utilizes generative AI models and custom actions to provide a system that provides warranty and after-care information based on user purchase data, and combines it with an emotion engine that recognizes user emotions to provide more personalized services. This system improves user satisfaction and reduces stress by providing warranty and after-care information and recommending after-care services based on the user's emotional data obtained by the emotion engine. It also includes a means for analyzing purchase data and failure information collected from e-commerce platforms to predict product failure rates and repair costs.

[1245] Explanation of program processing

[1246] 1. Acquiring purchase data

[1247] User: Logs into an online shopping site and enters their account information.

[1248] Terminal: Login information is sent to the authentication server and authenticated.

[1249] Server: After successful authentication, the EC platform API is called based on the user ID to retrieve the purchase history.

[1250] Server: Store the acquired purchase history data in a database.

[1251] 2. Acquiring Emotion Data

[1252] User: Provide real-time facial and voice data when checking warranty and aftercare information.

[1253] Device: Recognizes the user's facial expressions and voice and sends them to the emotion engine.

[1254] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[1255] 3. Providing warranty information

[1256] User: Select the product for which you want to view warranty information.

[1257] Terminal: Sends the selected product information as a request to the server.

[1258] Server: Extracts the warranty information for the relevant product from the database.

[1259] Server: Adjusts the extracted guarantee information based on the emotion data and returns it to the device.

[1260] Device: Display adjusted warranty information on the user's screen.

[1261] 4. Failure rate and repair cost prediction

[1262] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1263] Server: Personalizes prediction results and stores them in a database for each user.

[1264] 5. Aftercare service advice

[1265] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1266] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[1267] Server: Sends the recommendation results to the user's device.

[1268] Device: Notify the user of the recommendation and provide more information.

[1269] User: Check the details of the recommended aftercare service and sign up if necessary.

[1270] Specific examples

[1271] Example 1: Acquiring purchase data and utilizing sentiment data

[1272] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[1273] 2. Device: After logging in, the purchase history of the "smart band" is sent from the EC platform to the server.

[1274] 3. Server: Stores purchase data in a database and runs the emotion engine to obtain user emotion data.

[1275] 4. User: If you want to check the warranty information, select "Smart Band" on your device, and the emotion engine will analyze your emotion.

[1276] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "smart band" from the database.

[1277] 6. Server: Based on the analysis results of the emotion engine, adjust the guarantee information and send it back to the device.

[1278] 7. Device: Display the adjusted warranty information on the user's screen.

[1279] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[1280] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of the "smart band."

[1281] 2. Server: Based on the prediction results, it reflects the analysis results of the emotion engine and evaluates the need for aftercare services for the user.

[1282] 3. User: Click the "Aftercare Recommendations" button to see the recommendations based on your emotional data.

[1283] 4. On the device: Notify the user of the recommended results and display details.

[1284] 5. User: Check the details of the recommended aftercare service and sign up if necessary.

[1285] In this way, by combining an emotion engine, the present invention realizes the provision of warranty information and aftercare information that takes into account the user's emotional state, thereby reducing user stress and improving customer satisfaction.

[1286] The processing flow will be explained below.

[1287] Specific processing flow

[1288] 1. Acquiring purchase and sentiment data

[1289] Step 1:

[1290] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[1291] Step 2:

[1292] On the device: The login information entered by the user is sent to the authentication server.

[1293] Step 3:

[1294] Server: The authentication server verifies the user ID and password, and if authentication is successful, it calls the EC platform API based on the user ID to obtain the purchase history.

[1295] Step 4:

[1296] Server: Stores the acquired purchase history data in a database within the system.

[1297] Step 5:

[1298] User: Navigate through the site to select the product for which they want to check warranty and aftercare information.

[1299] Step 6:

[1300] Terminal: Sends the selected product information as a request to the server. At the same time, sends the user's facial expressions and voice to the emotion engine in real time.

[1301] Step 7:

[1302] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[1303] 2. Providing warranty information

[1304] Step 8:

[1305] Server: Extracts warranty information for the relevant product from the database and adjusts the information based on emotion data.

[1306] Step 9:

[1307] Server: Adjusts the extracted warranty information and returns it to the user's device.

[1308] Step 10:

[1309] Terminal: Display the returned warranty information on the user's screen.

[1310] 3. Failure rate and repair cost prediction

[1311] Step 11:

[1312] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1313] Step 12:

[1314] Server: Personalizes prediction results and stores them in a database for each user.

[1315] 4. Aftercare service advice

[1316] Step 13:

[1317] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1318] Step 14:

[1319] Server: Runs an algorithm that integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[1320] Step 15:

[1321] Server: Sends the generated aftercare service recommendation results to the user device.

[1322] Step 16:

[1323] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[1324] Step 17:

[1325] User: Check the details of the recommended aftercare service and sign up if necessary.

[1326] Example 2

[1327] 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."

[1328] Conventional systems for providing warranty and after-care information did not take into account the user's emotional state. This placed a heavy psychological burden on users, resulting in lower customer satisfaction. Furthermore, the accuracy of predictions based on purchase history and failure information was insufficient, resulting in problems with the after-care services provided not meeting the user's actual needs.

[1329] 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.

[1330] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing the collected purchase data and failure information and predicting product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for acquiring user emotional data and customizing the warranty information and after-care information based on the data; means for authenticating the user's login information and acquiring purchase history data from the EC platform; and means for storing the acquired purchase history data in a database, and, when the user selects a specific product, extracting the warranty information for that product from the database and adjusting and displaying it based on the emotional data. This makes it possible to provide warranty information and after-care information that takes the user's emotional state into consideration, thereby reducing the user's psychological burden and improving customer satisfaction.

[1331] A "generative AI model" is an artificial intelligence algorithm that is trained to make predictions or classifications based on specific input data.

[1332] A "custom action" is a unique process or operation that the system automatically performs in response to specific user actions or data input.

[1333] "User purchasing data" refers to the history of products purchased by a user on an online shopping site and information related to such purchases.

[1334] "Warranty Information" means information regarding the product warranty provided with the purchased product.

[1335] "Aftercare information" refers to information regarding support and services provided after purchasing a product.

[1336] "Failure information" refers to the product's failure history and data related to the failure.

[1337] "Emotional data" refers to information that indicates the emotional state of a user, such as information obtained from facial expressions or voice.

[1338] An "emotion engine" is software or a system for analyzing a user's emotional data and identifying the user's emotional state.

[1339] An "EC platform" is an e-commerce platform that allows you to sell and purchase products online.

[1340] An "authentication server" is a server that verifies a user's login information and performs authentication.

[1341] A "database" is a system that systematically organizes and stores information so that it can be searched and used as needed.

[1342] This invention relates to a system that utilizes generative AI models and custom actions to provide warranty and aftercare information based on user purchase data. This allows warranty and aftercare information to be customized based on user emotional data, thereby increasing user satisfaction and reducing stress.

[1343] The system utilizes the following major hardware and software components:

[1344] Server: A central computer system for processing and storing data, including the e-commerce platform API, authentication server, and emotion engine.

[1345] Terminal: A device used by a user (e.g., smartphone, PC) that displays the user interface and collects data using a camera and microphone.

[1346] Database: A system for storing acquired purchase history data and emotional data.

[1347] Emotion engine: Software that analyzes emotional data from a user's facial expressions and voice to identify their emotional state.

[1348] System Overview

[1349] Acquiring purchase data

[1350] User: Visits an online shopping site and logs in using their account information.

[1351] On your device: Send your login information to the authentication server.

[1352] Server: After successful authentication, the EC platform API is called based on the user ID, the purchase history is retrieved, and the history is saved in the database.

[1353] Acquiring emotion data

[1354] User: Provides real-time facial and audio feedback when checking warranty and aftercare information.

[1355] Device: Sends real-time data acquired by the camera and microphone to the emotion engine.

