system

Abstract

Provide a system. [Solution] means for receiving used car information from a user; means for collecting relevant data from a plurality of databases based on the used car information; means for pre-processing the collected data; A method for predicting the market value of used cars using AI models based on pre-processed data; a means for providing the predicted market value to a user; A system including:

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] In traditional used car transactions, it was difficult to set an appropriate price, requiring a lot of time and effort. In particular, there was a lack of a method for quickly and accurately assessing the value of a vehicle based on its characteristics, which often resulted in a lack of fairness in the buying and selling process. Another issue was that it was difficult to quickly reflect market fluctuations, making it difficult to set an optimal price. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means: a system including means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using an AI model based on the preprocessed data, and means for providing the predicted market value to the user. The used car information includes the vehicle type, model year, mileage, accident history, and repair history, the preprocessing means imputes missing values ​​and removes outliers, the AI ​​model uses regression analysis or a deep learning model, and means for saving feedback provided by the user and using it for the next model retraining, thereby achieving fast and accurate value assessment.

[0006] A "user" is a user of the system that provides used car information.

[0007] A "terminal" is a device through which a user inputs information and communicates with the system. For example, this applies to a computer or smartphone.

[0008] "Server" is the central computer system that collects, pre-processes, analyzes, and ultimately values ​​data.

[0009] A "database" is a digital storage system that stores information such as past sales history and market data.

[0010] "Used car information" refers to detailed information about a vehicle, such as the model, year, mileage, accident history, and repair history.

[0011] "Preprocessing" is the process of converting collected data into a format that can be used by an AI model, such as by filling in missing values ​​and removing outliers.

[0012] An "AI model" is a mathematical algorithm that uses machine learning techniques to make predictions and analyze data. Specifically, it includes regression analysis models and deep learning models.

[0013] "Market value" is the amount that indicates the price at which the used car being analyzed should be traded in the current market.

[0014] "Feedback" refers to opinions and evaluations of the system provided by users, which are used to improve the system.

[0015] "Model retraining" is the process of retraining an existing AI model using new data and feedback to improve its prediction accuracy.

[0016] "Missing values" are incomplete or missing values ​​present in collected data.

[0017] An "outlier" is a value in a data set that is significantly different from the other data points. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] 1. Enter user information

[0040] A user uses a terminal to input information about a used car they want to sell (model, year, mileage, accident history, repair history, etc.) For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0041] 2. Data Transmission

[0042] The terminal sends the information entered by the user to the server as a data package, which is sent in JSON or XML format.

[0043] 3. Data Collection and Preprocessing

[0044] The server collects historical sales data and market data for the relevant used car from multiple databases. For example, it retrieves historical sales price data for a 2018 Toyota Camry from a table. It also calls an external API to retrieve the latest market price data for competing models.

[0045] The server then preprocesses the collected data, including imputing missing values ​​(for example, if mileage is missing, it sets the average mileage based on the model and year) and removing outliers, creating a cleaned dataset.

[0046] 4. Value prediction using models

[0047] The server uses AI models, including regression analysis models and deep learning models, to predict the market value of used cars based on the data obtained through preprocessing. For example, a trained regression analysis model is used to calculate the predicted price of a 2018 Toyota Camry.

[0048] 5. Sending and Displaying Results

[0049] The server sends the predicted market value of a used car as a data package to the device, which interprets the data package and displays it on the user interface. For example, the predicted price of a 2018 Toyota Camry is displayed as 2 million yen.

[0050] 6. Feedback Processing

[0051] Users can provide feedback on the predicted price, such as their satisfaction with the system, whether the price is fair, etc. The server stores this feedback in a database and uses it for the next model retraining.

[0052] Specific examples

[0053] For example, if a used car dealer uses this system, they can immediately present the user with a fair price for the vehicle by following the steps below.

[0054] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[0055] 2. The device sends this information to the server.

[0056] 3. The server retrieves the relevant data from the database and external APIs and preprocesses the data.

[0057] 4. The server uses the AI ​​model to calculate the predicted price of the vehicle (for example, 2 million yen).

[0058] 5. The server sends the result to the terminal, and the user confirms the correct price (displays 2 million yen).

[0059] 6. Users can provide feedback that will be used to improve the system in the future.

[0060] In this way, dealers can efficiently and quickly determine the fair price of a used car and offer it to users, improving the fairness and efficiency of transactions.

[0061] The above is an embodiment of the present invention.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0065] Step 2:

[0066] The terminal converts the used car information entered by the user into a data package in JSON or XML format and sends it to the server via an API call.

[0067] Step 3:

[0068] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0069] Step 4:

[0070] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0071] Step 5:

[0072] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0073] Step 6:

[0074] The server converts the predicted market value information back into a data package and transmits it to the terminal.

[0075] Step 7:

[0076] The device interprets the received market value information and displays it on the user interface. For example, the predicted market value of a used car may be displayed on the screen as 2 million yen.

[0077] Step 8:

[0078] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[0079] Step 9:

[0080] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[0081] Example 1

[0082] 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."

[0083] In the traditional used car market, it is difficult to accurately predict market value based on the information provided by sellers, and the market value predictions lack accuracy and reliability.In addition, there is no mechanism for effectively incorporating feedback from users, which limits the system's ability to improve and increase accuracy.

[0084] 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.

[0085] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value to the user, and means for receiving feedback from the user and retraining the generative AI model based on the feedback. This not only enables highly accurate market value predictions based on information entered by the user, but also makes it possible to continuously improve the accuracy and reliability of the system by incorporating user feedback.

[0086] A "user" is a person or entity that uses the system to enter used vehicle information and receive estimated market values.

[0087] "Used car information" refers to information about the used car you want to sell, such as the model, year, mileage, accident history, and repair history.

[0088] The "database" is an information storage system in which the server collects past sales history data and market data for used cars.

[0089] "Collection" refers to the act of importing necessary data from databases, external APIs, etc.

[0090] "Preprocessing" refers to tasks such as filling in missing values ​​and removing outliers from collected data.

[0091] A "generative AI model" is a model trained using machine learning or deep learning algorithms and used to predict the market value of used cars.

[0092] "Market value" is the predicted buying and selling price of a used car.

[0093] "Feedback" is the rating or opinion provided by a user on the predicted market value.

[0094] "Retraining" refers to additional learning based on user feedback to improve the predictive accuracy of the generative AI model.

[0095] The present invention relates to a system for predicting the market value of used cars, and provides a process for users to input used car information and predict market value based on that information. How this system is implemented will be specifically described below.

[0096] First, a user accesses a terminal to enter used car information. A web browser is installed on the terminal, and the user can access the dealer's website. The user enters used car information such as model, year, mileage, accident history, and repair history into an input form on the website. For example, a user might enter the following information: "Toyota Camry, 2018 model, 50,000 km mileage, no accidents, no repairs."

[0097] The device then sends the entered information to the server using an HTTP POST request, with the data sent in JSON format. Based on the received used car information, the server collects relevant data from its own database (e.g., MySQL or PostgreSQL) and external APIs. For example, it retrieves historical sales price data for a 2018 Toyota Camry and the latest market price data for competing models.

[0098] The server preprocesses the collected data. This includes converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if there is data with missing mileage, the average mileage is set based on the model and year of the vehicle. A cleaned dataset is then created.

[0099] Next, the server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Specifically, it loads a trained regression analysis model using machine learning libraries such as TENSORFLOW® and Scikit-learn. The preprocessed data is input into the model, and a predicted value is calculated. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[0100] The server sends the predicted market value in JSON format to the terminal. The terminal receives this data, parses it using JavaScript (registered trademark) in the browser, and displays it in the user interface. The displayed content may include information such as "Predicted price of a 2018 Toyota Camry: 2 million yen."

[0101] Finally, the user can provide feedback on the predicted market value. The user has the option to provide feedback as "satisfied" or "unsatisfied" and submit it. The feedback is sent to the server and stored in a database. This stored feedback is used for the next retraining of the generative AI model.

[0102] An example of a prompt might be, "Toyota Camry 2018, 50,000km, no accidents, no repairs, market value prediction."

[0103] The above is a specific embodiment for carrying out the present invention.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] A user opens a web browser, accesses a dealer's website, enters the vehicle model (e.g., Toyota Camry), model year (e.g., 2018), mileage (e.g., 50,000 km), accident history (e.g., no accidents), and repair history (e.g., no repairs) into the input form, and clicks the "Submit" button.

[0107] (Input): Used car information entered by the user.

[0108] (Output): The entered used car information is saved on the device.

[0109] Step 2:

[0110] The device sends the entered information to the server, and the browser calls the backend API through JavaScript, sending an HTTP POST request, the body of which contains the user-entered information in JSON format.

[0111] (Input): Used car information entered by the user (JSON format).

[0112] (Output): The user's used car information is sent to the server.

[0113] Step 3:

[0114] The server receives the user's used car information and aggregates relevant data from multiple databases. The server first queries its own database (e.g., MySQL or PostgreSQL) to retrieve past sales history for the same model and year. It then calls an external API to retrieve the latest market price data.

[0115] (Input): The user's used car information sent to the server.

[0116] (Output): Historical sales data and latest market price data.

[0117] Step 4:

[0118] The server preprocesses the collected data, converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if mileage is missing, we set the average mileage based on the model and year.

[0119] (Input): Historical sales data and latest market price data.

[0120] (Output): Preprocessed data with missing values ​​and outliers removed.

[0121] Step 5:

[0122] The server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Using machine learning libraries such as TensorFlow and Scikit-learn, the server loads a trained regression analysis model, inputs the preprocessed data into the model, and calculates a predicted value. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[0123] (Input): Preprocessed data.

[0124] (Output): Predicted market value of used cars.

[0125] Step 6:

[0126] The server sends the predicted market value in JSON format to the terminal. The server returns the predicted result to the terminal as an HTTP response. The terminal receives this data, parses it using JavaScript, and displays it in the user interface. For example, it displays "Predicted price of a 2018 Toyota Camry: 2 million yen."

[0127] (Input): Predicted market value data (JSON format).

[0128] (Output): The prediction results displayed in the user interface.

[0129] Step 7:

[0130] The user provides feedback on the prediction results, for example by selecting and submitting a rating such as "satisfied" or "unsatisfied." The device then sends the feedback to the server using an HTTP POST request. The server stores this feedback in a database and uses it to retrain the generative AI model next time.

[0131] (Input): User feedback.

[0132] (Output): The feedback is stored in the database and used for the next model retraining.

[0133] The above are the specific processing steps of the system.

[0134] (Application example 1)

[0135] 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."

[0136] In the process of selling a used car, it is difficult for users to quickly and accurately understand the market value of the vehicle and make the transaction at a fair price. Conventional methods require users to visit multiple dealerships or compare different appraisal sites, which is time-consuming. Furthermore, there is no integrated system that can instantly determine the market value and then directly perform electronic payment, which often reduces the efficiency and fairness of the transaction. The objective of this invention is to solve these problems.

[0137] 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.

[0138] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value on a user interface, means for collecting feedback provided by the user, and means for linking with an electronic payment means so that the market value is settled immediately. This allows the user to quickly and accurately understand the market value of the used car and complete the transaction immediately.

[0139] "User" refers to an individual or corporation that uses this system to input information about used cars and receives the results.

[0140] "Used car information" refers to information required for evaluation, such as the model, year, mileage, accident history, and repair history of the car being sold.

[0141] "Database" refers to a system that manages past sales history data and market data related to used cars.

[0142] "Preprocessing" refers to the process of cleaning collected data, such as filling in missing values ​​and removing outliers.

[0143] "Generative AI model" refers to an artificial intelligence model trained to predict market value based on input data.

[0144] "Market value" refers to the estimated price at which a used car will be sold on the market.

[0145] "User interface" refers to the interface through which a user operates the system and checks information such as predicted market value.

[0146] "Feedback" refers to user-provided ratings and comments on predicted prices.

[0147] "Electronic payment instrument" refers to a system for completing transactions online and making payments instantly.

[0148] System Program

[0149] The system program for implementing the used car instant appraisal and payment app is described below. This system consists of three parties: a server, a terminal, and a user.

[0150] Program processing explanation

[0151] Enter your user information:

[0152] First, a user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. For example, a user might input "2018 Toyota Camry, 50,000 km, no accidents."

[0153] Data transmission:

[0154] The terminal sends the entered used car information to the server as a data package in JSON format, allowing the system to process the information in a consistent data format.

[0155] Data collection and preprocessing:

[0156] The server collects historical sales data and market data related to the used car in question from multiple databases. It also calls an external API to obtain the latest market price data. The server then preprocesses the collected data. Specifically, it completes missing values ​​and removes outliers. This creates a cleaned dataset.

[0157] Model-based value prediction:

[0158] The server uses the preprocessed data to predict the market value of used cars using a generative AI model. This AI model can use regression analysis models or deep learning models. For example, a trained regression analysis model can be used to calculate the predicted price of a 2018 Toyota Camry.

[0159] Send and view results:

[0160] The predicted market value is sent from the server to the terminal as a data package, which the terminal interprets and displays the result on the user interface. For example, the predicted price may be displayed as 2 million yen.

[0161] Feedback processing:

[0162] Users can provide feedback on predicted prices. This feedback includes their satisfaction with the system and their evaluation of the fairness of the price. The server collects this feedback and stores it in a database. This feedback can be used the next time the generative AI model is retrained, enabling more accurate price predictions.

[0163] Instant Payment:

[0164] If the predicted market value is reasonable, the user can immediately enter into a sales contract at that price. The server then connects to an electronic payment method to complete the transaction on the spot.

[0165] Specific examples

[0166] Let's say a user uses this system to enter information about a 2018 Toyota Camry with 50,000 km on the odometer. When the device sends this information to the server, the server collects and preprocesses the relevant data and predicts its market value using a generative AI model. The predicted price is displayed as 2 million yen. If the user is satisfied with the price, the transaction can be completed using the instant payment function. In addition, if the user provides feedback such as "I'm satisfied with the price," the accuracy of the predictions will improve in future transactions.

[0167] Prompt Sentence Examples

[0168] "2018 Toyota Camry, 50,000km, no accidents. What's the market value?"

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] A user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. The input information is formatted as a data package. For example, "2018 Toyota Camry, 50,000 km, no accidents" is input.

[0172] Step 2:

[0173] The terminal sends the entered used car information to the server as a JSON format data package. The sent data package is received by the server and saved in the database as used car information. The input data is "Vehicle model: Toyota Camry, Year: 2018, Mileage: 50,000 km, Accident history: No, Repair history: No."

[0174] Step 3:

[0175] The server collects historical sales data and market data for the relevant used car from multiple databases. Specifically, it executes a query to retrieve data related to the "2018 Toyota Camry." It also calls an external API to retrieve current market price data. The input data is the used car information received in the previous step, and the output data is the market price and past transaction data for competing models.