[1356] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[1357] Providing warranty information

[1358] User: Select the product on the device for which they want to check warranty information.

[1359] Terminal: Sends the selected product information as a request to the server.

[1360] Server: Extracts the warranty information for the relevant product from the database, customizes the warranty information based on the emotion data, and sends it to the terminal.

[1361] Device: Display customized warranty information to the user.

[1362] Failure rate and repair cost prediction

[1363] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1364] Server: Personalizes the prediction results and stores them in a database.

[1365] Aftercare service advice

[1366] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1367] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[1368] Server: Sends the recommendation results to the user's device.

[1369] Device: Notify the user of the recommendation and provide more information.

[1370] User: Check the details of the recommended aftercare service and sign up if necessary.

[1371] Specific examples

[1372] Example 1: Acquiring purchase data and utilizing sentiment data

[1373] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[1374] 2. Device: After logging in, it sends a request to the EC platform API and transmits the purchase history of the "smart band" to the server.

[1375] 3. Server: Stores purchase data in a database and launches an emotion engine to obtain the user's emotional state in real time.

[1376] 4. User: If you want to check the warranty information on your device, select "Smart Band."

[1377] 5. Terminal: Sends the selection information to the server, which extracts the product information from the database.

[1378] 6. Server: Adjusts the guarantee information based on the emotion data and returns it to the device.

[1379] 7. Device: Display the adjusted warranty information on the user's screen.

[1380] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[1381] 1. Server: Collects purchase data and failure information from each e-commerce platform and inputs it into the generative AI model.

[1382] 2. Server: Predict the failure rate and repair costs of a "smart band."

[1383] 3. Server: Reflects the user's emotional data and evaluates the need for aftercare.

[1384] 4. User: Click the "Aftercare Recommendations" button to see the recommendations based on the emotional data.

[1385] 5. On the device: Notify the user of the recommended results and display detailed information.

[1386] 6. User: Check the details of the recommended aftercare service and sign up if necessary.

[1387] Prompt Sentence Examples

[1388] "Please explain in detail the program that provides warranty information to users who purchase smart bands online based on their purchase history and real-time sentiment data."

[1389] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1390] Step 1:

[1391] A user accesses an online shopping site and logs in by entering their account information (user ID and password). This results in the acquisition of login information (input: user login information, output: transmission of login request).

[1392] Step 2:

[1393] The terminal sends login information to the authentication server (input: user login information, output: sent authentication request). The authentication server compares the received information with a database, and if the user is authenticated, issues an authentication token (input: authentication request, output: authentication token).

[1394] Step 3:

[1395] The terminal calls the EC platform API using the authentication token and sends a request to acquire the user's purchase history (input: authentication token, output: transmission of purchase history request).

[1396] The server saves the purchase history obtained from the EC platform in a database (input: purchase history data, output: saving to database).

[1397] Step 4:

[1398] When the user checks warranty information or aftercare information, real-time facial expressions and voice are provided (input: user's facial expressions and voice data, output: collection of emotion data).

[1399] The device sends data acquired by the user's camera and microphone to the emotion engine (input: facial expression and voice data, output: sent to the emotion engine).

[1400] Step 5:

[1401] The server's emotion engine analyzes the user's emotions and generates emotion data (input: facial expression and voice data, output: emotion data). Machine learning models and voice analysis algorithms are used for the analysis.

[1402] Step 6:

[1403] When a user selects a specific product and wants to check its warranty information, he or she selects the product on the terminal (input: product selection information, output: request sent to server).

[1404] The terminal sends information about the selected product to the server (input: product ID, output: sending purchase history).

[1405] Step 7:

[1406] The server extracts the warranty information of the relevant product from the database (input: product ID, output: extracted warranty information). The extracted warranty information is adjusted based on the emotion data (input: warranty information, emotion data / output: adjusted warranty information).

[1407] The server sends the adjusted warranty information to the terminal (input: adjusted warranty information, output: transmission to terminal).

[1408] Step 8:

[1409] The terminal displays the adjusted warranty information on the user's screen (input: adjusted warranty information, output: display on user's screen).

[1410] Step 9:

[1411] The server inputs purchasing data and failure information collected from all e-commerce platforms into a generative AI model to predict product failure rates and repair costs (input: purchasing data, failure information; output: predicted failure rates and repair costs).

[1412] Step 10:

[1413] The server personalizes the prediction results and stores them in a database for each user (input: prediction results, output: storage of prediction results).

[1414] Step 11:

[1415] The user clicks the "Recommend Aftercare" button to see the recommendation results (Input: User click information, Output: Submit recommendation request).

[1416] The server integrates the purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services (input: purchase history, prediction data, emotion data; output: aftercare recommendation results).

[1417] Step 12:

[1418] The server sends the recommendation results to the user terminal (input: recommendation results, output: transmission to user terminal).

[1419] The terminal notifies the user of the recommended results and displays detailed information (input: recommended results, output: notification to user, display of detailed information).

[1420] Step 13:

[1421] The user checks the details of the recommended aftercare service and completes the subscription procedure if necessary (input: recommendation result, output: subscription procedure).

[1422] (Application example 2)

[1423] 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."

[1424] Conventional systems for providing warranty and after-care information provide uniform information regardless of the user's emotions, which has the problem of not sufficiently improving user satisfaction or reducing stress.In addition, after-care service proposals based on product failure rates and repair cost predictions are insufficient, making it difficult to provide advice appropriate to each user's individual situation.

[1425] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1426] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; and means for acquiring user emotion data, recognizing emotions using an emotion engine, and personalizing warranty information and after-care information based on the emotion data. This makes it possible to provide personalized warranty information and after-care information that reflects the user's emotions, thereby achieving user satisfaction and stress reduction.

[1427] A "generative AI model" is an artificial intelligence model that analyzes user purchase data and failure information and provides warranty and after-care information.

[1428] A "custom action" is a set of actions that executes personalized warranty information or aftercare services for a specific user based on a generative AI model.

[1429] "Purchase Data" refers to historical information about products purchased by a user on e-commerce platforms and other online shopping sites.

[1430] "Failure information" refers to information such as the failure history and repair history of each product, and failure rate data provided by the manufacturer.

[1431] "Failure rate" is an indicator of the probability that a particular product will fail within a certain period of time.

[1432] "Repair costs" are the costs required to repair a broken product.

[1433] "Aftercare services" are services such as repairs, maintenance, and warranty extensions provided after a product is purchased.

[1434] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, voice, and other physiological data.

[1435] The "emotion engine" is an engine that analyzes the user's emotional data and recognizes their emotional state.

[1436] "Personalization" means customizing information and services to suit the individual preferences and feelings of each user.

[1437] An "EC platform" is an online system for conducting electronic commerce, where users can search for and purchase products.

[1438] The present invention is a system that utilizes generative AI models and custom actions to provide warranty and after-care information based on user purchase data. By combining this system with an emotion engine, the system provides personalized services that take user emotions into account. Below, we will explain in detail the various functions of the system and its implementation.

[1439] Hardware and Software Use

[1440] This system is realized using the following hardware and software.

[1441] Smartphone camera and microphone: Used to capture the user's facial expressions and voice.

[1442] Device: A device used by a user, such as a smartphone or tablet.

[1443] Server: Stores user credentials, purchase history data, sentiment data, and runs generative AI models.

[1444] Emotional Engine: Analyzes user emotional data using a virtual module called "Emotional Analysis."

[1445] Generative AI model: A virtual module called "AIPredictor" is used to provide warranty and aftercare information.

[1446] Acquiring purchase and sentiment data

[1447] A user logs in to an online shopping site and enters their account information into the device. The device sends the login information to the server, which then authenticates them. If authentication is successful, the server retrieves the user's purchase history data from the e-commerce platform via API and stores it in a database.

[1448] Next, when the user selects a product for which they wish to check warranty or after-sales information, the device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine, which then analyzes the user's emotions in real time and generates emotion data.

[1449] Providing warranty and aftercare information

[1450] When the device selects a specific product, the server retrieves the product's warranty information from the database. The warranty information is then analyzed by a generative AI model and personalized based on emotional data from the emotion engine. That is, if the user is stressed, a message that provides reassurance is added; if the user is satisfied, a message that emphasizes further comfort is added. The adjusted warranty information is then sent back to the device and displayed on the user's screen.

[1451] Prediction of failure rates and repair costs, and recommendations for aftercare services

[1452] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The prediction results are then analyzed along with emotional data to recommend optimal after-sales services to users.

[1453] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can check the details of the recommended aftercare service and, if necessary, complete the subscription procedure.

[1454] Examples of specific examples and prompts

[1455] For example, if a user is watching video content on a smartphone app and the emotion engine detects a stressed state, a personalized message such as "This product's warranty is very reassuring" will be displayed when providing warranty information.

[1456] An example of a prompt for a generative AI model is:

[1457] "A user is concerned about the possibility of their recently purchased smartphone breaking down. Please predict the failure rate and repair costs based on the selected product ID and the user's purchase history data."

[1458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1459] Step 1:

[1460] A user logs in to an online shopping site and enters their account information. The device sends this login information to the server, which then requests authentication from the authentication server. If authentication is successful, the server calls the EC platform API based on the user ID and obtains the user's purchase history data. The obtained purchase history data is stored in a database.

[1461] Input: User login information

[1462] Output: User purchase history data (stored in database)

[1463] Step 2:

[1464] The user selects the product for which they want to check warranty and after-sales information. The device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine. The emotion engine analyzes the user's emotions in real time and generates emotion data.

[1465] Input: User's facial expression data, voice data

[1466] Output: Parsed emotion data

[1467] Step 3:

[1468] When a device selects a specific product, it sends that information as a request to the server. The server extracts the product's warranty information from the database and analyzes it using a generative AI model. A personalized message based on emotional data is added to the analyzed warranty information, generating an adjusted warranty.

[1469] Input: Product selection information, emotion data

[1470] Output: Adjusted warranty information

[1471] Step 4:

[1472] The server returns the adjusted warranty information to the terminal, which displays it on the user's screen. The user then checks the displayed warranty information.

[1473] Input: Adjusted warranty information

[1474] Output: What is displayed to the user

[1475] Step 5:

[1476] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The predicted failure rates and repair costs are then analyzed along with emotional data to recommend optimal after-sales services to users.

[1477] Input: Purchase data, failure information

[1478] Output: Failure rate prediction data, repair cost prediction data

[1479] Step 6:

[1480] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can then check the details of the recommended aftercare service and, if necessary, apply for it.

[1481] Input: purchase history, failure prediction data, emotion data

[1482] Output: Display of aftercare service recommendation results and detailed information

[1483] 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.

[1484] 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.

[1485] 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.

[1486] [Fourth embodiment]

[1487] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1488] 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.

[1489] 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).

[1490] 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.

[1491] 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.

[1492] 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).

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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."

[1500] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and provides users with after-care services based on subsequent failure rates and repair costs. This system is characterized by the use of generative AI models and custom actions to quickly provide users with personalized information.

[1501] Explanation of program processing

[1502] 1. Acquiring purchase data

[1503] User: Logs into an online shopping site and enters their account information.

[1504] Terminal: Login information is sent to the authentication server and authenticated.

[1505] Server: After successful authentication, retrieve the purchase history from the EC platform based on the user ID.

[1506] Server: Store the acquired purchase history data in a database.

[1507] 2. Providing warranty information

[1508] User: Select the product for which you want to view warranty information.

[1509] Terminal: Sends the selected product information as a request to the server.

[1510] Server: Extracts the warranty information for the relevant product from the database.

[1511] Server: Returns the extracted warranty information to the device.

[1512] Device: Display the received warranty information on the screen.

[1513] 3. Failure rate and repair cost prediction

[1514] Server: Inputs purchase data and failure information collected from all e-commerce platforms into the generative AI model.

[1515] Server: Uses generative AI models to predict failure rates and repair costs for target products.

[1516] Server: Personalizes prediction results and stores them in a database for each user.

[1517] 4. Aftercare service advice

[1518] User: Clicks the Aftercare Recommendations button.

[1519] Server: Integrates purchase history and failure prediction data to assess the need for aftercare services.

[1520] Server: Sends aftercare recommendation results to the device.

[1521] On your device: Notify the user of the recommendation and display detailed information about it.

[1522] User: Review the details of the recommended aftercare service and take any necessary steps.

[1523] Specific examples

[1524] Example 1: Retrieving purchase data and displaying warranty information

[1525] 1. User: Purchases a home appliance "refrigerator" online and logs in to his / her account.

[1526] 2. Terminal: After logging in, the purchase history of "refrigerator" is sent from the e-commerce platform to the server.

[1527] 3. Server: Stores the purchase data in the database. At the same time, retrieves the refrigerator warranty information from the e-commerce platform and stores it in the database.

[1528] 4. User: If you want to check the warranty information, select "Refrigerator" on your device.

[1529] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "refrigerator" from the database.

[1530] 6. Terminal: Display the extracted warranty information on the user's screen.

[1531] Example 2: Predicting failure rates and repair costs and recommending aftercare

[1532] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of "refrigerators."

[1533] 2. Server: Based on the prediction results, evaluate the need for aftercare services for the user and store the recommendation results in the database.

[1534] 3. User: Click the "Aftercare Recommendations" button to view details of the recommended aftercare services.

[1535] 4. On the device: Notify the user of the recommended results and display details.

[1536] 5. User: Complete the recommended aftercare service enrollment process.

[1537] In this way, the system of the present invention centrally manages warranty and after-sales information for products purchased online, reducing stress for users when a product breaks down. It also improves customer satisfaction by recommending personalized after-sales services.

[1538] The processing flow will be explained below.

[1539] Step 1:

[1540] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[1541] Step 2:

[1542] On the device: The login information entered by the user is sent to the authentication server.

[1543] Step 3:

[1544] Server: The authentication server verifies the user ID and password, and if authentication is successful, calls the EC platform API based on the user ID.

[1545] Step 4:

[1546] Server: Obtains user purchase history via the EC platform API and stores that data in a database within the system.

[1547] Step 5:

[1548] User: If they want to view warranty information for a specific product they purchased, they select that product in the system.

[1549] Step 6:

[1550] Terminal: Sends the selected product information as a request to the server.

[1551] Step 7:

[1552] Server: Extracts warranty information for the requested product from the database.

[1553] Step 8:

[1554] Server: Returns the extracted warranty information to the user's device.

[1555] Step 9:

[1556] Terminal: Display the returned warranty information on the user's screen.

[1557] Step 10:

[1558] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1559] Step 11:

[1560] Server: The generated failure rate and repair cost prediction results are personalized and stored in a database for each user.

[1561] Step 12:

[1562] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1563] Step 13:

[1564] Server: Runs an algorithm that combines purchase history and failure prediction data to assess the need for aftercare services.

[1565] Step 14:

[1566] Server: Sends the generated aftercare service recommendation results to the user device.

[1567] Step 15:

[1568] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[1569] Step 16:

[1570] User: Check the details of the recommended aftercare service and sign up if necessary.

[1571] Example 1

[1572] 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."

[1573] In today's online shopping environment, users must purchase a variety of home appliances and electronic devices and individually manage the associated warranty and after-care information, which is extremely time-consuming. Furthermore, insufficient information on product failure rates and repair costs after purchase makes it difficult for users to select the appropriate after-care service. Furthermore, the lack of personalized information reduces user convenience. Therefore, to solve these issues, a system is needed that can centrally manage purchase data and failure information and provide users with prompt and accurate warranty information and after-care services.