[0176] Step 4:

[0177] The server preprocesses the collected data. This includes filling in missing values ​​and removing outliers. For example, if the mileage is missing in the collected data, the server sets the average mileage based on the vehicle model and year. The input data is the collected raw data, and the output data is a cleaned dataset.

[0178] Step 5:

[0179] The server uses the preprocessed data to apply a generative AI model to predict the market value of a used car. This AI model uses regression analysis models and deep learning models. The model inputs data such as "Year: 2018, Mileage: 50,000 km" and outputs "Predicted price: 2 million yen."

[0180] Step 6:

[0181] The server sends the predicted market value as a data package to the terminal. The terminal interprets this data package and displays the result on a user interface. For example, "The predicted price of a 2018 Toyota Camry is 2 million yen." The input data is the predicted market value, and the output data is the price information displayed to the user.

[0182] Step 7:

[0183] The user provides feedback on the predicted price displayed on the device. The feedback includes comments on satisfaction and price fairness. The device sends this feedback as a data package to the server. The server stores the feedback in a database and uses it for the next model retraining. The input data is the user's feedback, and the output data is an improved generative AI model.

[0184] Step 8:

[0185] If the user is satisfied with the predicted market value, they can immediately complete the transaction using an electronic payment method through their terminal. The server processes the payment and confirms that the transaction has been successfully completed. The input data are the predicted price and payment information, and the output data is the completed transaction information.

[0186] 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.

[0187] Overall structure

[0188] The present invention combines a system that receives used car information from users and predicts market value based on that information with an emotion engine. The system aims to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation of this system is described below.

[0189] Enter user information

[0190] A user inputs information about a used car (model, year, mileage, accident history, repair history, etc.) through a terminal. For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0191] Recognition of emotional information

[0192] The device monitors the user's input behavior and interface usage in real time to obtain emotional information about the user. Specifically, data such as input speed, input consistency, and error rate are sent to the emotion engine to estimate the user's stress level and satisfaction.

[0193] Data transmission

[0194] The device sends the used car information and emotion information entered by the user to the server as a data package in JSON or XML format.

[0195] Data collection and preprocessing

[0196] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0197] The server then preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0198] Model-based value prediction

[0199] The server uses the preprocessed data to calculate the market value of a used car using an AI model (regression analysis model or deep learning model). For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0200] Emotion-based customization

[0201] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[0202] Sending and viewing results

[0203] The server converts the market value information customized based on the emotion information back into a data package and transmits it to the terminal.

[0204] The device interprets this data package and displays it in a user interface, for example displaying a predicted market value of 2 million yen for a used car, in a way that is adapted to the user's emotional state.

[0205] Feedback Processing

[0206] Users can provide feedback on the displayed market value, including their satisfaction with the system and whether the price is fair.

[0207] The server stores the feedback provided by the user in a database and uses it to retrain the AI ​​model next time, which improves the model's accuracy and allows for more accurate predictions in the future.

[0208] Specific examples

[0209] For example, if a used car dealer uses this system, they can present the user with a fair price for the vehicle by following the steps below.

[0210] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[0211] 2. The device's emotion engine uses this information and the input to detect that the user is feeling stressed.

[0212] 3. The device sends the used car information and emotion information to the server.

[0213] 4. The server collects and preprocesses the relevant data and uses an AI model to calculate the predicted price of the vehicle (for example, 2 million yen).

[0214] 5. The server supports the user's emotional information, selects a rich interface that carefully explains the predicted price, and sends it to the terminal.

[0215] 6. The user checks the fair price (2 million yen) and provides feedback.

[0216] 7. The server stores the feedback and uses it for the next model training.

[0217] The above is an embodiment of a system that combines an emotion engine. This system makes it possible to provide value assessment information that is adapted to the emotional state of the user, and is expected to improve user satisfaction.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0221] Step 2:

[0222] The device monitors the user's input behavior and interface usage, and acquires emotional information from the emotion engine. Specifically, the device estimates the user's stress level and satisfaction level based on data such as input speed, input consistency, and error rate.

[0223] Step 3:

[0224] The terminal converts the used car information entered by the user and the acquired emotional information into a data package in JSON or XML format and sends it to the server via an API call.

[0225] Step 4:

[0226] The server aggregates data related to the received used vehicle information from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0227] Step 5:

[0228] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0229] Step 6:

[0230] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0231] Step 7:

[0232] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation method, and if the user is relaxed, the server presents the information in a standard presentation method.

[0233] Step 8:

[0234] The server reconverts the customized market value information into a data package and transmits it to the terminal.

[0235] Step 9:

[0236] The device interprets the received market value information and displays it in a user interface, for example, displaying a predicted market value of 2 million yen for a used car in a manner that is adapted to the user's emotional state.

[0237] Step 10:

[0238] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[0239] Step 11:

[0240] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[0241] Example 2

[0242] 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."

[0243] Conventional used car market value prediction systems present market values ​​without considering the user's emotional state, resulting in a poor user experience. Furthermore, incorporating emotional information to improve user satisfaction and provide more appropriate information was needed.

[0244] 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.

[0245] In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant data from multiple databases based on the vehicle information, means for preprocessing the collected data, means for predicting the vehicle value using a generative AI model based on the preprocessed data, means for monitoring the user's operating state in real time and acquiring emotional information, means for customizing the presentation method of predicted market value information based on the acquired emotional information, and means for providing the customized market value information to the user. This makes it possible to provide value information according to the user's emotional state, and is expected to improve user satisfaction.

[0246] "User" refers to a person who uses the system to input used car information and obtain value prediction results.

[0247] "Vehicle information" refers to information that indicates the condition of the vehicle, such as the model, year of manufacture, mileage, accident history, and repair history.

[0248] "Database" refers to a data collection that centrally manages multiple data and provides the information necessary to predict the market value of used cars.

[0249] "Preprocessing" refers to the preparation of data before data analysis, such as filling in missing values ​​and removing outliers from collected data.

[0250] A "generative AI model" refers to an algorithm that uses machine learning and deep learning technologies to predict the market value of used cars.

[0251] "Emotion information" refers to information such as the user's stress level and satisfaction level that is estimated based on the user's operating state and input actions.

[0252] "Customization" refers to the process of adjusting the way market value information is presented depending on the user's emotional state.

[0253] "Vehicle Value" refers to the market price of a used vehicle predicted using a generative AI model.

[0254] MODE FOR CARRYING OUT THE INVENTION

[0255] The present invention combines an emotion engine with a system that receives vehicle information from users and predicts market value based on that information. The purpose of this invention is to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation and implementation method of this system are described below.

[0256] Overall structure

[0257] The system consists of multiple software components: a terminal used by users, a server that handles data and analysis, and an emotion engine. The main software used includes the Python pandas library for data processing, TensorFlow and Scikit-learn for AI models, and React and Vue.js for building the user interface.

[0258] 1. Enter user information

[0259] First, the user uses a device to enter vehicle information. This information includes the model, year of manufacture, mileage, accident history, repair history, etc. For example, the user enters information such as "2018 model vehicle, 50,000 km mileage, no accidents." This is done using a web form on the device or a mobile application.

[0260] 2. Recognition of emotional information

[0261] Next, the device monitors the user's operation actions, mouse movements, click speed, etc. in real time. This operation data is sent to the emotion engine, which estimates the user's emotional information (such as stress level and satisfaction). The emotion engine has the ability to recognize the user's emotional state using data such as keystrokes and mouse movements.

[0262] 3. Data Transmission

[0263] The device sends the vehicle information entered by the user and the acquired emotion information as a data package (mainly in JSON format) to the server, where the sent data is managed securely.

[0264] 4. Data Collection and Preprocessing

[0265] The server collects relevant data from internal and external databases, such as past sales history and market price data for specific vehicle models and manufacturing years. It then performs preprocessing on the collected data, such as imputing missing values ​​and removing outliers. This process is performed using the Python pandas library.

[0266] 5. Value Prediction by Model

[0267] Based on the preprocessed data, the server uses a generative AI model to predict the market value of a vehicle. The generative AI model uses machine learning algorithms such as TensorFlow and Scikit-learn. For example, the server predicts that the market value of a specific car model is 2 million yen.

[0268] 6. Emotional customization

[0269] The server customizes the presentation of predicted market value information based on the user's emotional state, for example, by displaying the information in a more visual and easy-to-understand format if the user is feeling stressed.

[0270] 7. Sending and Displaying Results

[0271] The server sends the customized market value information to the device, which then displays it to the user, using a rich interface developed using React and Vue.js.

[0272] 8. Feedback Processing

[0273] Users can provide feedback on the displayed market value information, which is used for the next model retraining, thereby contributing to improving the accuracy of the system.

[0274] Specific examples

[0275] For example, if a used car dealer uses this system, it operates as follows.

[0276] "A user enters information about the car they want to sell on a dealer's website (e.g., "2018 model, 50,000 km on the odometer, no accidents"). The device detects the user's stress from how they type, and the emotion engine generates emotional data. The device sends this data to a server, which collects and preprocesses the data and uses an AI model to predict the market value at 2 million yen. The server customizes the way the information is presented based on the emotional information and sends it to the device. The user then checks the price and provides feedback."

[0277] Example prompts for using generative AI models:

[0278] "Please explain the operating procedure of a system that allows a user to input information about a used car and predict and display its market value based on that information and the user's emotional state. The input vehicle information is a 2018 model with 50,000 km on the odometer and no accidents. The predicted market value is 2 million yen. Also, please explain how to display the results when the user is feeling stressed."

[0279] The above is the details of the "Mode for Carrying Out the Invention." This system makes it possible to provide value information according to the emotional state of the user, thereby improving user satisfaction.

[0280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0281] Step 1:

[0282] The user enters information about the used car (model, year of manufacture, mileage, accident history, repair history, etc.) through the terminal. For example, the user enters information such as "2018 vehicle, 50,000 km mileage, no accidents."

[0283] Input: Vehicle information (e.g., model, year of manufacture, mileage, accident history, repair history)

[0284] Output: Vehicle information is logged to the device.

[0285] Step 2:

[0286] The device monitors the user's input behavior in real time and sends the data to the emotion engine. The emotion engine estimates the user's emotional information from factors such as input speed and error rate. For example, if the input speed is slow and there are many errors, it can be determined that the user is feeling stressed.

[0287] Input: User input behavior (e.g., typing speed, error rate)

[0288] Output: Emotional information (e.g., stress level)

[0289] Step 3:

[0290] The device sends the vehicle information and emotion information entered by the user to the server in JSON format.

[0291] Input: Vehicle information and emotion information

[0292] Output: JSON formatted data package

[0293] Step 4:

[0294] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as market price and past sales history related to a "2018 Toyota Camry."

[0295] Input: Received data (e.g. vehicle information)

[0296] Output: Relevant data collected

[0297] Step 5:

[0298] The server preprocesses the collected data, specifically by imputing missing values ​​and removing outliers. For example, missing mileage data is imputed with the mean value.

[0299] Input: Collected data (e.g. market price, sales history)

[0300] Output: Preprocessed clean data

[0301] Step 6:

[0302] The server uses a generative AI model based on the preprocessed data to predict the market value of a vehicle. For example, the generative AI model predicts the market value of a "2018 model vehicle" to be 2 million yen.

[0303] Input: Preprocessed data

[0304] Output: Predicted market value (e.g., $20,000)

[0305] Step 7:

[0306] The server customizes the presentation of the predicted market value information based on the user's emotional information, for example, selecting a visually easy-to-understand graphical interface if the user is feeling stressed.

[0307] Input: Predicted market value, sentiment information

[0308] Output: Customized presentation

[0309] Step 8:

[0310] The server sends the customized information to the terminal, which then displays the information on a user interface, for example, displaying a predicted market value of 2 million yen. This display is customized according to the user's emotional state.

[0311] Input: Customized Presentation

[0312] Output: Market value information displayed in the user interface

[0313] Step 9:

[0314] Users can provide feedback on the displayed market value information, which is sent to the server and used for the next model retraining.

[0315] Input: Feedback information

[0316] Output: Feedback stored in a database

[0317] It is through these process steps that the invention is embodied.

[0318] (Application example 2)

[0319] 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."

[0320] Conventional used car market value prediction systems predict market value based on information provided by the user, but because they do not take the user's emotional state into account, the presentation method is uniform, resulting in a low quality user experience.While it is necessary to provide appropriate information depending on whether the user is feeling stressed or relaxed, the lack of technology to achieve this is a problem.

[0321] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant information from multiple databases based on the vehicle information, means for preprocessing the collected information, means for predicting market value using a machine learning model based on the preprocessed information, means for evaluating the emotional state of the user and customizing the method for presenting the market value based on the evaluation result, and means for providing the predicted market value to the user in a customized format. This makes it possible to provide appropriate information according to the emotional state of the user, thereby improving the quality of the user experience.

[0322] A "user" is an individual or entity that provides vehicle information to the system.

[0323] "Vehicle information" refers to information about vehicle details, including model, year, mileage, accident history, and repair history.

[0324] "Database" means an internal or external information source for collecting information related to user-provided vehicle information.

[0325] "Preprocessing" is the process of filling in missing information from the collected information and removing outliers.

[0326] A "machine learning model" is a system consisting of a learning algorithm for predicting market value using preprocessed information.

[0327] "Market Value" is the vehicle's estimated value in the current market.

[0328] The "emotional state" refers to the psychological state, such as stress or relaxation, that the user feels when inputting information.

[0329] "Evaluation" is the act of quantitatively measuring and judging the user's emotional state.

[0330] "Customization" refers to tailoring the way information is presented based on the user's emotional state.

[0331] "Offering" is the act of presenting the predicted market value to the user.

[0332] The system for realizing this invention has the following hardware and software configuration: First, a user inputs vehicle information using a smartphone. Next, the device transmits this information to a server, which simultaneously evaluates and digitizes the user's emotional state. Based on the received vehicle information and emotional state information, the server collects relevant information from multiple databases and performs preprocessing. Then, based on the preprocessed data, the server predicts the market value using a machine learning model. Finally, the server provides the user with the market value in a format customized based on the emotional state. This process is described in detail below.

[0333] Enter user information

[0334] The user inputs vehicle information (model, year, mileage, accident history, repair history, etc.) via smartphone. For example, the user inputs a 2018 self-driving car (mileage 50,000 km).

[0335] Recognition of emotional information

[0336] The device monitors the user's input behavior and interface usage in real time to obtain information about the user's emotions. Specifically, the emotion engine estimates the user's stress level and satisfaction level based on data such as input speed and error rate.

[0337] Data transmission

[0338] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format.