[1574] 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.

[1575] In this invention, the server includes: means for providing warranty and after-care information based on user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for logging in using the user's account information and acquiring the purchase history after authentication; means for saving the acquired purchase history data in a database; means for extracting warranty information for products selected by the user from the database and displaying it on the user's terminal; means for personalizing the prediction results and saving them in the database for each user; and means for evaluating the need for after-care services and displaying the results on the user's terminal. This allows users to centrally manage warranty and after-care information for home appliances and electronic devices purchased online, providing prompt and accurate information. Furthermore, personalized after-care service recommendations based on predicted failure rates and repair costs significantly improve user convenience.

[1576] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to make predictions and analyze data based on collected data.

[1577] A "custom action" is a special program or function designed to perform a specific task or operation.

[1578] "User purchasing data" refers to data including information about products purchased by users on online shopping platforms and their purchase history.

[1579] "Warranty Information" refers to information that describes the conditions and scope of repairs or replacements within a certain period from the date of purchase of the product.

[1580] "Aftercare information" refers to information regarding services such as repairs, maintenance, and support provided after the purchase of a product.

[1581] "Failure information" refers to data such as troubles and repair history when a product stops working properly.

[1582] "Failure rate" refers to the probability that a product will fail within a specific period of time.

[1583] "Repair costs" refers to the costs required to repair a product when it breaks down.

[1584] "Personalization" refers to the customization of information and services based on the characteristics and history of each individual user.

[1585] "Authentication token" refers to a security token used when exchanging user authentication information.

[1586] "Online platform" refers to a service provision infrastructure available on the Internet, including websites and applications.

[1587] A "database" refers to a dedicated system for efficiently storing, searching, and managing large amounts of data.

[1588] "User terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[1589] This invention is a system that centrally manages warranty and after-care information for home appliances and electronic devices purchased online, and quickly provides personalized information to users. This system uses generative AI models and custom actions to recommend the most suitable after-care services to users.

[1590] First, a user logs in to an online shopping site and enters their account information. The login information is sent from the terminal to the authentication server, which receives an authentication token. After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID and stores this purchase history data in a database.

[1591] Next, when the user selects the product for which they wish to check warranty information, the terminal sends a request to the server with the information about the selected product. The server extracts the warranty information for that product from the database and returns it to the terminal. The terminal then displays the received warranty information on its screen.

[1592] The server then inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The prediction results are personalized and stored in a database for each user.

[1593] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for aftercare service. The evaluation results are sent to the device, which notifies the user and displays detailed information. The user can then check the details of the recommended aftercare service and take the necessary steps.

[1594] This system uses various hardware and software. The server uses a high-performance database system (e.g., MySQL or PostgreSQL) and a machine learning framework such as PyTorch or TensorFlow to run the AI ​​model. The terminal is a device operated by the user, such as a computer or smartphone, which communicates with the server via a browser or dedicated application.

[1595] As a concrete example, a user purchases a home appliance "refrigerator" online and logs in to their account. After logging in, the e-commerce platform sends the purchase history for "refrigerator" to the server. The server saves the purchase data in a database and also retrieves and stores warranty information. If the user wants to check the warranty information, they select "refrigerator" on their device, and the server extracts and displays the warranty information. The generative AI model also predicts the failure rate and repair costs of the "refrigerator," and after-care services are recommended. The user clicks the "Recommend After-care" button, checks the recommended after-care services, and proceeds with the procedure.

[1596] An example of a prompt to input to a generative AI model is as follows:

[1597] Using purchase data and failure information as input, predict the failure rate and repair costs for the target product.

[1598] In this way, the system of the present invention can centrally manage warranty and after-sales information for products purchased by users through online shopping, enabling the provision of fast and accurate information. Furthermore, personalized after-sales service recommendations can significantly improve user convenience.

[1599] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1600] Step 1:

[1601] A user logs into an online shopping site and enters their account information, such as an email address and password, which is then processed on the device.

[1602] Input: User's email address and password

[1603] Output: Authentication request data

[1604] Step 2:

[1605] The terminal sends login information to the authentication server and receives an authentication token. The authentication server verifies the login information and issues an authentication token if it is valid.

[1606] Input: Authentication request data

[1607] Output: Authentication token

[1608] Step 3:

[1609] After successful authentication, the server retrieves the purchase history from the EC platform based on the user ID. The server then uses the authentication token to retrieve the purchase history data from the EC platform via API.

[1610] Input: Authentication token and user ID

[1611] Output: Purchase history data

[1612] Step 4:

[1613] The server saves the acquired purchase history data in the database. The server formats the purchase history data into an appropriate format and saves it in the database using the INSERT statement.

[1614] Input: Purchase history data

[1615] Output: Purchase history stored in the database

[1616] Step 5:

[1617] The user selects the product for which they wish to check warranty information. After logging in, the user clicks on the product in question from the purchase history list on their My Page.

[1618] Input: User input (product selection)

[1619] Output: Product ID

[1620] Step 6:

[1621] The terminal sends the information about the selected product to the server as a request. The terminal uses AJAX to send a request including the product ID to the server.

[1622] Input: Product ID

[1623] Output: Product information request

[1624] Step 7:

[1625] The server extracts the warranty information for the relevant product from the database. The server retrieves the warranty information from the database using a SELECT statement based on the product ID.

[1626] Input: Product information request (product ID)

[1627] Output: Warranty information data

[1628] Step 8:

[1629] The server returns the extracted warranty information to the terminal, converts it into JSON format, and sends it to the terminal as an HTTP response.

[1630] Input: Warranty information data

[1631] Output: Warranty information response

[1632] Step 9:

[1633] The terminal displays the received warranty information on the screen. The terminal parses the received JSON data and dynamically generates and displays the warranty information in HTML.

[1634] Input: Warranty information response

[1635] Output: Warranty information displayed on screen

[1636] Step 10:

[1637] The server inputs purchase data and failure information collected from all e-commerce platforms into a generative AI model to predict the failure rate and repair costs of the target product. The server then formats the collected data into an appropriate format and inputs it into the generative AI model to make predictions.

[1638] Input: Purchase data and failure information

[1639] Output: Failure rate and repair cost prediction results

[1640] Step 11:

[1641] The server personalizes the prediction results and stores them in a database for each user. The server associates the prediction results with the user ID and inserts or updates them into the database.

[1642] Input: Failure rate and repair cost prediction results

[1643] Output: Personalized prediction data

[1644] Step 12:

[1645] The user clicks the "Aftercare Recommendations" button. The user clicks a button on the interface to trigger an event.

[1646] Input: User input (button click)

[1647] Output: Aftercare recommendation request

[1648] Step 13:

[1649] The server integrates the purchase history and failure prediction data to evaluate the need for after-sales service, analyzes the integrated data, and generates after-sales service recommendations based on an algorithm.

[1650] Input: Aftercare recommendation requests, purchase history, failure prediction data

[1651] Output: Aftercare recommendation results

[1652] Step 14:

[1653] The server sends the aftercare recommendation results to the device, converts the recommendation results into JSON format, and sends it to the device as an HTTP response.

[1654] Input: Aftercare recommendation results

[1655] Output: Aftercare recommended response

[1656] Step 15:

[1657] The device will notify the user of the recommended results and display detailed information. The device will parse the received JSON data and dynamically generate and display the recommended results in HTML.

[1658] Input: Aftercare recommendation response

[1659] Output: Aftercare recommendation results displayed on screen

[1660] Step 16:

[1661] The user checks the details of the recommended aftercare service and takes the necessary steps. The user clicks on the link for the recommended aftercare service to go to the details page and proceed with the necessary steps.

[1662] Input: Display aftercare recommendation results

[1663] Output: Aftercare service application procedure

[1664] (Application example 1)

[1665] 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."