[0339] Data collection and preprocessing

[0340] The server collects data related to the vehicle information received in the previous step from multiple internal and external databases. For example, it retrieves past sales history and market price data for autonomous vehicles manufactured in 2018. Next, the server preprocesses the collected data, imputing missing values ​​with averages or estimated values ​​and removing outliers.

[0341] Model-based value prediction

[0342] The server uses machine learning models (linear regression models, deep learning models, etc.) based on the preprocessed data to calculate the market value of the vehicle. For example, the AI ​​model predicts that the market value of an autonomous vehicle manufactured in 2018 is 2 million yen.

[0343] Emotion-based customization

[0344] The server customizes the presentation of the predicted market value information based on the user's emotional state. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[0345] Sending and viewing results

[0346] The server converts the market value information customized based on the emotion information into a data package and transmits it to the terminal, which interprets the data package and displays it on a user interface.

[0347] Feedback Processing

[0348] Users can provide feedback on the displayed market value. This feedback can be about their satisfaction with the system or whether the price is fair. The server stores the feedback provided by users in a database and uses it for the next retraining of the AI ​​model. This improves the accuracy of the model and enables more accurate predictions.

[0349] Examples and prompts

[0350] For example, if a user types into their smartphone that they want to sell a "2018 self-driving car (50,000 km)" and the emotion engine determines that the user is stressed based on their input speed and error rate, the system will provide an interface that explains the market value more clearly.If a prompt such as "Please tell me the value of a 2018 self-driving car. I need this information urgently, so please explain it as clearly as possible" is entered, the system will be able to provide the appropriate information.

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Step 1:

[0353] The user uses a smartphone to input vehicle information (model, year, mileage, accident history, repair history, etc.). At this time, the user inputs the information through the UI, and after input is complete, the information is sent to the device. The input information is first saved on the user's device.

[0354] Step 2:

[0355] The device monitors the user's input behavior (input speed, error rate, etc.) in real time and obtains emotional information. An emotion engine then works to estimate stress levels and satisfaction levels. This evaluates whether the user is relaxed or stressed. This information is also saved as a data package.

[0356] Step 3:

[0357] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format, which includes all the vehicle information and emotion evaluation entered by the user.

[0358] Step 4:

[0359] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as past sales history and market price data, using REST APIs and SQL queries. This information is temporarily stored in a data store.

[0360] Step 5:

[0361] The server preprocesses the collected data, completing missing values ​​with averages or estimated values ​​and removing outliers. The preprocessed data is then passed to the next machine learning model. For example, the Pandas library is used to cleanse the data.

[0362] Step 6:

[0363] The server inputs the preprocessed data into a machine learning model to predict market value. The model used can be, for example, a linear regression model or a deep learning model. The predicted market value obtained here is passed on to the next step. The model prediction is made using a library such as Scikit-learn.

[0364] Step 7:

[0365] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the server determines that the user is stressed, it selects an interface with detailed and thorough explanations, and if the user is relaxed, it selects a simplified interface.

[0366] Step 8:

[0367] The server converts the customized market value information into a data package and transmits it to the terminal, where the data package includes the market value prediction result along with the customized layout.

[0368] Step 9:

[0369] The terminal interprets the data package received from the server and displays it on a user interface, allowing the user to view the estimated market value of the autonomous vehicle in a customized format.

[0370] Step 10:

[0371] The user provides feedback on the displayed market value, for example, by inputting opinions on satisfaction and fairness of the price. This feedback is again transmitted to the server via the terminal.

[0372] Step 11:

[0373] The server stores the feedback provided by users in a database and uses it to retrain the AI ​​model in the future, thereby improving its accuracy.

[0374] 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.

[0375] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0376] 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.

[0377] [Second embodiment]

[0378] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0389] 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."

[0390] 1. Enter user information

[0391] A user uses a terminal to input information about a used car they want to sell (model, year, mileage, accident history, repair history, etc.) For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0392] 2. Data Transmission

[0393] The terminal sends the information entered by the user to the server as a data package, which is sent in JSON or XML format.

[0394] 3. Data Collection and Preprocessing

[0395] The server collects historical sales data and market data for the relevant used car from multiple databases. For example, it retrieves historical sales price data for a 2018 Toyota Camry from a table. It also calls an external API to retrieve the latest market price data for competing models.

[0396] The server then preprocesses the collected data, including imputing missing values ​​(for example, if mileage is missing, it sets the average mileage based on the model and year) and removing outliers, creating a cleaned dataset.

[0397] 4. Value prediction using models

[0398] The server uses AI models, including regression analysis models and deep learning models, to predict the market value of used cars based on the data obtained through preprocessing. For example, a trained regression analysis model is used to calculate the predicted price of a 2018 Toyota Camry.

[0399] 5. Sending and Displaying Results

[0400] The server sends the predicted market value of a used car as a data package to the device, which interprets the data package and displays it on the user interface. For example, the predicted price of a 2018 Toyota Camry is displayed as 2 million yen.

[0401] 6. Feedback Processing

[0402] Users can provide feedback on the predicted price, such as their satisfaction with the system, whether the price is fair, etc. The server stores this feedback in a database and uses it for the next model retraining.

[0403] Specific examples

[0404] For example, if a used car dealer uses this system, they can immediately present the user with a fair price for the vehicle by following the steps below.

[0405] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[0406] 2. The device sends this information to the server.

[0407] 3. The server retrieves the relevant data from the database and external APIs and preprocesses the data.

[0408] 4. The server uses the AI ​​model to calculate the predicted price of the vehicle (for example, 2 million yen).

[0409] 5. The server sends the result to the terminal, and the user confirms the correct price (displays 2 million yen).

[0410] 6. Users can provide feedback that will be used to improve the system in the future.

[0411] In this way, dealers can efficiently and quickly determine the fair price of a used car and offer it to users, improving the fairness and efficiency of transactions.

[0412] The above is an embodiment of the present invention.

[0413] The processing flow will be explained below.

[0414] Step 1:

[0415] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0416] Step 2:

[0417] The terminal converts the used car information entered by the user into a data package in JSON or XML format and sends it to the server via an API call.

[0418] Step 3:

[0419] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0420] Step 4:

[0421] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0422] Step 5:

[0423] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0424] Step 6:

[0425] The server converts the predicted market value information back into a data package and transmits it to the terminal.

[0426] Step 7:

[0427] The device interprets the received market value information and displays it on the user interface. For example, the predicted market value of a used car may be displayed on the screen as 2 million yen.

[0428] Step 8:

[0429] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[0430] Step 9:

[0431] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[0432] Example 1

[0433] 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."

[0434] In the traditional used car market, it is difficult to accurately predict market value based on the information provided by sellers, and the market value predictions lack accuracy and reliability.In addition, there is no mechanism for effectively incorporating feedback from users, which limits the system's ability to improve and increase accuracy.

[0435] 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.

[0436] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value to the user, and means for receiving feedback from the user and retraining the generative AI model based on the feedback. This not only enables highly accurate market value predictions based on information entered by the user, but also makes it possible to continuously improve the accuracy and reliability of the system by incorporating user feedback.

[0437] A "user" is a person or entity that uses the system to enter used vehicle information and receive estimated market values.

[0438] "Used car information" refers to information about the used car you want to sell, such as the model, year, mileage, accident history, and repair history.

[0439] The "database" is an information storage system in which the server collects past sales history data and market data for used cars.

[0440] "Collection" refers to the act of importing necessary data from databases, external APIs, etc.

[0441] "Preprocessing" refers to tasks such as filling in missing values ​​and removing outliers from collected data.

[0442] A "generative AI model" is a model trained using machine learning or deep learning algorithms and used to predict the market value of used cars.

[0443] "Market value" is the predicted buying and selling price of a used car.

[0444] "Feedback" is the rating or opinion provided by a user on the predicted market value.

[0445] "Retraining" refers to additional learning based on user feedback to improve the predictive accuracy of the generative AI model.

[0446] The present invention relates to a system for predicting the market value of used cars, and provides a process for users to input used car information and predict market value based on that information. How this system is implemented will be specifically described below.

[0447] First, a user accesses a terminal to enter used car information. A web browser is installed on the terminal, and the user can access the dealer's website. The user enters used car information such as model, year, mileage, accident history, and repair history into an input form on the website. For example, a user might enter the following information: "Toyota Camry, 2018 model, 50,000 km mileage, no accidents, no repairs."

[0448] The device then sends the entered information to the server using an HTTP POST request, with the data sent in JSON format. The server then gathers relevant data from its own database (e.g., MySQL or PostgreSQL) and external APIs based on the used car information received. For example, it retrieves historical sales price data for a 2018 Toyota Camry and the latest market price data for competing models.

[0449] The server preprocesses the collected data. This includes converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if there is data with missing mileage, the average mileage is set based on the model and year of the vehicle. A cleaned dataset is then created.

[0450] Next, the server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Specifically, it loads a trained regression analysis model using machine learning libraries such as TensorFlow and Scikit-learn. The preprocessed data is input into the model, and a predicted value is calculated. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[0451] The server sends the predicted market value in JSON format to the terminal. The terminal receives this data, parses it using JavaScript in the browser, and displays it in the user interface. The displayed content might include information such as "Predicted price of a 2018 Toyota Camry: 2 million yen."

[0452] Finally, the user can provide feedback on the predicted market value. The user has the option to provide feedback as "satisfied" or "unsatisfied" and submit it. The feedback is sent to the server and stored in a database. This stored feedback is used for the next retraining of the generative AI model.

[0453] An example of a prompt might be, "Toyota Camry 2018, 50,000km, no accidents, no repairs, market value prediction."

[0454] The above is a specific embodiment for carrying out the present invention.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1:

[0457] A user opens a web browser, accesses a dealer's website, enters the vehicle model (e.g., Toyota Camry), model year (e.g., 2018), mileage (e.g., 50,000 km), accident history (e.g., no accidents), and repair history (e.g., no repairs) into the input form, and clicks the "Submit" button.

[0458] (Input): Used car information entered by the user.

[0459] (Output): The entered used car information is saved on the device.

[0460] Step 2:

[0461] The device sends the entered information to the server, and the browser calls the backend API through JavaScript, sending an HTTP POST request, the body of which contains the user-entered information in JSON format.

[0462] (Input): Used car information entered by the user (JSON format).

[0463] (Output): The user's used car information is sent to the server.

[0464] Step 3:

[0465] The server receives the user's used car information and aggregates relevant data from multiple databases. The server first queries its own database (e.g., MySQL or PostgreSQL) to retrieve past sales history for the same model and year. It then calls an external API to retrieve the latest market price data.

[0466] (Input): The user's used car information sent to the server.

[0467] (Output): Historical sales data and latest market price data.

[0468] Step 4:

[0469] The server preprocesses the collected data, converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if mileage is missing, we set the average mileage based on the model and year.

[0470] (Input): Historical sales data and latest market price data.

[0471] (Output): Preprocessed data with missing values ​​and outliers removed.

[0472] Step 5:

[0473] The server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Using machine learning libraries such as TensorFlow and Scikit-learn, the server loads a trained regression analysis model, inputs the preprocessed data into the model, and calculates a predicted value. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[0474] (Input): Preprocessed data.

[0475] (Output): Predicted market value of used cars.

[0476] Step 6:

[0477] The server sends the predicted market value in JSON format to the terminal. The server returns the predicted result to the terminal as an HTTP response. The terminal receives this data, parses it using JavaScript, and displays it in the user interface. For example, it displays "Predicted price of a 2018 Toyota Camry: 2 million yen."

[0478] (Input): Predicted market value data (JSON format).

[0479] (Output): The prediction results displayed in the user interface.

[0480] Step 7:

[0481] The user provides feedback on the prediction results, for example by selecting and submitting a rating such as "satisfied" or "unsatisfied." The device then sends the feedback to the server using an HTTP POST request. The server stores this feedback in a database and uses it to retrain the generative AI model next time.

[0482] (Input): User feedback.

[0483] (Output): The feedback is stored in the database and used for the next model retraining.

[0484] The above are the specific processing steps of the system.

[0485] (Application example 1)

[0486] 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."

[0487] In the process of selling a used car, it is difficult for users to quickly and accurately understand the market value of the vehicle and make the transaction at a fair price. Conventional methods require users to visit multiple dealerships or compare different appraisal sites, which is time-consuming. Furthermore, there is no integrated system that can instantly determine the market value and then directly perform electronic payment, which often reduces the efficiency and fairness of the transaction. The objective of this invention is to solve these problems.

[0488] 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.

[0489] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value on a user interface, means for collecting feedback provided by the user, and means for linking with an electronic payment means so that the market value is settled immediately. This allows the user to quickly and accurately understand the market value of the used car and complete the transaction immediately.

[0490] "User" refers to an individual or corporation that uses this system to input information about used cars and receives the results.

[0491] "Used car information" refers to information required for evaluation, such as the model, year, mileage, accident history, and repair history of the car being sold.

[0492] "Database" refers to a system that manages past sales history data and market data related to used cars.

[0493] "Preprocessing" refers to the process of cleaning collected data, such as filling in missing values ​​and removing outliers.

[0494] "Generative AI model" refers to an artificial intelligence model trained to predict market value based on input data.

[0495] "Market value" refers to the estimated price at which a used car will be sold on the market.

[0496] "User interface" refers to the interface through which a user operates the system and checks information such as predicted market value.

[0497] "Feedback" refers to user-provided ratings and comments on predicted prices.

[0498] "Electronic payment instrument" refers to a system for completing transactions online and making payments instantly.

[0499] System Program

[0500] The system program for implementing the used car instant appraisal and payment app is described below. This system consists of three parties: a server, a terminal, and a user.

[0501] Program processing explanation

[0502] Enter your user information:

[0503] First, a user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. For example, a user might input "2018 Toyota Camry, 50,000 km, no accidents."

[0504] Data transmission:

[0505] The terminal sends the entered used car information to the server as a data package in JSON format, allowing the system to process the information in a consistent data format.

[0506] Data collection and preprocessing:

[0507] The server collects historical sales data and market data related to the used car in question from multiple databases. It also calls an external API to obtain the latest market price data. The server then preprocesses the collected data. Specifically, it completes missing values ​​and removes outliers. This creates a cleaned dataset.

[0508] Model-based value prediction:

[0509] The server uses the preprocessed data to predict the market value of used cars using a generative AI model. This AI model can use regression analysis models or deep learning models. For example, a trained regression analysis model can be used to calculate the predicted price of a 2018 Toyota Camry.

[0510] Send and view results:

[0511] The predicted market value is sent from the server to the terminal as a data package, which the terminal interprets and displays the result on the user interface. For example, the predicted price may be displayed as 2 million yen.

[0512] Feedback processing:

[0513] Users can provide feedback on predicted prices. This feedback includes their satisfaction with the system and their evaluation of the fairness of the price. The server collects this feedback and stores it in a database. This feedback can be used the next time the generative AI model is retrained, enabling more accurate price predictions.

[0514] Instant Payment:

[0515] If the predicted market value is reasonable, the user can immediately enter into a sales contract at that price. The server then connects to an electronic payment method to complete the transaction on the spot.

[0516] Specific examples

[0517] Let's say a user uses this system to enter information about a 2018 Toyota Camry with 50,000 km on the odometer. When the device sends this information to the server, the server collects and preprocesses the relevant data and predicts its market value using a generative AI model. The predicted price is displayed as 2 million yen. If the user is satisfied with the price, the transaction can be completed using the instant payment function. In addition, if the user provides feedback such as "I'm satisfied with the price," the accuracy of the predictions will improve in future transactions.

[0518] Prompt Sentence Examples

[0519] "2018 Toyota Camry, 50,000km, no accidents. What's the market value?"

[0520] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0521] Step 1:

[0522] A user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. The input information is formatted as a data package. For example, "2018 Toyota Camry, 50,000 km, no accidents" is input.

[0523] Step 2:

[0524] The terminal sends the entered used car information to the server as a JSON format data package. The sent data package is received by the server and saved in the database as used car information. The input data is "Vehicle model: Toyota Camry, Year: 2018, Mileage: 50,000 km, Accident history: No, Repair history: No."

[0525] Step 3:

[0526] The server collects historical sales data and market data for the relevant used car from multiple databases. Specifically, it executes a query to retrieve data related to the "2018 Toyota Camry." It also calls an external API to retrieve current market price data. The input data is the used car information received in the previous step, and the output data is the market price and past transaction data for competing models.

[0527] Step 4:

[0528] The server preprocesses the collected data. This includes filling in missing values ​​and removing outliers. For example, if the mileage is missing in the collected data, the server sets the average mileage based on the vehicle model and year. The input data is the collected raw data, and the output data is a cleaned dataset.

[0529] Step 5:

[0530] The server uses the preprocessed data to apply a generative AI model to predict the market value of a used car. This AI model uses regression analysis models and deep learning models. The model inputs data such as "Year: 2018, Mileage: 50,000 km" and outputs "Predicted price: 2 million yen."

[0531] Step 6:

[0532] The server sends the predicted market value as a data package to the terminal. The terminal interprets this data package and displays the result on a user interface. For example, "The predicted price of a 2018 Toyota Camry is 2 million yen." The input data is the predicted market value, and the output data is the price information displayed to the user.

[0533] Step 7:

[0534] The user provides feedback on the predicted price displayed on the device. The feedback includes comments on satisfaction and price fairness. The device sends this feedback as a data package to the server. The server stores the feedback in a database and uses it for the next model retraining. The input data is the user's feedback, and the output data is an improved generative AI model.

[0535] Step 8:

[0536] If the user is satisfied with the predicted market value, they can immediately complete the transaction using an electronic payment method through their terminal. The server processes the payment and confirms that the transaction has been successfully completed. The input data are the predicted price and payment information, and the output data is the completed transaction information.

[0537] 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.

[0538] Overall structure

[0539] The present invention combines a system that receives used car information from users and predicts market value based on that information with an emotion engine. The system aims to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation of this system is described below.

[0540] Enter user information

[0541] A user inputs information about a used car (model, year, mileage, accident history, repair history, etc.) through a terminal. For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0542] Recognition of emotional information

[0543] The device monitors the user's input behavior and interface usage in real time to obtain emotional information about the user. Specifically, data such as input speed, input consistency, and error rate are sent to the emotion engine to estimate the user's stress level and satisfaction.

[0544] Data transmission

[0545] The device sends the used car information and emotion information entered by the user to the server as a data package in JSON or XML format.

[0546] Data collection and preprocessing

[0547] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0548] The server then preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0549] Model-based value prediction

[0550] The server uses the preprocessed data to calculate the market value of a used car using an AI model (regression analysis model or deep learning model). For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0551] Emotion-based customization

[0552] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[0553] Sending and viewing results

[0554] The server converts the market value information customized based on the emotion information back into a data package and transmits it to the terminal.

[0555] The device interprets this data package and displays it in a user interface, for example displaying a predicted market value of 2 million yen for a used car, in a way that is adapted to the user's emotional state.

[0556] Feedback Processing

[0557] Users can provide feedback on the displayed market value, including their satisfaction with the system and whether the price is fair.

[0558] The server stores the feedback provided by the user in a database and uses it to retrain the AI ​​model next time, which improves the model's accuracy and allows for more accurate predictions in the future.

[0559] Specific examples

[0560] For example, if a used car dealer uses this system, they can present the user with a fair price for the vehicle by following the steps below.

[0561] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[0562] 2. The device's emotion engine uses this information and the input to detect that the user is feeling stressed.

[0563] 3. The device sends the used car information and emotion information to the server.

[0564] 4. The server collects and preprocesses the relevant data and uses an AI model to calculate the predicted price of the vehicle (for example, 2 million yen).

[0565] 5. The server supports the user's emotional information, selects a rich interface that carefully explains the predicted price, and sends it to the terminal.

[0566] 6. The user checks the fair price (2 million yen) and provides feedback.

[0567] 7. The server stores the feedback and uses it for the next model training.

[0568] The above is an embodiment of a system that combines an emotion engine. This system makes it possible to provide value assessment information that is adapted to the emotional state of the user, and is expected to improve user satisfaction.

[0569] The processing flow will be explained below.

[0570] Step 1:

[0571] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0572] Step 2:

[0573] The device monitors the user's input behavior and interface usage, and acquires emotional information from the emotion engine. Specifically, the device estimates the user's stress level and satisfaction level based on data such as input speed, input consistency, and error rate.

[0574] Step 3:

[0575] The terminal converts the used car information entered by the user and the acquired emotional information into a data package in JSON or XML format and sends it to the server via an API call.

[0576] Step 4:

[0577] The server aggregates data related to the received used vehicle information from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0578] Step 5:

[0579] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0580] Step 6:

[0581] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0582] Step 7:

[0583] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation method, and if the user is relaxed, the server presents the information in a standard presentation method.

[0584] Step 8:

[0585] The server reconverts the customized market value information into a data package and transmits it to the terminal.

[0586] Step 9:

[0587] The device interprets the received market value information and displays it in a user interface, for example, displaying a predicted market value of 2 million yen for a used car in a manner that is adapted to the user's emotional state.

[0588] Step 10:

[0589] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[0590] Step 11:

[0591] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[0592] Example 2

[0593] 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."

[0594] Conventional used car market value prediction systems present market values ​​without considering the user's emotional state, resulting in a poor user experience. Furthermore, incorporating emotional information to improve user satisfaction and provide more appropriate information was needed.

[0595] 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.

[0596] In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant data from multiple databases based on the vehicle information, means for preprocessing the collected data, means for predicting the vehicle value using a generative AI model based on the preprocessed data, means for monitoring the user's operating state in real time and acquiring emotional information, means for customizing the presentation method of predicted market value information based on the acquired emotional information, and means for providing the customized market value information to the user. This makes it possible to provide value information according to the user's emotional state, and is expected to improve user satisfaction.

[0597] "User" refers to a person who uses the system to input used car information and obtain value prediction results.

[0598] "Vehicle information" refers to information that indicates the condition of the vehicle, such as the model, year of manufacture, mileage, accident history, and repair history.

[0599] "Database" refers to a data collection that centrally manages multiple data and provides the information necessary to predict the market value of used cars.

[0600] "Preprocessing" refers to the preparation of data before data analysis, such as filling in missing values ​​and removing outliers from collected data.

[0601] A "generative AI model" refers to an algorithm that uses machine learning and deep learning technologies to predict the market value of used cars.

[0602] "Emotion information" refers to information such as the user's stress level and satisfaction level that is estimated based on the user's operating state and input actions.

[0603] "Customization" refers to the process of adjusting the way market value information is presented depending on the user's emotional state.

[0604] "Vehicle Value" refers to the market price of a used vehicle predicted using a generative AI model.

[0605] MODE FOR CARRYING OUT THE INVENTION

[0606] The present invention combines an emotion engine with a system that receives vehicle information from users and predicts market value based on that information. The purpose of this invention is to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation and implementation method of this system are described below.

[0607] Overall structure

[0608] The system consists of multiple software components: a terminal used by users, a server that handles data and analysis, and an emotion engine. The main software used includes the Python pandas library for data processing, TensorFlow and Scikit-learn for AI models, and React and Vue.js for building the user interface.

[0609] 1. Enter user information

[0610] First, the user uses a device to enter vehicle information. This information includes the model, year of manufacture, mileage, accident history, repair history, etc. For example, the user enters information such as "2018 model vehicle, 50,000 km mileage, no accidents." This is done using a web form on the device or a mobile application.

[0611] 2. Recognition of emotional information

[0612] Next, the device monitors the user's operation actions, mouse movements, click speed, etc. in real time. This operation data is sent to the emotion engine, which estimates the user's emotional information (such as stress level and satisfaction). The emotion engine has the ability to recognize the user's emotional state using data such as keystrokes and mouse movements.

[0613] 3. Data Transmission

[0614] The device sends the vehicle information entered by the user and the acquired emotion information as a data package (mainly in JSON format) to the server, where the sent data is managed securely.

[0615] 4. Data Collection and Preprocessing

[0616] The server collects relevant data from internal and external databases, such as past sales history and market price data for specific vehicle models and manufacturing years. It then performs preprocessing on the collected data, such as imputing missing values ​​and removing outliers. This process is performed using the Python pandas library.

[0617] 5. Value Prediction by Model

[0618] Based on the preprocessed data, the server uses a generative AI model to predict the market value of a vehicle. The generative AI model uses machine learning algorithms such as TensorFlow and Scikit-learn. For example, the server predicts that the market value of a specific car model is 2 million yen.

[0619] 6. Emotional customization

[0620] The server customizes the presentation of predicted market value information based on the user's emotional state, for example, by displaying the information in a more visual and easy-to-understand format if the user is feeling stressed.

[0621] 7. Sending and Displaying Results

[0622] The server sends the customized market value information to the device, which then displays it to the user, using a rich interface developed using React and Vue.js.

[0623] 8. Feedback Processing

[0624] Users can provide feedback on the displayed market value information, which is used for the next model retraining, thereby contributing to improving the accuracy of the system.

[0625] Specific examples

[0626] For example, if a used car dealer uses this system, it operates as follows.

[0627] "A user enters information about the car they want to sell on a dealer's website (e.g., "2018 model, 50,000 km on the odometer, no accidents"). The device detects the user's stress from how they type, and the emotion engine generates emotional data. The device sends this data to a server, which collects and preprocesses the data and uses an AI model to predict the market value at 2 million yen. The server customizes the way the information is presented based on the emotional information and sends it to the device. The user then checks the price and provides feedback."

[0628] Example prompts for using generative AI models:

[0629] "Please explain the operating procedure of a system that allows a user to input information about a used car and predict and display its market value based on that information and the user's emotional state. The input vehicle information is a 2018 model with 50,000 km on the odometer and no accidents. The predicted market value is 2 million yen. Also, please explain how to display the results when the user is feeling stressed."

[0630] The above is the details of the "Mode for Carrying Out the Invention." This system makes it possible to provide value information according to the emotional state of the user, thereby improving user satisfaction.

[0631] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0632] Step 1:

[0633] The user enters information about the used car (model, year of manufacture, mileage, accident history, repair history, etc.) through the terminal. For example, the user enters information such as "2018 vehicle, 50,000 km mileage, no accidents."

[0634] Input: Vehicle information (e.g., model, year of manufacture, mileage, accident history, repair history)

[0635] Output: Vehicle information is logged to the device.

[0636] Step 2:

[0637] The device monitors the user's input behavior in real time and sends the data to the emotion engine. The emotion engine estimates the user's emotional information from factors such as input speed and error rate. For example, if the input speed is slow and there are many errors, it can be determined that the user is feeling stressed.

[0638] Input: User input behavior (e.g., typing speed, error rate)

[0639] Output: Emotional information (e.g., stress level)

[0640] Step 3:

[0641] The device sends the vehicle information and emotion information entered by the user to the server in JSON format.

[0642] Input: Vehicle information and emotion information

[0643] Output: JSON formatted data package

[0644] Step 4:

[0645] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as market price and past sales history related to a "2018 Toyota Camry."

[0646] Input: Received data (e.g. vehicle information)

[0647] Output: Relevant data collected

[0648] Step 5:

[0649] The server preprocesses the collected data, specifically by imputing missing values ​​and removing outliers. For example, missing mileage data is imputed with the mean value.

[0650] Input: Collected data (e.g. market price, sales history)

[0651] Output: Preprocessed clean data

[0652] Step 6:

[0653] The server uses a generative AI model based on the preprocessed data to predict the market value of a vehicle. For example, the generative AI model predicts the market value of a "2018 model vehicle" to be 2 million yen.

[0654] Input: Preprocessed data

[0655] Output: Predicted market value (e.g., $20,000)

[0656] Step 7:

[0657] The server customizes the presentation of the predicted market value information based on the user's emotional information, for example, selecting a visually easy-to-understand graphical interface if the user is feeling stressed.

[0658] Input: Predicted market value, sentiment information

[0659] Output: Customized presentation

[0660] Step 8:

[0661] The server sends the customized information to the terminal, which then displays the information on a user interface, for example, displaying a predicted market value of 2 million yen. This display is customized according to the user's emotional state.

[0662] Input: Customized Presentation

[0663] Output: Market value information displayed in the user interface

[0664] Step 9:

[0665] Users can provide feedback on the displayed market value information, which is sent to the server and used for the next model retraining.

[0666] Input: Feedback information

[0667] Output: Feedback stored in a database

[0668] It is through these process steps that the invention is embodied.

[0669] (Application example 2)

[0670] 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."

[0671] Conventional used car market value prediction systems predict market value based on information provided by the user, but because they do not take the user's emotional state into account, the presentation method is uniform, resulting in a low quality user experience.While it is necessary to provide appropriate information depending on whether the user is feeling stressed or relaxed, the lack of technology to achieve this is a problem.

[0672] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant information from multiple databases based on the vehicle information, means for preprocessing the collected information, means for predicting market value using a machine learning model based on the preprocessed information, means for evaluating the emotional state of the user and customizing the method for presenting the market value based on the evaluation result, and means for providing the predicted market value to the user in a customized format. This makes it possible to provide appropriate information according to the emotional state of the user, thereby improving the quality of the user experience.

[0673] A "user" is an individual or entity that provides vehicle information to the system.

[0674] "Vehicle information" refers to information about vehicle details, including model, year, mileage, accident history, and repair history.

[0675] "Database" means an internal or external information source for collecting information related to user-provided vehicle information.