[1666] Currently, it is difficult for users to individually manage warranty and after-sales care information for home appliances and electronic devices purchased online, which increases the amount of work required. In addition, since there is no prediction of failure rates or repair costs after purchase, users often miss opportunities to receive appropriate after-sales care services. This results in issues such as lower user satisfaction and lower customer retention rates.

[1667] 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.

[1668] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to users based on the predicted failure rates and repair costs; means for automatically acquiring purchase history from an e-commerce platform and centrally managing warranty information; and means for transmitting personalized after-care service recommendations based on the predicted data to a user terminal. This allows users to centrally manage warranty information and after-care information for purchased products and quickly receive optimal after-care services based on the predicted failure rates and repair costs.

[1669] A "generative AI model" is a type of artificial intelligence that uses purchase data and failure information to predict product failure rates and repair costs.

[1670] A "custom action" is a program that automatically performs specific actions or processes according to the user's needs.

[1671] "Purchase Data" refers to information about products purchased by a User through online shopping.

[1672] "Warranty information" refers to information regarding the warranty period and warranty details provided at the time of product purchase.

[1673] "Aftercare information" refers to information about services such as maintenance, repair, and replacement after purchasing a product.

[1674] "Failure information" refers to data regarding the circumstances and causes of a product failure.

[1675] "Failure rate" is an indicator that indicates the rate at which a certain number of products fail within a specific period of time.

[1676] "Repair costs" refers to the costs required to repair a broken product.

[1677] "Aftercare services" refers to support and maintenance services provided for products after purchase.

[1678] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[1679] "Personalized services" refer to services that are customized based on the characteristics and needs of individual users.

[1680] "Server" refers to a high-performance computer system that stores, manages, and processes data.

[1681] This invention is a system that uses generative AI models and custom actions to provide warranty and after-care information based on user purchase data. To implement this system, a program based on the following steps is required.

[1682] Hardware and software used:

[1683] Hardware:

[1684] server

[1685] User's device (smartphone, smart glasses, head-mounted display)

[1686] software:

[1687] Backend: Python, Flask

[1688] Frontend: React Native

[1689] Database: MongoDB

[1690] AI model: TensorFlow

[1691] Overview of what the system does:

[1692] Retrieving purchase data:

[1693] When a user logs in to the e-commerce platform, the terminal sends the login information to the server. The server obtains the authentication information and, after successful login, retrieves the user's purchase history data from the e-commerce platform. This data is stored in a MongoDB database.

[1694] Warranty information provided:

[1695] When a user selects a specific product in the application, the device requests information about that product from the server, which then retrieves the corresponding warranty information from the MongoDB database and returns it to the device, which then displays the warranty information on the user's screen.

[1696] Failure rate and repair cost forecast:

[1697] The server inputs the collected purchase data and failure information into a generative AI model built with TensorFlow, which predicts product failure rates and repair costs and stores the results in a personalized database.

[1698] Aftercare service advice:

[1699] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history and failure prediction data to evaluate the need for the most appropriate aftercare service. The generated recommendation results are sent to the user's device, which notifies the user and displays detailed information. The user can then proceed with the subscription process for the recommended aftercare service.

[1700] Examples:

[1701] For example, when a user logs into the app on their smartphone, warranty information for a recently purchased refrigerator is automatically displayed. The aftercare screen displays information such as "Predicted failure rate: Low (less than 5%)" and "Predicted repair cost: Less than 5,000 yen." If necessary, the user can click the "Apply for aftercare service" button to proceed with the process.

[1702] Example prompt sentence:

[1703] I'd like to check the warranty information for my refrigerator. I'm also considering after-sales service. Could you please tell me what the warranty covers, the failure rate, and repair costs? Also, could you recommend any after-sales service?

[1704] This allows the system of the present invention to centrally manage and provide warranty and after-care information for products purchased online by users, enabling them to quickly receive optimal after-care service based on predicted failure rates and repair costs.

[1705] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1706] Step 1:

[1707] A user logs in to an e-commerce platform. The terminal sends the user's login information to the server. The server authenticates the login information and obtains the user's ID if successful.

[1708] Input: User login information

[1709] Output: User ID

[1710] Step 2:

[1711] The server retrieves purchase history data from the e-commerce platform based on the user's ID, and stores the data in a MongoDB database.

[1712] Input: User ID

[1713] Output: Purchase history data

[1714] Step 3:

[1715] When a user selects a specific product, the device sends a request to the server with information about the selected product. The server extracts the product's warranty information from the MongoDB database and returns it to the device. The device then displays the warranty information on its screen.

[1716] Input: User selected product information

[1717] Output: Warranty information for the product

[1718] Step 4:

[1719] The server inputs the collected purchase data and failure information into a TensorFlow generative AI model, which then predicts product failure rates and repair costs and stores the results in a personalized database.

[1720] Input: Purchase data and failure information

[1721] Output: Predicted failure rate and repair costs

[1722] Step 5:

[1723] When a user clicks the "Aftercare Recommendation" button, the device sends the information to the server. The server then combines the purchase history with the predicted data on failure rates and repair costs to evaluate the need for aftercare services. The generated recommendation results are sent to the user's device, which then notifies the user.

[1724] Input: Purchase history and predicted failure rate and repair cost data

[1725] Output: Aftercare service recommendation results

[1726] Step 6:

[1727] The user checks the details of the recommended aftercare service and completes the necessary procedures. The terminal sends the procedure completion information to the server, and the server updates the information in the database.

[1728] Input: User's aftercare service procedure information

[1729] Output: Updated database information

[1730] The above is a flow of specific processing steps for implementing this invention, with inputs and outputs clearly defined for each step. This processing flow allows users to centrally manage warranty and after-sales care information for purchased products, enabling them to quickly receive appropriate after-sales care service.

[1731] 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.

[1732] This invention utilizes generative AI models and custom actions to provide a system that provides warranty and after-care information based on user purchase data, and combines it with an emotion engine that recognizes user emotions to provide more personalized services. This system improves user satisfaction and reduces stress by providing warranty and after-care information and recommending after-care services based on the user's emotional data obtained by the emotion engine. It also includes a means for analyzing purchase data and failure information collected from e-commerce platforms to predict product failure rates and repair costs.

[1733] Explanation of program processing

[1734] 1. Acquiring purchase data

[1735] User: Logs into an online shopping site and enters their account information.

[1736] Terminal: Login information is sent to the authentication server and authenticated.

[1737] Server: After successful authentication, the EC platform API is called based on the user ID to retrieve the purchase history.

[1738] Server: Store the acquired purchase history data in a database.

[1739] 2. Acquiring Emotion Data

[1740] User: Provide real-time facial and voice data when checking warranty and aftercare information.

[1741] Device: Recognizes the user's facial expressions and voice and sends them to the emotion engine.

[1742] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[1743] 3. Providing warranty information

[1744] User: Select the product for which you want to view warranty information.

[1745] Terminal: Sends the selected product information as a request to the server.

[1746] Server: Extracts the warranty information for the relevant product from the database.

[1747] Server: Adjusts the extracted guarantee information based on the emotion data and returns it to the device.

[1748] Device: Display adjusted warranty information on the user's screen.

[1749] 4. Failure rate and repair cost prediction

[1750] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1751] Server: Personalizes prediction results and stores them in a database for each user.

[1752] 5. Aftercare service advice

[1753] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1754] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[1755] Server: Sends the recommendation results to the user's device.

[1756] Device: Notify the user of the recommendation and provide more information.

[1757] User: Check the details of the recommended aftercare service and sign up if necessary.

[1758] Specific examples

[1759] Example 1: Acquiring purchase data and utilizing sentiment data

[1760] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[1761] 2. Device: After logging in, the purchase history of the "smart band" is sent from the EC platform to the server.

[1762] 3. Server: Stores purchase data in a database and runs the emotion engine to obtain user emotion data.