[0676] "Preprocessing" is the process of filling in missing information from the collected information and removing outliers.

[0677] A "machine learning model" is a system consisting of a learning algorithm for predicting market value using preprocessed information.

[0678] "Market Value" is the vehicle's estimated value in the current market.

[0679] The "emotional state" refers to the psychological state, such as stress or relaxation, that the user feels when inputting information.

[0680] "Evaluation" is the act of quantitatively measuring and judging the user's emotional state.

[0681] "Customization" refers to tailoring the way information is presented based on the user's emotional state.

[0682] "Offering" is the act of presenting the predicted market value to the user.

[0683] The system for realizing this invention has the following hardware and software configuration: First, a user inputs vehicle information using a smartphone. Next, the device transmits this information to a server, which simultaneously evaluates and digitizes the user's emotional state. Based on the received vehicle information and emotional state information, the server collects relevant information from multiple databases and performs preprocessing. Then, based on the preprocessed data, the server predicts the market value using a machine learning model. Finally, the server provides the user with the market value in a format customized based on the emotional state. This process is described in detail below.

[0684] Enter user information

[0685] The user inputs vehicle information (model, year, mileage, accident history, repair history, etc.) via smartphone. For example, the user inputs a 2018 self-driving car (mileage 50,000 km).

[0686] Recognition of emotional information

[0687] The device monitors the user's input behavior and interface usage in real time to obtain information about the user's emotions. Specifically, the emotion engine estimates the user's stress level and satisfaction level based on data such as input speed and error rate.

[0688] Data transmission

[0689] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format.

[0690] Data collection and preprocessing

[0691] The server collects data related to the vehicle information received in the previous step from multiple internal and external databases. For example, it retrieves past sales history and market price data for autonomous vehicles manufactured in 2018. Next, the server preprocesses the collected data, imputing missing values ​​with averages or estimated values ​​and removing outliers.

[0692] Model-based value prediction

[0693] The server uses machine learning models (linear regression models, deep learning models, etc.) based on the preprocessed data to calculate the market value of the vehicle. For example, the AI ​​model predicts that the market value of an autonomous vehicle manufactured in 2018 is 2 million yen.

[0694] Emotion-based customization

[0695] The server customizes the presentation of the predicted market value information based on the user's emotional state. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[0696] Sending and viewing results

[0697] The server converts the market value information customized based on the emotion information into a data package and transmits it to the terminal, which interprets the data package and displays it on a user interface.

[0698] Feedback Processing

[0699] Users can provide feedback on the displayed market value. This feedback can be about their satisfaction with the system or whether the price is fair. The server stores the feedback provided by users in a database and uses it for the next retraining of the AI ​​model. This improves the accuracy of the model and enables more accurate predictions.

[0700] Examples and prompts

[0701] For example, if a user types into their smartphone that they want to sell a "2018 self-driving car (50,000 km)" and the emotion engine determines that the user is stressed based on their input speed and error rate, the system will provide an interface that explains the market value more clearly.If a prompt such as "Please tell me the value of a 2018 self-driving car. I need this information urgently, so please explain it as clearly as possible" is entered, the system will be able to provide the appropriate information.

[0702] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0703] Step 1:

[0704] The user uses a smartphone to input vehicle information (model, year, mileage, accident history, repair history, etc.). At this time, the user inputs the information through the UI, and after input is complete, the information is sent to the device. The input information is first saved on the user's device.

[0705] Step 2:

[0706] The device monitors the user's input behavior (input speed, error rate, etc.) in real time and obtains emotional information. An emotion engine then works to estimate stress levels and satisfaction levels. This evaluates whether the user is relaxed or stressed. This information is also saved as a data package.

[0707] Step 3:

[0708] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format, which includes all the vehicle information and emotion evaluation entered by the user.

[0709] Step 4:

[0710] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as past sales history and market price data, using REST APIs and SQL queries. This information is temporarily stored in a data store.

[0711] Step 5:

[0712] The server preprocesses the collected data, completing missing values ​​with averages or estimated values ​​and removing outliers. The preprocessed data is then passed to the next machine learning model. For example, the Pandas library is used to cleanse the data.

[0713] Step 6:

[0714] The server inputs the preprocessed data into a machine learning model to predict market value. The model used can be, for example, a linear regression model or a deep learning model. The predicted market value obtained here is passed on to the next step. The model prediction is made using a library such as Scikit-learn.

[0715] Step 7:

[0716] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the server determines that the user is stressed, it selects an interface with detailed and thorough explanations, and if the user is relaxed, it selects a simplified interface.

[0717] Step 8:

[0718] The server converts the customized market value information into a data package and transmits it to the terminal, where the data package includes the market value prediction result along with the customized layout.

[0719] Step 9:

[0720] The terminal interprets the data package received from the server and displays it on a user interface, allowing the user to view the estimated market value of the autonomous vehicle in a customized format.

[0721] Step 10:

[0722] The user provides feedback on the displayed market value, for example, by inputting opinions on satisfaction and fairness of the price. This feedback is again transmitted to the server via the terminal.

[0723] Step 11:

[0724] The server stores the feedback provided by users in a database and uses it to retrain the AI ​​model in the future, thereby improving its accuracy.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] [Third embodiment]

[0729] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0730] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0731] 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).

[0732] 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.

[0733] 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.

[0734] 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).

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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."

[0741] 1. Enter user information

[0742] A user uses a terminal to input information about a used car they want to sell (model, year, mileage, accident history, repair history, etc.) For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0743] 2. Data Transmission

[0744] The terminal sends the information entered by the user to the server as a data package, which is sent in JSON or XML format.

[0745] 3. Data Collection and Preprocessing

[0746] The server collects historical sales data and market data for the relevant used car from multiple databases. For example, it retrieves historical sales price data for a 2018 Toyota Camry from a table. It also calls an external API to retrieve the latest market price data for competing models.

[0747] The server then preprocesses the collected data, including imputing missing values ​​(for example, if mileage is missing, it sets the average mileage based on the model and year) and removing outliers, creating a cleaned dataset.

[0748] 4. Value prediction using models

[0749] The server uses AI models, including regression analysis models and deep learning models, to predict the market value of used cars based on the data obtained through preprocessing. For example, a trained regression analysis model is used to calculate the predicted price of a 2018 Toyota Camry.

[0750] 5. Sending and Displaying Results

[0751] The server sends the predicted market value of a used car as a data package to the device, which interprets the data package and displays it on the user interface. For example, the predicted price of a 2018 Toyota Camry is displayed as 2 million yen.

[0752] 6. Feedback Processing

[0753] Users can provide feedback on the predicted price, such as their satisfaction with the system, whether the price is fair, etc. The server stores this feedback in a database and uses it for the next model retraining.

[0754] Specific examples

[0755] For example, if a used car dealer uses this system, they can immediately present the user with a fair price for the vehicle by following the steps below.

[0756] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[0757] 2. The device sends this information to the server.

[0758] 3. The server retrieves the relevant data from the database and external APIs and preprocesses the data.

[0759] 4. The server uses the AI ​​model to calculate the predicted price of the vehicle (for example, 2 million yen).

[0760] 5. The server sends the result to the terminal, and the user confirms the correct price (displays 2 million yen).

[0761] 6. Users can provide feedback that will be used to improve the system in the future.

[0762] In this way, dealers can efficiently and quickly determine the fair price of a used car and offer it to users, improving the fairness and efficiency of transactions.

[0763] The above is an embodiment of the present invention.

[0764] The processing flow will be explained below.

[0765] Step 1:

[0766] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0767] Step 2:

[0768] The terminal converts the used car information entered by the user into a data package in JSON or XML format and sends it to the server via an API call.

[0769] Step 3:

[0770] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0771] Step 4:

[0772] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0773] Step 5:

[0774] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0775] Step 6:

[0776] The server converts the predicted market value information back into a data package and transmits it to the terminal.

[0777] Step 7:

[0778] The device interprets the received market value information and displays it on the user interface. For example, the predicted market value of a used car may be displayed on the screen as 2 million yen.

[0779] Step 8:

[0780] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[0781] Step 9:

[0782] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[0783] Example 1

[0784] 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."

[0785] In the traditional used car market, it is difficult to accurately predict market value based on the information provided by sellers, and the market value predictions lack accuracy and reliability.In addition, there is no mechanism for effectively incorporating feedback from users, which limits the system's ability to improve and increase accuracy.

[0786] 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.

[0787] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value to the user, and means for receiving feedback from the user and retraining the generative AI model based on the feedback. This not only enables highly accurate market value predictions based on information entered by the user, but also makes it possible to continuously improve the accuracy and reliability of the system by incorporating user feedback.

[0788] A "user" is a person or entity that uses the system to enter used vehicle information and receive estimated market values.

[0789] "Used car information" refers to information about the used car you want to sell, such as the model, year, mileage, accident history, and repair history.

[0790] The "database" is an information storage system in which the server collects past sales history data and market data for used cars.

[0791] "Collection" refers to the act of importing necessary data from databases, external APIs, etc.

[0792] "Preprocessing" refers to tasks such as filling in missing values ​​and removing outliers from collected data.

[0793] A "generative AI model" is a model trained using machine learning or deep learning algorithms and used to predict the market value of used cars.

[0794] "Market value" is the predicted buying and selling price of a used car.

[0795] "Feedback" is the rating or opinion provided by a user on the predicted market value.

[0796] "Retraining" refers to additional learning based on user feedback to improve the predictive accuracy of the generative AI model.

[0797] The present invention relates to a system for predicting the market value of used cars, and provides a process for users to input used car information and predict market value based on that information. How this system is implemented will be specifically described below.

[0798] First, a user accesses a terminal to enter used car information. A web browser is installed on the terminal, and the user can access the dealer's website. The user enters used car information such as model, year, mileage, accident history, and repair history into an input form on the website. For example, a user might enter the following information: "Toyota Camry, 2018 model, 50,000 km mileage, no accidents, no repairs."

[0799] The device then sends the entered information to the server using an HTTP POST request, with the data sent in JSON format. The server then gathers relevant data from its own database (e.g., MySQL or PostgreSQL) and external APIs based on the used car information received. For example, it retrieves historical sales price data for a 2018 Toyota Camry and the latest market price data for competing models.

[0800] The server preprocesses the collected data. This includes converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if there is data with missing mileage, the average mileage is set based on the model and year of the vehicle. A cleaned dataset is then created.

[0801] Next, the server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Specifically, it loads a trained regression analysis model using machine learning libraries such as TensorFlow and Scikit-learn. The preprocessed data is input into the model, and a predicted value is calculated. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[0802] The server sends the predicted market value in JSON format to the terminal. The terminal receives this data, parses it using JavaScript in the browser, and displays it in the user interface. The displayed content might include information such as "Predicted price of a 2018 Toyota Camry: 2 million yen."

[0803] Finally, the user can provide feedback on the predicted market value. The user has the option to provide feedback as "satisfied" or "unsatisfied" and submit it. The feedback is sent to the server and stored in a database. This stored feedback is used for the next retraining of the generative AI model.

[0804] An example of a prompt might be, "Toyota Camry 2018, 50,000km, no accidents, no repairs, market value prediction."

[0805] The above is a specific embodiment for carrying out the present invention.

[0806] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0807] Step 1:

[0808] A user opens a web browser, accesses a dealer's website, enters the vehicle model (e.g., Toyota Camry), model year (e.g., 2018), mileage (e.g., 50,000 km), accident history (e.g., no accidents), and repair history (e.g., no repairs) into the input form, and clicks the "Submit" button.

[0809] (Input): Used car information entered by the user.

[0810] (Output): The entered used car information is saved on the device.

[0811] Step 2:

[0812] The device sends the entered information to the server, and the browser calls the backend API through JavaScript, sending an HTTP POST request, the body of which contains the user-entered information in JSON format.

[0813] (Input): Used car information entered by the user (JSON format).

[0814] (Output): The user's used car information is sent to the server.

[0815] Step 3:

[0816] The server receives the user's used car information and aggregates relevant data from multiple databases. The server first queries its own database (e.g., MySQL or PostgreSQL) to retrieve past sales history for the same model and year. It then calls an external API to retrieve the latest market price data.

[0817] (Input): The user's used car information sent to the server.

[0818] (Output): Historical sales data and latest market price data.

[0819] Step 4:

[0820] The server preprocesses the collected data, converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if mileage is missing, we set the average mileage based on the model and year.

[0821] (Input): Historical sales data and latest market price data.

[0822] (Output): Preprocessed data with missing values ​​and outliers removed.

[0823] Step 5:

[0824] The server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Using machine learning libraries such as TensorFlow and Scikit-learn, the server loads a trained regression analysis model, inputs the preprocessed data into the model, and calculates a predicted value. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[0825] (Input): Preprocessed data.

[0826] (Output): Predicted market value of used cars.

[0827] Step 6:

[0828] The server sends the predicted market value in JSON format to the terminal. The server returns the predicted result to the terminal as an HTTP response. The terminal receives this data, parses it using JavaScript, and displays it in the user interface. For example, it displays "Predicted price of a 2018 Toyota Camry: 2 million yen."

[0829] (Input): Predicted market value data (JSON format).

[0830] (Output): The prediction results displayed in the user interface.

[0831] Step 7:

[0832] The user provides feedback on the prediction results, for example by selecting and submitting a rating such as "satisfied" or "unsatisfied." The device then sends the feedback to the server using an HTTP POST request. The server stores this feedback in a database and uses it to retrain the generative AI model next time.

[0833] (Input): User feedback.

[0834] (Output): The feedback is stored in the database and used for the next model retraining.

[0835] The above are the specific processing steps of the system.

[0836] (Application example 1)

[0837] 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."

[0838] In the process of selling a used car, it is difficult for users to quickly and accurately understand the market value of the vehicle and make the transaction at a fair price. Conventional methods require users to visit multiple dealerships or compare different appraisal sites, which is time-consuming. Furthermore, there is no integrated system that can instantly determine the market value and then directly perform electronic payment, which often reduces the efficiency and fairness of the transaction. The objective of this invention is to solve these problems.

[0839] 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.

[0840] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value on a user interface, means for collecting feedback provided by the user, and means for linking with an electronic payment means so that the market value is settled immediately. This allows the user to quickly and accurately understand the market value of the used car and complete the transaction immediately.

[0841] "User" refers to an individual or corporation that uses this system to input information about used cars and receives the results.

[0842] "Used car information" refers to information required for evaluation, such as the model, year, mileage, accident history, and repair history of the car being sold.

[0843] "Database" refers to a system that manages past sales history data and market data related to used cars.

[0844] "Preprocessing" refers to the process of cleaning collected data, such as filling in missing values ​​and removing outliers.

[0845] "Generative AI model" refers to an artificial intelligence model trained to predict market value based on input data.

[0846] "Market value" refers to the estimated price at which a used car will be sold on the market.

[0847] "User interface" refers to the interface through which a user operates the system and checks information such as predicted market value.

[0848] "Feedback" refers to user-provided ratings and comments on predicted prices.

[0849] "Electronic payment instrument" refers to a system for completing transactions online and making payments instantly.

[0850] System Program

[0851] The system program for implementing the used car instant appraisal and payment app is described below. This system consists of three parties: a server, a terminal, and a user.

[0852] Program processing explanation

[0853] Enter your user information:

[0854] First, a user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. For example, a user might input "2018 Toyota Camry, 50,000 km, no accidents."

[0855] Data transmission:

[0856] The terminal sends the entered used car information to the server as a data package in JSON format, allowing the system to process the information in a consistent data format.

[0857] Data collection and preprocessing:

[0858] The server collects historical sales data and market data related to the used car in question from multiple databases. It also calls an external API to obtain the latest market price data. The server then preprocesses the collected data. Specifically, it completes missing values ​​and removes outliers. This creates a cleaned dataset.

[0859] Model-based value prediction:

[0860] The server uses the preprocessed data to predict the market value of used cars using a generative AI model. This AI model can use regression analysis models or deep learning models. For example, a trained regression analysis model can be used to calculate the predicted price of a 2018 Toyota Camry.

[0861] Send and view results:

[0862] The predicted market value is sent from the server to the terminal as a data package, which the terminal interprets and displays the result on the user interface. For example, the predicted price may be displayed as 2 million yen.

[0863] Feedback processing:

[0864] Users can provide feedback on predicted prices. This feedback includes their satisfaction with the system and their evaluation of the fairness of the price. The server collects this feedback and stores it in a database. This feedback can be used the next time the generative AI model is retrained, enabling more accurate price predictions.

[0865] Instant Payment:

[0866] If the predicted market value is reasonable, the user can immediately enter into a sales contract at that price. The server then connects to an electronic payment method to complete the transaction on the spot.

[0867] Specific examples

[0868] Let's say a user uses this system to enter information about a 2018 Toyota Camry with 50,000 km on the odometer. When the device sends this information to the server, the server collects and preprocesses the relevant data and predicts its market value using a generative AI model. The predicted price is displayed as 2 million yen. If the user is satisfied with the price, the transaction can be completed using the instant payment function. In addition, if the user provides feedback such as "I'm satisfied with the price," the accuracy of the predictions will improve in future transactions.

[0869] Prompt Sentence Examples

[0870] "2018 Toyota Camry, 50,000km, no accidents. What's the market value?"

[0871] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0872] Step 1:

[0873] A user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. The input information is formatted as a data package. For example, "2018 Toyota Camry, 50,000 km, no accidents" is input.

[0874] Step 2:

[0875] The terminal sends the entered used car information to the server as a JSON format data package. The sent data package is received by the server and saved in the database as used car information. The input data is "Vehicle model: Toyota Camry, Year: 2018, Mileage: 50,000 km, Accident history: No, Repair history: No."

[0876] Step 3:

[0877] The server collects historical sales data and market data for the relevant used car from multiple databases. Specifically, it executes a query to retrieve data related to the "2018 Toyota Camry." It also calls an external API to retrieve current market price data. The input data is the used car information received in the previous step, and the output data is the market price and past transaction data for competing models.

[0878] Step 4:

[0879] The server preprocesses the collected data. This includes filling in missing values ​​and removing outliers. For example, if the mileage is missing in the collected data, the server sets the average mileage based on the vehicle model and year. The input data is the collected raw data, and the output data is a cleaned dataset.

[0880] Step 5:

[0881] The server uses the preprocessed data to apply a generative AI model to predict the market value of a used car. This AI model uses regression analysis models and deep learning models. The model inputs data such as "Year: 2018, Mileage: 50,000 km" and outputs "Predicted price: 2 million yen."

[0882] Step 6:

[0883] The server sends the predicted market value as a data package to the terminal. The terminal interprets this data package and displays the result on a user interface. For example, "The predicted price of a 2018 Toyota Camry is 2 million yen." The input data is the predicted market value, and the output data is the price information displayed to the user.

[0884] Step 7:

[0885] The user provides feedback on the predicted price displayed on the device. The feedback includes comments on satisfaction and price fairness. The device sends this feedback as a data package to the server. The server stores the feedback in a database and uses it for the next model retraining. The input data is the user's feedback, and the output data is an improved generative AI model.

[0886] Step 8:

[0887] If the user is satisfied with the predicted market value, they can immediately complete the transaction using an electronic payment method through their terminal. The server processes the payment and confirms that the transaction has been successfully completed. The input data are the predicted price and payment information, and the output data is the completed transaction information.

[0888] 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.

[0889] Overall structure

[0890] The present invention combines a system that receives used car information from users and predicts market value based on that information with an emotion engine. The system aims to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation of this system is described below.

[0891] Enter user information

[0892] A user inputs information about a used car (model, year, mileage, accident history, repair history, etc.) through a terminal. For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0893] Recognition of emotional information

[0894] The device monitors the user's input behavior and interface usage in real time to obtain emotional information about the user. Specifically, data such as input speed, input consistency, and error rate are sent to the emotion engine to estimate the user's stress level and satisfaction.

[0895] Data transmission

[0896] The device sends the used car information and emotion information entered by the user to the server as a data package in JSON or XML format.

[0897] Data collection and preprocessing

[0898] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0899] The server then preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0900] Model-based value prediction

[0901] The server uses the preprocessed data to calculate the market value of a used car using an AI model (regression analysis model or deep learning model). For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0902] Emotion-based customization

[0903] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[0904] Sending and viewing results

[0905] The server converts the market value information customized based on the emotion information back into a data package and transmits it to the terminal.

[0906] The device interprets this data package and displays it in a user interface, for example displaying a predicted market value of 2 million yen for a used car, in a way that is adapted to the user's emotional state.

[0907] Feedback Processing

[0908] Users can provide feedback on the displayed market value, including their satisfaction with the system and whether the price is fair.

[0909] The server stores the feedback provided by the user in a database and uses it to retrain the AI ​​model next time, which improves the model's accuracy and allows for more accurate predictions in the future.

[0910] Specific examples

[0911] For example, if a used car dealer uses this system, they can present the user with a fair price for the vehicle by following the steps below.

[0912] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[0913] 2. The device's emotion engine uses this information and the input to detect that the user is feeling stressed.

[0914] 3. The device sends the used car information and emotion information to the server.

[0915] 4. The server collects and preprocesses the relevant data and uses an AI model to calculate the predicted price of the vehicle (for example, 2 million yen).

[0916] 5. The server supports the user's emotional information, selects a rich interface that carefully explains the predicted price, and sends it to the terminal.

[0917] 6. The user checks the fair price (2 million yen) and provides feedback.

[0918] 7. The server stores the feedback and uses it for the next model training.

[0919] The above is an embodiment of a system that combines an emotion engine. This system makes it possible to provide value assessment information that is adapted to the emotional state of the user, and is expected to improve user satisfaction.

[0920] The processing flow will be explained below.

[0921] Step 1:

[0922] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[0923] Step 2:

[0924] The device monitors the user's input behavior and interface usage, and acquires emotional information from the emotion engine. Specifically, the device estimates the user's stress level and satisfaction level based on data such as input speed, input consistency, and error rate.

[0925] Step 3:

[0926] The terminal converts the used car information entered by the user and the acquired emotional information into a data package in JSON or XML format and sends it to the server via an API call.

[0927] Step 4:

[0928] The server aggregates data related to the received used vehicle information from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[0929] Step 5:

[0930] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[0931] Step 6:

[0932] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[0933] Step 7:

[0934] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation method, and if the user is relaxed, the server presents the information in a standard presentation method.

[0935] Step 8:

[0936] The server reconverts the customized market value information into a data package and transmits it to the terminal.

[0937] Step 9:

[0938] The device interprets the received market value information and displays it in a user interface, for example, displaying a predicted market value of 2 million yen for a used car in a manner that is adapted to the user's emotional state.

[0939] Step 10:

[0940] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[0941] Step 11:

[0942] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[0943] Example 2

[0944] 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."

[0945] Conventional used car market value prediction systems present market values ​​without considering the user's emotional state, resulting in a poor user experience. Furthermore, incorporating emotional information to improve user satisfaction and provide more appropriate information was needed.

[0946] 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.

[0947] In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant data from multiple databases based on the vehicle information, means for preprocessing the collected data, means for predicting the vehicle value using a generative AI model based on the preprocessed data, means for monitoring the user's operating state in real time and acquiring emotional information, means for customizing the presentation method of predicted market value information based on the acquired emotional information, and means for providing the customized market value information to the user. This makes it possible to provide value information according to the user's emotional state, and is expected to improve user satisfaction.

[0948] "User" refers to a person who uses the system to input used car information and obtain value prediction results.

[0949] "Vehicle information" refers to information that indicates the condition of the vehicle, such as the model, year of manufacture, mileage, accident history, and repair history.

[0950] "Database" refers to a data collection that centrally manages multiple data and provides the information necessary to predict the market value of used cars.

[0951] "Preprocessing" refers to the preparation of data before data analysis, such as filling in missing values ​​and removing outliers from collected data.

[0952] A "generative AI model" refers to an algorithm that uses machine learning and deep learning technologies to predict the market value of used cars.

[0953] "Emotion information" refers to information such as the user's stress level and satisfaction level that is estimated based on the user's operating state and input actions.

[0954] "Customization" refers to the process of adjusting the way market value information is presented depending on the user's emotional state.

[0955] "Vehicle Value" refers to the market price of a used vehicle predicted using a generative AI model.

[0956] MODE FOR CARRYING OUT THE INVENTION

[0957] The present invention combines an emotion engine with a system that receives vehicle information from users and predicts market value based on that information. The purpose of this invention is to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation and implementation method of this system are described below.

[0958] Overall structure

[0959] The system consists of multiple software components: a terminal used by users, a server that handles data and analysis, and an emotion engine. The main software used includes the Python pandas library for data processing, TensorFlow and Scikit-learn for AI models, and React and Vue.js for building the user interface.

[0960] 1. Enter user information

[0961] First, the user uses a device to enter vehicle information. This information includes the model, year of manufacture, mileage, accident history, repair history, etc. For example, the user enters information such as "2018 model vehicle, 50,000 km mileage, no accidents." This is done using a web form on the device or a mobile application.

[0962] 2. Recognition of emotional information

[0963] Next, the device monitors the user's operation actions, mouse movements, click speed, etc. in real time. This operation data is sent to the emotion engine, which estimates the user's emotional information (such as stress level and satisfaction). The emotion engine has the ability to recognize the user's emotional state using data such as keystrokes and mouse movements.

[0964] 3. Data Transmission

[0965] The device sends the vehicle information entered by the user and the acquired emotion information as a data package (mainly in JSON format) to the server, where the sent data is managed securely.

[0966] 4. Data Collection and Preprocessing

[0967] The server collects relevant data from internal and external databases, such as past sales history and market price data for specific vehicle models and manufacturing years. It then performs preprocessing on the collected data, such as imputing missing values ​​and removing outliers. This process is performed using the Python pandas library.

[0968] 5. Value Prediction by Model

[0969] Based on the preprocessed data, the server uses a generative AI model to predict the market value of a vehicle. The generative AI model uses machine learning algorithms such as TensorFlow and Scikit-learn. For example, the server predicts that the market value of a specific car model is 2 million yen.

[0970] 6. Emotional customization

[0971] The server customizes the presentation of predicted market value information based on the user's emotional state, for example, by displaying the information in a more visual and easy-to-understand format if the user is feeling stressed.

[0972] 7. Sending and Displaying Results

[0973] The server sends the customized market value information to the device, which then displays it to the user, using a rich interface developed using React and Vue.js.

[0974] 8. Feedback Processing

[0975] Users can provide feedback on the displayed market value information, which is used for the next model retraining, thereby contributing to improving the accuracy of the system.

[0976] Specific examples

[0977] For example, if a used car dealer uses this system, it operates as follows.

[0978] "A user enters information about the car they want to sell on a dealer's website (e.g., "2018 model, 50,000 km on the odometer, no accidents"). The device detects the user's stress from how they type, and the emotion engine generates emotional data. The device sends this data to a server, which collects and preprocesses the data and uses an AI model to predict the market value at 2 million yen. The server customizes the way the information is presented based on the emotional information and sends it to the device. The user then checks the price and provides feedback."

[0979] Example prompts for using generative AI models:

[0980] "Please explain the operating procedure of a system that allows a user to input information about a used car and predict and display its market value based on that information and the user's emotional state. The input vehicle information is a 2018 model with 50,000 km on the odometer and no accidents. The predicted market value is 2 million yen. Also, please explain how to display the results when the user is feeling stressed."

[0981] The above is the details of the "Mode for Carrying Out the Invention." This system makes it possible to provide value information according to the emotional state of the user, thereby improving user satisfaction.

[0982] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0983] Step 1:

[0984] The user enters information about the used car (model, year of manufacture, mileage, accident history, repair history, etc.) through the terminal. For example, the user enters information such as "2018 vehicle, 50,000 km mileage, no accidents."

[0985] Input: Vehicle information (e.g., model, year of manufacture, mileage, accident history, repair history)

[0986] Output: Vehicle information is logged to the device.

[0987] Step 2:

[0988] The device monitors the user's input behavior in real time and sends the data to the emotion engine. The emotion engine estimates the user's emotional information from factors such as input speed and error rate. For example, if the input speed is slow and there are many errors, it can be determined that the user is feeling stressed.

[0989] Input: User input behavior (e.g., typing speed, error rate)

[0990] Output: Emotional information (e.g., stress level)

[0991] Step 3:

[0992] The device sends the vehicle information and emotion information entered by the user to the server in JSON format.

[0993] Input: Vehicle information and emotion information

[0994] Output: JSON formatted data package

[0995] Step 4:

[0996] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as market price and past sales history related to a "2018 Toyota Camry."

[0997] Input: Received data (e.g. vehicle information)

[0998] Output: Relevant data collected

[0999] Step 5:

[1000] The server preprocesses the collected data, specifically by imputing missing values ​​and removing outliers. For example, missing mileage data is imputed with the mean value.

[1001] Input: Collected data (e.g. market price, sales history)

[1002] Output: Preprocessed clean data

[1003] Step 6:

[1004] The server uses a generative AI model based on the preprocessed data to predict the market value of a vehicle. For example, the generative AI model predicts the market value of a "2018 model vehicle" to be 2 million yen.

[1005] Input: Preprocessed data

[1006] Output: Predicted market value (e.g., $20,000)

[1007] Step 7:

[1008] The server customizes the presentation of the predicted market value information based on the user's emotional information, for example, selecting a visually easy-to-understand graphical interface if the user is feeling stressed.