[1763] 4. User: If you want to check the warranty information, select "Smart Band" on your device, and the emotion engine will analyze your emotion.

[1764] 5. Terminal: Sends the selection information to the server, which extracts the warranty information for the "smart band" from the database.

[1765] 6. Server: Based on the analysis results of the emotion engine, adjust the guarantee information and send it back to the device.

[1766] 7. Device: Display the adjusted warranty information on the user's screen.

[1767] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[1768] 1. Server: Collects data from each e-commerce platform and inputs it into a generative AI model to predict the failure rate and repair costs of the "smart band."

[1769] 2. Server: Based on the prediction results, it reflects the analysis results of the emotion engine and evaluates the need for aftercare services for the user.

[1770] 3. User: Click the "Aftercare Recommendations" button to see the recommendations based on your emotional data.

[1771] 4. On the device: Notify the user of the recommended results and display details.

[1772] 5. User: Check the details of the recommended aftercare service and sign up if necessary.

[1773] In this way, by combining an emotion engine, the present invention realizes the provision of warranty information and aftercare information that takes into account the user's emotional state, thereby reducing user stress and improving customer satisfaction.

[1774] The processing flow will be explained below.

[1775] Specific processing flow

[1776] 1. Acquiring purchase and sentiment data

[1777] Step 1:

[1778] User: Accesses an online shopping site and enters their account information (user ID and password) on the login screen.

[1779] Step 2:

[1780] On the device: The login information entered by the user is sent to the authentication server.

[1781] Step 3:

[1782] Server: The authentication server verifies the user ID and password, and if authentication is successful, it calls the EC platform API based on the user ID to obtain the purchase history.

[1783] Step 4:

[1784] Server: Stores the acquired purchase history data in a database within the system.

[1785] Step 5:

[1786] User: Navigate through the site to select the product for which they want to check warranty and aftercare information.

[1787] Step 6:

[1788] Terminal: Sends the selected product information as a request to the server. At the same time, sends the user's facial expressions and voice to the emotion engine in real time.

[1789] Step 7:

[1790] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[1791] 2. Providing warranty information

[1792] Step 8:

[1793] Server: Extracts warranty information for the relevant product from the database and adjusts the information based on emotion data.

[1794] Step 9:

[1795] Server: Adjusts the extracted warranty information and returns it to the user's device.

[1796] Step 10:

[1797] Terminal: Display the returned warranty information on the user's screen.

[1798] 3. Failure rate and repair cost prediction

[1799] Step 11:

[1800] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1801] Step 12:

[1802] Server: Personalizes prediction results and stores them in a database for each user.

[1803] 4. Aftercare service advice

[1804] Step 13:

[1805] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1806] Step 14:

[1807] Server: Runs an algorithm that integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[1808] Step 15:

[1809] Server: Sends the generated aftercare service recommendation results to the user device.

[1810] Step 16:

[1811] Device: Aftercare service recommendations are displayed on the screen and notified to the user.

[1812] Step 17:

[1813] User: Check the details of the recommended aftercare service and sign up if necessary.

[1814] Example 2

[1815] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1816] Conventional systems for providing warranty and after-care information did not take into account the user's emotional state. This placed a heavy psychological burden on users, resulting in lower customer satisfaction. Furthermore, the accuracy of predictions based on purchase history and failure information was insufficient, resulting in problems with the after-care services provided not meeting the user's actual needs.

[1817] 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.

[1818] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing the collected purchase data and failure information and predicting product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; means for acquiring user emotional data and customizing the warranty information and after-care information based on the data; means for authenticating the user's login information and acquiring purchase history data from the EC platform; and means for storing the acquired purchase history data in a database, and, when the user selects a specific product, extracting the warranty information for that product from the database and adjusting and displaying it based on the emotional data. This makes it possible to provide warranty information and after-care information that takes the user's emotional state into consideration, thereby reducing the user's psychological burden and improving customer satisfaction.

[1819] A "generative AI model" is an artificial intelligence algorithm that is trained to make predictions or classifications based on specific input data.

[1820] A "custom action" is a unique process or operation that the system automatically performs in response to specific user actions or data input.

[1821] "User purchasing data" refers to the history of products purchased by a user on an online shopping site and information related to such purchases.

[1822] "Warranty Information" means information regarding the product warranty provided with the purchased product.

[1823] "Aftercare information" refers to information regarding support and services provided after purchasing a product.

[1824] "Failure information" refers to the product's failure history and data related to the failure.

[1825] "Emotional data" refers to information that indicates the emotional state of a user, such as information obtained from facial expressions or voice.

[1826] An "emotion engine" is software or a system for analyzing a user's emotional data and identifying the user's emotional state.

[1827] An "EC platform" is an e-commerce platform that allows you to sell and purchase products online.

[1828] An "authentication server" is a server that verifies a user's login information and performs authentication.

[1829] A "database" is a system that systematically organizes and stores information so that it can be searched and used as needed.

[1830] This invention relates to a system that utilizes generative AI models and custom actions to provide warranty and aftercare information based on user purchase data. This allows warranty and aftercare information to be customized based on user emotional data, thereby increasing user satisfaction and reducing stress.

[1831] The system utilizes the following major hardware and software components:

[1832] Server: A central computer system for processing and storing data, including the e-commerce platform API, authentication server, and emotion engine.

[1833] Terminal: A device used by a user (e.g., smartphone, PC) that displays the user interface and collects data using a camera and microphone.

[1834] Database: A system for storing acquired purchase history data and emotional data.

[1835] Emotion engine: Software that analyzes emotional data from a user's facial expressions and voice to identify their emotional state.

[1836] System Overview

[1837] Acquiring purchase data

[1838] User: Visits an online shopping site and logs in using their account information.

[1839] On your device: Send your login information to the authentication server.

[1840] Server: After successful authentication, the EC platform API is called based on the user ID, the purchase history is retrieved, and the history is saved in the database.

[1841] Acquiring emotion data

[1842] User: Provides real-time facial and audio feedback when checking warranty and aftercare information.

[1843] Device: Sends real-time data acquired by the camera and microphone to the emotion engine.

[1844] Server: The emotion engine analyzes the user's emotions and generates emotion data.

[1845] Providing warranty information

[1846] User: Select the product on the device for which they want to check warranty information.

[1847] Terminal: Sends the selected product information as a request to the server.

[1848] Server: Extracts the warranty information for the relevant product from the database, customizes the warranty information based on the emotion data, and sends it to the terminal.

[1849] Device: Display customized warranty information to the user.

[1850] Failure rate and repair cost prediction

[1851] Server: Purchase data and failure information collected from all e-commerce platforms are input into a generative AI model to predict product failure rates and repair costs.

[1852] Server: Personalizes the prediction results and stores them in a database.

[1853] Aftercare service advice

[1854] User: Click the "Aftercare Recommendations" button to see the recommendations.

[1855] Server: Integrates purchase history, failure prediction data, and sentiment data to assess the need for aftercare services.

[1856] Server: Sends the recommendation results to the user's device.

[1857] Device: Notify the user of the recommendation and provide more information.

[1858] User: Check the details of the recommended aftercare service and sign up if necessary.

[1859] Specific examples

[1860] Example 1: Acquiring purchase data and utilizing sentiment data

[1861] 1. User: Purchases a smart band, a home appliance, online and logs in to their account.

[1862] 2. Device: After logging in, it sends a request to the EC platform API and transmits the purchase history of the "smart band" to the server.

[1863] 3. Server: Stores purchase data in a database and launches an emotion engine to obtain the user's emotional state in real time.

[1864] 4. User: If you want to check the warranty information on your device, select "Smart Band."

[1865] 5. Terminal: Sends the selection information to the server, which extracts the product information from the database.

[1866] 6. Server: Adjusts the guarantee information based on the emotion data and returns it to the device.

[1867] 7. Device: Display the adjusted warranty information on the user's screen.