[1009] Input: Predicted market value, sentiment information

[1010] Output: Customized presentation

[1011] Step 8:

[1012] The server sends the customized information to the terminal, which then displays the information on a user interface, for example, displaying a predicted market value of 2 million yen. This display is customized according to the user's emotional state.

[1013] Input: Customized Presentation

[1014] Output: Market value information displayed in the user interface

[1015] Step 9:

[1016] Users can provide feedback on the displayed market value information, which is sent to the server and used for the next model retraining.

[1017] Input: Feedback information

[1018] Output: Feedback stored in a database

[1019] It is through these process steps that the invention is embodied.

[1020] (Application example 2)

[1021] 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."

[1022] Conventional used car market value prediction systems predict market value based on information provided by the user, but because they do not take the user's emotional state into account, the presentation method is uniform, resulting in a low quality user experience.While it is necessary to provide appropriate information depending on whether the user is feeling stressed or relaxed, the lack of technology to achieve this is a problem.

[1023] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant information from multiple databases based on the vehicle information, means for preprocessing the collected information, means for predicting market value using a machine learning model based on the preprocessed information, means for evaluating the emotional state of the user and customizing the method for presenting the market value based on the evaluation result, and means for providing the predicted market value to the user in a customized format. This makes it possible to provide appropriate information according to the emotional state of the user, thereby improving the quality of the user experience.

[1024] A "user" is an individual or entity that provides vehicle information to the system.

[1025] "Vehicle information" refers to information about vehicle details, including model, year, mileage, accident history, and repair history.

[1026] "Database" means an internal or external information source for collecting information related to user-provided vehicle information.

[1027] "Preprocessing" is the process of filling in missing information from the collected information and removing outliers.

[1028] A "machine learning model" is a system consisting of a learning algorithm for predicting market value using preprocessed information.

[1029] "Market Value" is the vehicle's estimated value in the current market.

[1030] The "emotional state" refers to the psychological state, such as stress or relaxation, that the user feels when inputting information.

[1031] "Evaluation" is the act of quantitatively measuring and judging the user's emotional state.

[1032] "Customization" refers to tailoring the way information is presented based on the user's emotional state.

[1033] "Offering" is the act of presenting the predicted market value to the user.

[1034] The system for realizing this invention has the following hardware and software configuration: First, a user inputs vehicle information using a smartphone. Next, the device transmits this information to a server, which simultaneously evaluates and digitizes the user's emotional state. Based on the received vehicle information and emotional state information, the server collects relevant information from multiple databases and performs preprocessing. Then, based on the preprocessed data, the server predicts the market value using a machine learning model. Finally, the server provides the user with the market value in a format customized based on the emotional state. This process is described in detail below.

[1035] Enter user information

[1036] The user inputs vehicle information (model, year, mileage, accident history, repair history, etc.) via smartphone. For example, the user inputs a 2018 self-driving car (mileage 50,000 km).

[1037] Recognition of emotional information

[1038] The device monitors the user's input behavior and interface usage in real time to obtain information about the user's emotions. Specifically, the emotion engine estimates the user's stress level and satisfaction level based on data such as input speed and error rate.

[1039] Data transmission

[1040] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format.

[1041] Data collection and preprocessing

[1042] The server collects data related to the vehicle information received in the previous step from multiple internal and external databases. For example, it retrieves past sales history and market price data for autonomous vehicles manufactured in 2018. Next, the server preprocesses the collected data, imputing missing values ​​with averages or estimated values ​​and removing outliers.

[1043] Model-based value prediction

[1044] The server uses machine learning models (linear regression models, deep learning models, etc.) based on the preprocessed data to calculate the market value of the vehicle. For example, the AI ​​model predicts that the market value of an autonomous vehicle manufactured in 2018 is 2 million yen.

[1045] Emotion-based customization

[1046] The server customizes the presentation of the predicted market value information based on the user's emotional state. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[1047] Sending and viewing results

[1048] The server converts the market value information customized based on the emotion information into a data package and transmits it to the terminal, which interprets the data package and displays it on a user interface.

[1049] Feedback Processing

[1050] Users can provide feedback on the displayed market value. This feedback can be about their satisfaction with the system or whether the price is fair. The server stores the feedback provided by users in a database and uses it for the next retraining of the AI ​​model. This improves the accuracy of the model and enables more accurate predictions.

[1051] Examples and prompts

[1052] For example, if a user types into their smartphone that they want to sell a "2018 self-driving car (50,000 km)" and the emotion engine determines that the user is stressed based on their input speed and error rate, the system will provide an interface that explains the market value more clearly.If a prompt such as "Please tell me the value of a 2018 self-driving car. I need this information urgently, so please explain it as clearly as possible" is entered, the system will be able to provide the appropriate information.

[1053] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1054] Step 1:

[1055] The user uses a smartphone to input vehicle information (model, year, mileage, accident history, repair history, etc.). At this time, the user inputs the information through the UI, and after input is complete, the information is sent to the device. The input information is first saved on the user's device.

[1056] Step 2:

[1057] The device monitors the user's input behavior (input speed, error rate, etc.) in real time and obtains emotional information. An emotion engine then works to estimate stress levels and satisfaction levels. This evaluates whether the user is relaxed or stressed. This information is also saved as a data package.

[1058] Step 3:

[1059] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format, which includes all the vehicle information and emotion evaluation entered by the user.

[1060] Step 4:

[1061] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as past sales history and market price data, using REST APIs and SQL queries. This information is temporarily stored in a data store.

[1062] Step 5:

[1063] The server preprocesses the collected data, completing missing values ​​with averages or estimated values ​​and removing outliers. The preprocessed data is then passed to the next machine learning model. For example, the Pandas library is used to cleanse the data.

[1064] Step 6:

[1065] The server inputs the preprocessed data into a machine learning model to predict market value. The model used can be, for example, a linear regression model or a deep learning model. The predicted market value obtained here is passed on to the next step. The model prediction is made using a library such as Scikit-learn.

[1066] Step 7:

[1067] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the server determines that the user is stressed, it selects an interface with detailed and thorough explanations, and if the user is relaxed, it selects a simplified interface.

[1068] Step 8:

[1069] The server converts the customized market value information into a data package and transmits it to the terminal, where the data package includes the market value prediction result along with the customized layout.

[1070] Step 9:

[1071] The terminal interprets the data package received from the server and displays it on a user interface, allowing the user to view the estimated market value of the autonomous vehicle in a customized format.

[1072] Step 10:

[1073] The user provides feedback on the displayed market value, for example, by inputting opinions on satisfaction and fairness of the price. This feedback is again transmitted to the server via the terminal.

[1074] Step 11:

[1075] The server stores the feedback provided by users in a database and uses it to retrain the AI ​​model in the future, thereby improving its accuracy.

[1076] 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.

[1077] 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.

[1078] 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.

[1079] [Fourth embodiment]

[1080] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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).

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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.

[1091] 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.

[1092] 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."

[1093] 1. Enter user information

[1094] A user uses a terminal to input information about a used car they want to sell (model, year, mileage, accident history, repair history, etc.) For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[1095] 2. Data Transmission

[1096] The terminal sends the information entered by the user to the server as a data package, which is sent in JSON or XML format.

[1097] 3. Data Collection and Preprocessing

[1098] The server collects historical sales data and market data for the relevant used car from multiple databases. For example, it retrieves historical sales price data for a 2018 Toyota Camry from a table. It also calls an external API to retrieve the latest market price data for competing models.

[1099] The server then preprocesses the collected data, including imputing missing values ​​(for example, if mileage is missing, it sets the average mileage based on the model and year) and removing outliers, creating a cleaned dataset.

[1100] 4. Value prediction using models

[1101] The server uses AI models, including regression analysis models and deep learning models, to predict the market value of used cars based on the data obtained through preprocessing. For example, a trained regression analysis model is used to calculate the predicted price of a 2018 Toyota Camry.

[1102] 5. Sending and Displaying Results

[1103] The server sends the predicted market value of a used car as a data package to the device, which interprets the data package and displays it on the user interface. For example, the predicted price of a 2018 Toyota Camry is displayed as 2 million yen.

[1104] 6. Feedback Processing

[1105] Users can provide feedback on the predicted price, such as their satisfaction with the system, whether the price is fair, etc. The server stores this feedback in a database and uses it for the next model retraining.

[1106] Specific examples

[1107] For example, if a used car dealer uses this system, they can immediately present the user with a fair price for the vehicle by following the steps below.

[1108] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[1109] 2. The device sends this information to the server.

[1110] 3. The server retrieves the relevant data from the database and external APIs and preprocesses the data.

[1111] 4. The server uses the AI ​​model to calculate the predicted price of the vehicle (for example, 2 million yen).

[1112] 5. The server sends the result to the terminal, and the user confirms the correct price (displays 2 million yen).

[1113] 6. Users can provide feedback that will be used to improve the system in the future.

[1114] In this way, dealers can efficiently and quickly determine the fair price of a used car and offer it to users, improving the fairness and efficiency of transactions.

[1115] The above is an embodiment of the present invention.

[1116] The processing flow will be explained below.

[1117] Step 1:

[1118] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[1119] Step 2:

[1120] The terminal converts the used car information entered by the user into a data package in JSON or XML format and sends it to the server via an API call.

[1121] Step 3:

[1122] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[1123] Step 4:

[1124] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[1125] Step 5:

[1126] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[1127] Step 6:

[1128] The server converts the predicted market value information back into a data package and transmits it to the terminal.

[1129] Step 7:

[1130] The device interprets the received market value information and displays it on the user interface. For example, the predicted market value of a used car may be displayed on the screen as 2 million yen.

[1131] Step 8:

[1132] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[1133] Step 9:

[1134] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[1135] Example 1

[1136] 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."

[1137] In the traditional used car market, it is difficult to accurately predict market value based on the information provided by sellers, and the market value predictions lack accuracy and reliability.In addition, there is no mechanism for effectively incorporating feedback from users, which limits the system's ability to improve and increase accuracy.

[1138] 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.

[1139] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value to the user, and means for receiving feedback from the user and retraining the generative AI model based on the feedback. This not only enables highly accurate market value predictions based on information entered by the user, but also makes it possible to continuously improve the accuracy and reliability of the system by incorporating user feedback.

[1140] A "user" is a person or entity that uses the system to enter used vehicle information and receive estimated market values.

[1141] "Used car information" refers to information about the used car you want to sell, such as the model, year, mileage, accident history, and repair history.

[1142] The "database" is an information storage system in which the server collects past sales history data and market data for used cars.

[1143] "Collection" refers to the act of importing necessary data from databases, external APIs, etc.

[1144] "Preprocessing" refers to tasks such as filling in missing values ​​and removing outliers from collected data.

[1145] A "generative AI model" is a model trained using machine learning or deep learning algorithms and used to predict the market value of used cars.

[1146] "Market value" is the predicted buying and selling price of a used car.

[1147] "Feedback" is the rating or opinion provided by a user on the predicted market value.

[1148] "Retraining" refers to additional learning based on user feedback to improve the predictive accuracy of the generative AI model.

[1149] The present invention relates to a system for predicting the market value of used cars, and provides a process for users to input used car information and predict market value based on that information. How this system is implemented will be specifically described below.

[1150] First, a user accesses a terminal to enter used car information. A web browser is installed on the terminal, and the user can access the dealer's website. The user enters used car information such as model, year, mileage, accident history, and repair history into an input form on the website. For example, a user might enter the following information: "Toyota Camry, 2018 model, 50,000 km mileage, no accidents, no repairs."

[1151] The device then sends the entered information to the server using an HTTP POST request, with the data sent in JSON format. The server then gathers relevant data from its own database (e.g., MySQL or PostgreSQL) and external APIs based on the used car information received. For example, it retrieves historical sales price data for a 2018 Toyota Camry and the latest market price data for competing models.

[1152] The server preprocesses the collected data. This includes converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if there is data with missing mileage, the average mileage is set based on the model and year of the vehicle. A cleaned dataset is then created.

[1153] Next, the server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Specifically, it loads a trained regression analysis model using machine learning libraries such as TensorFlow and Scikit-learn. The preprocessed data is input into the model, and a predicted value is calculated. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[1154] The server sends the predicted market value in JSON format to the terminal. The terminal receives this data, parses it using JavaScript in the browser, and displays it in the user interface. The displayed content might include information such as "Predicted price of a 2018 Toyota Camry: 2 million yen."

[1155] Finally, the user can provide feedback on the predicted market value. The user has the option to provide feedback as "satisfied" or "unsatisfied" and submit it. The feedback is sent to the server and stored in a database. This stored feedback is used for the next retraining of the generative AI model.

[1156] An example of a prompt might be, "Toyota Camry 2018, 50,000km, no accidents, no repairs, market value prediction."

[1157] The above is a specific embodiment for carrying out the present invention.

[1158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1159] Step 1:

[1160] A user opens a web browser, accesses a dealer's website, enters the vehicle model (e.g., Toyota Camry), model year (e.g., 2018), mileage (e.g., 50,000 km), accident history (e.g., no accidents), and repair history (e.g., no repairs) into the input form, and clicks the "Submit" button.

[1161] (Input): Used car information entered by the user.

[1162] (Output): The entered used car information is saved on the device.

[1163] Step 2:

[1164] The device sends the entered information to the server, and the browser calls the backend API through JavaScript, sending an HTTP POST request, the body of which contains the user-entered information in JSON format.

[1165] (Input): Used car information entered by the user (JSON format).

[1166] (Output): The user's used car information is sent to the server.

[1167] Step 3:

[1168] The server receives the user's used car information and aggregates relevant data from multiple databases. The server first queries its own database (e.g., MySQL or PostgreSQL) to retrieve past sales history for the same model and year. It then calls an external API to retrieve the latest market price data.

[1169] (Input): The user's used car information sent to the server.

[1170] (Output): Historical sales data and latest market price data.

[1171] Step 4:

[1172] The server preprocesses the collected data, converting it into a data frame using the Pandas library, imputing missing values, and removing outliers. For example, if mileage is missing, we set the average mileage based on the model and year.

[1173] (Input): Historical sales data and latest market price data.

[1174] (Output): Preprocessed data with missing values ​​and outliers removed.

[1175] Step 5:

[1176] The server uses a generative AI model based on the preprocessed data to predict the market value of used cars. Using machine learning libraries such as TensorFlow and Scikit-learn, the server loads a trained regression analysis model, inputs the preprocessed data into the model, and calculates a predicted value. For example, the market value of a 2018 Toyota Camry is predicted to be 2 million yen.

[1177] (Input): Preprocessed data.

[1178] (Output): Predicted market value of used cars.