[1868] Example 2: Predicting failure rates and repair costs and utilizing emotion data

[1869] 1. Server: Collects purchase data and failure information from each e-commerce platform and inputs it into the generative AI model.

[1870] 2. Server: Predict the failure rate and repair costs of a "smart band."

[1871] 3. Server: Reflects the user's emotional data and evaluates the need for aftercare.

[1872] 4. User: Click the "Aftercare Recommendations" button to see the recommendations based on the emotional data.

[1873] 5. On the device: Notify the user of the recommended results and display detailed information.

[1874] 6. User: Check the details of the recommended aftercare service and sign up if necessary.

[1875] Prompt Sentence Examples

[1876] "Please explain in detail the program that provides warranty information to users who purchase smart bands online based on their purchase history and real-time sentiment data."

[1877] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1878] Step 1:

[1879] A user accesses an online shopping site and logs in by entering their account information (user ID and password). This results in the acquisition of login information (input: user login information, output: transmission of login request).

[1880] Step 2:

[1881] The terminal sends login information to the authentication server (input: user login information, output: sent authentication request). The authentication server compares the received information with a database, and if the user is authenticated, issues an authentication token (input: authentication request, output: authentication token).

[1882] Step 3:

[1883] The terminal calls the EC platform API using the authentication token and sends a request to acquire the user's purchase history (input: authentication token, output: transmission of purchase history request).

[1884] The server saves the purchase history obtained from the EC platform in a database (input: purchase history data, output: saving to database).

[1885] Step 4:

[1886] When the user checks warranty information or aftercare information, real-time facial expressions and voice are provided (input: user's facial expressions and voice data, output: collection of emotion data).

[1887] The device sends data acquired by the user's camera and microphone to the emotion engine (input: facial expression and voice data, output: sent to the emotion engine).

[1888] Step 5:

[1889] The server's emotion engine analyzes the user's emotions and generates emotion data (input: facial expression and voice data, output: emotion data). Machine learning models and voice analysis algorithms are used for the analysis.

[1890] Step 6:

[1891] When a user selects a specific product and wants to check its warranty information, he or she selects the product on the terminal (input: product selection information, output: request sent to server).

[1892] The terminal sends information about the selected product to the server (input: product ID, output: sending purchase history).

[1893] Step 7:

[1894] The server extracts the warranty information of the relevant product from the database (input: product ID, output: extracted warranty information). The extracted warranty information is adjusted based on the emotion data (input: warranty information, emotion data / output: adjusted warranty information).

[1895] The server sends the adjusted warranty information to the terminal (input: adjusted warranty information, output: transmission to terminal).

[1896] Step 8:

[1897] The terminal displays the adjusted warranty information on the user's screen (input: adjusted warranty information, output: display on user's screen).

[1898] Step 9:

[1899] The server inputs purchasing data and failure information collected from all e-commerce platforms into a generative AI model to predict product failure rates and repair costs (input: purchasing data, failure information; output: predicted failure rates and repair costs).

[1900] Step 10:

[1901] The server personalizes the prediction results and stores them in a database for each user (input: prediction results, output: storage of prediction results).

[1902] Step 11:

[1903] The user clicks the "Recommend Aftercare" button to see the recommendation results (Input: User click information, Output: Submit recommendation request).

[1904] The server integrates the purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services (input: purchase history, prediction data, emotion data; output: aftercare recommendation results).

[1905] Step 12:

[1906] The server sends the recommendation results to the user terminal (input: recommendation results, output: transmission to user terminal).

[1907] The terminal notifies the user of the recommended results and displays detailed information (input: recommended results, output: notification to user, display of detailed information).

[1908] Step 13:

[1909] The user checks the details of the recommended aftercare service and completes the subscription procedure if necessary (input: recommendation result, output: subscription procedure).

[1910] (Application example 2)

[1911] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1912] Conventional systems for providing warranty and after-care information provide uniform information regardless of the user's emotions, which has the problem of not sufficiently improving user satisfaction or reducing stress.In addition, after-care service proposals based on product failure rates and repair cost predictions are insufficient, making it difficult to provide advice appropriate to each user's individual situation.

[1913] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1914] In this invention, the server includes: means for providing warranty information and after-care information from user purchase data using a generative AI model and custom actions; means for analyzing collected purchase data and failure information to predict product failure rates and repair costs; means for recommending optimal after-care services to the user based on the predicted failure rates and repair costs; and means for acquiring user emotion data, recognizing emotions using an emotion engine, and personalizing warranty information and after-care information based on the emotion data. This makes it possible to provide personalized warranty information and after-care information that reflects the user's emotions, thereby achieving user satisfaction and stress reduction.

[1915] A "generative AI model" is an artificial intelligence model that analyzes user purchase data and failure information and provides warranty and after-care information.

[1916] A "custom action" is a set of actions that executes personalized warranty information or aftercare services for a specific user based on a generative AI model.

[1917] "Purchase Data" refers to historical information about products purchased by a user on e-commerce platforms and other online shopping sites.

[1918] "Failure information" refers to information such as the failure history and repair history of each product, and failure rate data provided by the manufacturer.

[1919] "Failure rate" is an indicator of the probability that a particular product will fail within a certain period of time.

[1920] "Repair costs" are the costs required to repair a broken product.

[1921] "Aftercare services" are services such as repairs, maintenance, and warranty extensions provided after a product is purchased.

[1922] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, voice, and other physiological data.

[1923] The "emotion engine" is an engine that analyzes the user's emotional data and recognizes their emotional state.

[1924] "Personalization" means customizing information and services to suit the individual preferences and feelings of each user.

[1925] An "EC platform" is an online system for conducting electronic commerce, where users can search for and purchase products.

[1926] The present invention is a system that utilizes generative AI models and custom actions to provide warranty and after-care information based on user purchase data. By combining this system with an emotion engine, the system provides personalized services that take user emotions into account. Below, we will explain in detail the various functions of the system and its implementation.

[1927] Hardware and Software Use

[1928] This system is realized using the following hardware and software.

[1929] Smartphone camera and microphone: Used to capture the user's facial expressions and voice.

[1930] Device: A device used by a user, such as a smartphone or tablet.

[1931] Server: Stores user credentials, purchase history data, sentiment data, and runs generative AI models.

[1932] Emotional Engine: Analyzes user emotional data using a virtual module called "Emotional Analysis."

[1933] Generative AI model: A virtual module called "AIPredictor" is used to provide warranty and aftercare information.

[1934] Acquiring purchase and sentiment data

[1935] A user logs in to an online shopping site and enters their account information into the device. The device sends the login information to the server, which then authenticates them. If authentication is successful, the server retrieves the user's purchase history data from the e-commerce platform via API and stores it in a database.

[1936] Next, when the user selects a product for which they wish to check warranty or after-sales information, the device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine, which then analyzes the user's emotions in real time and generates emotion data.

[1937] Providing warranty and aftercare information

[1938] When the device selects a specific product, the server retrieves the product's warranty information from the database. The warranty information is then analyzed by a generative AI model and personalized based on emotional data from the emotion engine. That is, if the user is stressed, a message that provides reassurance is added; if the user is satisfied, a message that emphasizes further comfort is added. The adjusted warranty information is then sent back to the device and displayed on the user's screen.

[1939] Prediction of failure rates and repair costs, and recommendations for aftercare services

[1940] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The prediction results are then analyzed along with emotional data to recommend optimal after-sales services to users.

[1941] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can check the details of the recommended aftercare service and, if necessary, complete the subscription procedure.

[1942] Examples of specific examples and prompts

[1943] For example, if a user is watching video content on a smartphone app and the emotion engine detects a stressed state, a personalized message such as "This product's warranty is very reassuring" will be displayed when providing warranty information.

[1944] An example of a prompt for a generative AI model is:

[1945] "A user is concerned about the possibility of their recently purchased smartphone breaking down. Please predict the failure rate and repair costs based on the selected product ID and the user's purchase history data."

[1946] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1947] Step 1:

[1948] A user logs in to an online shopping site and enters their account information. The device sends this login information to the server, which then requests authentication from the authentication server. If authentication is successful, the server calls the EC platform API based on the user ID and obtains the user's purchase history data. The obtained purchase history data is stored in a database.

[1949] Input: User login information

[1950] Output: User purchase history data (stored in database)

[1951] Step 2:

[1952] The user selects the product for which they want to check warranty and after-sales information. The device uses a camera and microphone to record the user's facial expressions and voice, and transmits them to the emotion engine. The emotion engine analyzes the user's emotions in real time and generates emotion data.

[1953] Input: User's facial expression data, voice data

[1954] Output: Parsed emotion data

[1955] Step 3:

[1956] When a device selects a specific product, it sends that information as a request to the server. The server extracts the product's warranty information from the database and analyzes it using a generative AI model. A personalized message based on emotional data is added to the analyzed warranty information, generating an adjusted warranty.

[1957] Input: Product selection information, emotion data

[1958] Output: Adjusted warranty information

[1959] Step 4:

[1960] The server returns the adjusted warranty information to the terminal, which displays it on the user's screen. The user then checks the displayed warranty information.

[1961] Input: Adjusted warranty information

[1962] Output: What is displayed to the user

[1963] Step 5:

[1964] The server inputs purchase data and failure information collected from the e-commerce platform into a generative AI model to predict product failure rates and repair costs. The predicted failure rates and repair costs are then analyzed along with emotional data to recommend optimal after-sales services to users.

[1965] Input: Purchase data, failure information

[1966] Output: Failure rate prediction data, repair cost prediction data

[1967] Step 6:

[1968] When a user clicks the "Recommend Aftercare" button, the server integrates purchase history, failure prediction data, and emotion data to evaluate the need for aftercare services. The recommendation results are sent to the user's device, where detailed information is displayed. The user can then check the details of the recommended aftercare service and, if necessary, apply for it.

[1969] Input: purchase history, failure prediction data, emotion data

[1970] Output: Display of aftercare service recommendation results and detailed information

[1971] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1972] 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.

[1973] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1974] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1975] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1976] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1977] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1978] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1979] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1980] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1981] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1982] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1983] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1984] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1985] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1986] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1987] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1988] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1989] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1990] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1991] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1992] The following is further disclosed regarding the above embodiment.

[1993] (Claim 1)

[1994] A way to provide warranty and aftercare information from user purchase data using generative AI models and custom actions;

[1995] A method for analyzing collected purchase data and failure information to predict product failure rates and repair costs;

[1996] A method for recommending optimal aftercare services to users based on the predicted failure rate and repair costs;

[1997] A system including:

[1998] (Claim 2)

[1999] 2. The system according to claim 1, wherein authentication information is obtained by a user logging in, and purchase history data of the user who has successfully logged in is obtained from the EC platform.

[2000] (Claim 3)

[2001] The system according to claim 1, wherein the acquired purchase history data is stored in a database, and when a user selects a specific product, warranty information for the product is extracted from the database and displayed on the user's terminal.

[2002] "Example 1"

[2003] (Claim 1)

[2004] A means to provide warranty and aftercare information from user purchasing data using generative AI models and custom actions;

[2005] A means of analyzing the collected purchase data and failure information to predict product failure rates and repair costs;

[2006] A method for recommending optimal aftercare services to users based on the predicted failure rate and repair costs;

[2007] A method for logging in using the user's account information and obtaining purchase history after authentication;

[2008] A means for storing the acquired purchase history data in a database;

[2009] A means for extracting warranty information for a product selected by a user from the database and displaying it on a terminal;

[2010] A means to personalize the prediction results and store them in a database for each user;

[2011] a means for assessing the need for aftercare services and displaying the results on a user terminal;

[2012] A system including:

[2013] (Claim 2)

[2014] The system according to claim 1, wherein an authentication token is obtained by a user logging in, and purchase history data of the user who has successfully logged in is obtained from the online platform.

[2015] (Claim 3)

[2016] The system according to claim 1, wherein the acquired purchase history data is stored in a database, and when a user selects a specific product, warranty information for the product is extracted from the database and displayed on the user's terminal.

[2017] "Application Example 1"

[2018] (Claim 1)

[2019] A way to provide warranty and aftercare information from user purchase data using generative AI models and custom actions;

[2020] A method for analyzing collected purchase data and failure information to predict product failure rates and repair costs;

[2021] A method for recommending optimal aftercare services to users based on the predicted failure rate and repair costs;

[2022] A means to automatically retrieve purchase history from e-commerce platforms and centrally manage warranty information;

[2023] a means for transmitting personalized aftercare service recommendations based on the predicted data to a user device;

[2024] A system including:

[2025] (Claim 2)

[2026] 2. The system according to claim 1, wherein authentication information is obtained by a user logging in, and purchase history data of the user who has successfully logged in is obtained from the e-commerce platform.

[2027] (Claim 3)

[2028] The system according to claim 1, wherein the acquired purchase history data is stored in a database, and when a user selects a specific product, warranty information for the product is extracted from the database and displayed on the user's terminal.

[2029] "Example 2: Combining Emotion Engines"

[2030] (Claim 1)

[2031] A means to provide warranty and aftercare information from user purchasing data using generative AI models and custom actions;

[2032] A means of analyzing the collected purchase data and failure information to predict product failure rates and repair costs;

[2033] A method for recommending optimal aftercare services to users based on the predicted failure rate and repair costs;

[2034] A means for acquiring user emotional data and customizing warranty and aftercare information based on that data;

[2035] A means of authenticating user login information and obtaining purchase history data from the e-commerce platform;

[2036] A means for storing the acquired purchase history data in a database, and when a user selects a specific product, extracting warranty information for the product from the database, adjusting it based on the emotion data, and displaying it;

[2037] ...

[2038] A system including:

[2039] (Claim 2)

[2040] The system of claim 1, further comprising: acquiring user purchase data from an e-commerce platform using the acquired login information.

[2041] (Claim 3)

[2042] 10. The system of claim 1, further comprising means for acquiring emotion data in real time and analyzing the data with an emotion engine.

[2043] "Application example 2 when combining emotion engines"

[2044] (Claim 1)

[2045] A way to provide warranty and aftercare information from user purchase data using generative AI models and custom actions;

[2046] A method for analyzing collected purchase data and failure information to predict product failure rates and repair costs;

[2047] A method for recommending optimal aftercare services to users based on the predicted failure rate and repair costs;

[2048] a means for acquiring user emotion data, recognizing the emotion using an emotion engine, and personalizing warranty information and aftercare information based on the emotion data;

[2049] A system including:

[2050] (Claim 2)

[2051] 2. The system according to claim 1, wherein authentication information is obtained by a user logging in, and purchase history data of the user who has successfully logged in is obtained from the EC platform.

[2052] (Claim 3)

[2053] The system of claim 1 stores the acquired purchase history data in a database, and when a user selects a specific product, extracts warranty information for the product from the database, displays it on the user's terminal, and adjusts the warranty information based on the emotion data. [Explanation of symbols]

[2054] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A way to provide warranty and aftercare information from user purchase data using generative AI models and custom actions; A method for analyzing collected purchase data and failure information to predict product failure rates and repair costs; A method for recommending optimal aftercare services to users based on the predicted failure rate and repair costs; A system including:

2. The system according to claim 1, wherein authentication information is acquired by a user logging in, and purchase history data of the user who has successfully logged in is acquired from the EC platform.

3. 2. The system according to claim 1, wherein the acquired purchase history data is stored in a database, and when a user selects a specific product, warranty information for the product is extracted from the database and displayed on the user's terminal.

Images