[1179] Step 6:

[1180] The server sends the predicted market value in JSON format to the terminal. The server returns the predicted result to the terminal as an HTTP response. The terminal receives this data, parses it using JavaScript, and displays it in the user interface. For example, it displays "Predicted price of a 2018 Toyota Camry: 2 million yen."

[1181] (Input): Predicted market value data (JSON format).

[1182] (Output): The prediction results displayed in the user interface.

[1183] Step 7:

[1184] The user provides feedback on the prediction results, for example by selecting and submitting a rating such as "satisfied" or "unsatisfied." The device then sends the feedback to the server using an HTTP POST request. The server stores this feedback in a database and uses it to retrain the generative AI model next time.

[1185] (Input): User feedback.

[1186] (Output): The feedback is stored in the database and used for the next model retraining.

[1187] The above are the specific processing steps of the system.

[1188] (Application example 1)

[1189] 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."

[1190] In the process of selling a used car, it is difficult for users to quickly and accurately understand the market value of the vehicle and make the transaction at a fair price. Conventional methods require users to visit multiple dealerships or compare different appraisal sites, which is time-consuming. Furthermore, there is no integrated system that can instantly determine the market value and then directly perform electronic payment, which often reduces the efficiency and fairness of the transaction. The objective of this invention is to solve these problems.

[1191] 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.

[1192] In this invention, the server includes means for receiving used car information from a user, means for collecting relevant data from multiple databases based on the used car information, means for preprocessing the collected data, means for predicting the market value of the used car using a generative AI model based on the preprocessed data, means for providing the predicted market value on a user interface, means for collecting feedback provided by the user, and means for linking with an electronic payment means so that the market value is settled immediately. This allows the user to quickly and accurately understand the market value of the used car and complete the transaction immediately.

[1193] "User" refers to an individual or corporation that uses this system to input information about used cars and receives the results.

[1194] "Used car information" refers to information required for evaluation, such as the model, year, mileage, accident history, and repair history of the car being sold.

[1195] "Database" refers to a system that manages past sales history data and market data related to used cars.

[1196] "Preprocessing" refers to the process of cleaning collected data, such as filling in missing values ​​and removing outliers.

[1197] "Generative AI model" refers to an artificial intelligence model trained to predict market value based on input data.

[1198] "Market value" refers to the estimated price at which a used car will be sold on the market.

[1199] "User interface" refers to the interface through which a user operates the system and checks information such as predicted market value.

[1200] "Feedback" refers to user-provided ratings and comments on predicted prices.

[1201] "Electronic payment instrument" refers to a system for completing transactions online and making payments instantly.

[1202] System Program

[1203] The system program for implementing the used car instant appraisal and payment app is described below. This system consists of three parties: a server, a terminal, and a user.

[1204] Program processing explanation

[1205] Enter your user information:

[1206] First, a user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. For example, a user might input "2018 Toyota Camry, 50,000 km, no accidents."

[1207] Data transmission:

[1208] The terminal sends the entered used car information to the server as a data package in JSON format, allowing the system to process the information in a consistent data format.

[1209] Data collection and preprocessing:

[1210] The server collects historical sales data and market data related to the used car in question from multiple databases. It also calls an external API to obtain the latest market price data. The server then preprocesses the collected data. Specifically, it completes missing values ​​and removes outliers. This creates a cleaned dataset.

[1211] Model-based value prediction:

[1212] The server uses the preprocessed data to predict the market value of used cars using a generative AI model. This AI model can use regression analysis models or deep learning models. For example, a trained regression analysis model can be used to calculate the predicted price of a 2018 Toyota Camry.

[1213] Send and view results:

[1214] The predicted market value is sent from the server to the terminal as a data package, which the terminal interprets and displays the result on the user interface. For example, the predicted price may be displayed as 2 million yen.

[1215] Feedback processing:

[1216] Users can provide feedback on predicted prices. This feedback includes their satisfaction with the system and their evaluation of the fairness of the price. The server collects this feedback and stores it in a database. This feedback can be used the next time the generative AI model is retrained, enabling more accurate price predictions.

[1217] Instant Payment:

[1218] If the predicted market value is reasonable, the user can immediately enter into a sales contract at that price. The server then connects to an electronic payment method to complete the transaction on the spot.

[1219] Specific examples

[1220] Let's say a user uses this system to enter information about a 2018 Toyota Camry with 50,000 km on the odometer. When the device sends this information to the server, the server collects and preprocesses the relevant data and predicts its market value using a generative AI model. The predicted price is displayed as 2 million yen. If the user is satisfied with the price, the transaction can be completed using the instant payment function. In addition, if the user provides feedback such as "I'm satisfied with the price," the accuracy of the predictions will improve in future transactions.

[1221] Prompt Sentence Examples

[1222] "2018 Toyota Camry, 50,000km, no accidents. What's the market value?"

[1223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1224] Step 1:

[1225] A user uses a terminal to input information about a used car. This information includes the model, year, mileage, accident history, repair history, etc. The input information is formatted as a data package. For example, "2018 Toyota Camry, 50,000 km, no accidents" is input.

[1226] Step 2:

[1227] The terminal sends the entered used car information to the server as a JSON format data package. The sent data package is received by the server and saved in the database as used car information. The input data is "Vehicle model: Toyota Camry, Year: 2018, Mileage: 50,000 km, Accident history: No, Repair history: No."

[1228] Step 3:

[1229] The server collects historical sales data and market data for the relevant used car from multiple databases. Specifically, it executes a query to retrieve data related to the "2018 Toyota Camry." It also calls an external API to retrieve current market price data. The input data is the used car information received in the previous step, and the output data is the market price and past transaction data for competing models.

[1230] Step 4:

[1231] The server preprocesses the collected data. This includes filling in missing values ​​and removing outliers. For example, if the mileage is missing in the collected data, the server sets the average mileage based on the vehicle model and year. The input data is the collected raw data, and the output data is a cleaned dataset.

[1232] Step 5:

[1233] The server uses the preprocessed data to apply a generative AI model to predict the market value of a used car. This AI model uses regression analysis models and deep learning models. The model inputs data such as "Year: 2018, Mileage: 50,000 km" and outputs "Predicted price: 2 million yen."

[1234] Step 6:

[1235] The server sends the predicted market value as a data package to the terminal. The terminal interprets this data package and displays the result on a user interface. For example, "The predicted price of a 2018 Toyota Camry is 2 million yen." The input data is the predicted market value, and the output data is the price information displayed to the user.

[1236] Step 7:

[1237] The user provides feedback on the predicted price displayed on the device. The feedback includes comments on satisfaction and price fairness. The device sends this feedback as a data package to the server. The server stores the feedback in a database and uses it for the next model retraining. The input data is the user's feedback, and the output data is an improved generative AI model.

[1238] Step 8:

[1239] If the user is satisfied with the predicted market value, they can immediately complete the transaction using an electronic payment method through their terminal. The server processes the payment and confirms that the transaction has been successfully completed. The input data are the predicted price and payment information, and the output data is the completed transaction information.

[1240] 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.

[1241] Overall structure

[1242] The present invention combines a system that receives used car information from users and predicts market value based on that information with an emotion engine. The system aims to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation of this system is described below.

[1243] Enter user information

[1244] A user inputs information about a used car (model, year, mileage, accident history, repair history, etc.) through a terminal. For example, a user inputs information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[1245] Recognition of emotional information

[1246] The device monitors the user's input behavior and interface usage in real time to obtain emotional information about the user. Specifically, data such as input speed, input consistency, and error rate are sent to the emotion engine to estimate the user's stress level and satisfaction.

[1247] Data transmission

[1248] The device sends the used car information and emotion information entered by the user to the server as a data package in JSON or XML format.

[1249] Data collection and preprocessing

[1250] The server collects data related to the used vehicle information received in the previous step from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[1251] The server then preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[1252] Model-based value prediction

[1253] The server uses the preprocessed data to calculate the market value of a used car using an AI model (regression analysis model or deep learning model). For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[1254] Emotion-based customization

[1255] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[1256] Sending and viewing results

[1257] The server converts the market value information customized based on the emotion information back into a data package and transmits it to the terminal.

[1258] The device interprets this data package and displays it in a user interface, for example displaying a predicted market value of 2 million yen for a used car, in a way that is adapted to the user's emotional state.

[1259] Feedback Processing

[1260] Users can provide feedback on the displayed market value, including their satisfaction with the system and whether the price is fair.

[1261] The server stores the feedback provided by the user in a database and uses it to retrain the AI ​​model next time, which improves the model's accuracy and allows for more accurate predictions in the future.

[1262] Specific examples

[1263] For example, if a used car dealer uses this system, they can present the user with a fair price for the vehicle by following the steps below.

[1264] 1. A user enters the details of the car they want to sell on a dealer's website (Toyota Camry, 2018 model, 50,000 km).

[1265] 2. The device's emotion engine uses this information and the input to detect that the user is feeling stressed.

[1266] 3. The device sends the used car information and emotion information to the server.

[1267] 4. The server collects and preprocesses the relevant data and uses an AI model to calculate the predicted price of the vehicle (for example, 2 million yen).

[1268] 5. The server supports the user's emotional information, selects a rich interface that carefully explains the predicted price, and sends it to the terminal.

[1269] 6. The user checks the fair price (2 million yen) and provides feedback.

[1270] 7. The server stores the feedback and uses it for the next model training.

[1271] The above is an embodiment of a system that combines an emotion engine. This system makes it possible to provide value assessment information that is adapted to the emotional state of the user, and is expected to improve user satisfaction.

[1272] The processing flow will be explained below.

[1273] Step 1:

[1274] A user enters information about a used car (model, year, mileage, accident history, repair history, etc.) into the device interface. For example, a user enters information about a 2018 Toyota Camry with 50,000 km of mileage and no accidents.

[1275] Step 2:

[1276] The device monitors the user's input behavior and interface usage, and acquires emotional information from the emotion engine. Specifically, the device estimates the user's stress level and satisfaction level based on data such as input speed, input consistency, and error rate.

[1277] Step 3:

[1278] The terminal converts the used car information entered by the user and the acquired emotional information into a data package in JSON or XML format and sends it to the server via an API call.

[1279] Step 4:

[1280] The server aggregates data related to the received used vehicle information from multiple internal and external databases, such as past sales history and market price data for a 2018 Toyota Camry.

[1281] Step 5:

[1282] The server preprocesses the collected data, imputing missing values ​​with averages or estimates and removing outliers (for example, imputing missing mileage data with the average mileage based on the vehicle model and year).

[1283] Step 6:

[1284] The server uses an AI model (regression analysis model or deep learning model) to calculate the market value of a used car based on the preprocessed data. For example, the AI ​​model predicts that the market value of a 2018 Toyota Camry is 2 million yen.

[1285] Step 7:

[1286] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation method, and if the user is relaxed, the server presents the information in a standard presentation method.

[1287] Step 8:

[1288] The server reconverts the customized market value information into a data package and transmits it to the terminal.

[1289] Step 9:

[1290] The device interprets the received market value information and displays it in a user interface, for example, displaying a predicted market value of 2 million yen for a used car in a manner that is adapted to the user's emotional state.

[1291] Step 10:

[1292] Users provide feedback on the displayed market value, including their evaluation of the system and the fairness of the price.

[1293] Step 11:

[1294] The server stores the user-provided feedback in a database and uses it to retrain the AI ​​model next time, improving the model's accuracy and enabling more accurate predictions in the future.

[1295] Example 2

[1296] 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."

[1297] Conventional used car market value prediction systems present market values ​​without considering the user's emotional state, resulting in a poor user experience. Furthermore, incorporating emotional information to improve user satisfaction and provide more appropriate information was needed.

[1298] 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.

[1299] In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant data from multiple databases based on the vehicle information, means for preprocessing the collected data, means for predicting the vehicle value using a generative AI model based on the preprocessed data, means for monitoring the user's operating state in real time and acquiring emotional information, means for customizing the presentation method of predicted market value information based on the acquired emotional information, and means for providing the customized market value information to the user. This makes it possible to provide value information according to the user's emotional state, and is expected to improve user satisfaction.

[1300] "User" refers to a person who uses the system to input used car information and obtain value prediction results.

[1301] "Vehicle information" refers to information that indicates the condition of the vehicle, such as the model, year of manufacture, mileage, accident history, and repair history.

[1302] "Database" refers to a data collection that centrally manages multiple data and provides the information necessary to predict the market value of used cars.

[1303] "Preprocessing" refers to the preparation of data before data analysis, such as filling in missing values ​​and removing outliers from collected data.

[1304] A "generative AI model" refers to an algorithm that uses machine learning and deep learning technologies to predict the market value of used cars.

[1305] "Emotion information" refers to information such as the user's stress level and satisfaction level that is estimated based on the user's operating state and input actions.

[1306] "Customization" refers to the process of adjusting the way market value information is presented depending on the user's emotional state.

[1307] "Vehicle Value" refers to the market price of a used vehicle predicted using a generative AI model.

[1308] MODE FOR CARRYING OUT THE INVENTION

[1309] The present invention combines an emotion engine with a system that receives vehicle information from users and predicts market value based on that information. The purpose of this invention is to recognize the user's emotional state and customize the way market value information is presented based on that state. The specific operation and implementation method of this system are described below.

[1310] Overall structure

[1311] The system consists of multiple software components: a terminal used by users, a server that handles data and analysis, and an emotion engine. The main software used includes the Python pandas library for data processing, TensorFlow and Scikit-learn for AI models, and React and Vue.js for building the user interface.

[1312] 1. Enter user information

[1313] First, the user uses a device to enter vehicle information. This information includes the model, year of manufacture, mileage, accident history, repair history, etc. For example, the user enters information such as "2018 model vehicle, 50,000 km mileage, no accidents." This is done using a web form on the device or a mobile application.

[1314] 2. Recognition of emotional information

[1315] Next, the device monitors the user's operation actions, mouse movements, click speed, etc. in real time. This operation data is sent to the emotion engine, which estimates the user's emotional information (such as stress level and satisfaction). The emotion engine has the ability to recognize the user's emotional state using data such as keystrokes and mouse movements.

[1316] 3. Data Transmission

[1317] The device sends the vehicle information entered by the user and the acquired emotion information as a data package (mainly in JSON format) to the server, where the sent data is managed securely.

[1318] 4. Data Collection and Preprocessing

[1319] The server collects relevant data from internal and external databases, such as past sales history and market price data for specific vehicle models and manufacturing years. It then performs preprocessing on the collected data, such as imputing missing values ​​and removing outliers. This process is performed using the Python pandas library.

[1320] 5. Value Prediction by Model

[1321] Based on the preprocessed data, the server uses a generative AI model to predict the market value of a vehicle. The generative AI model uses machine learning algorithms such as TensorFlow and Scikit-learn. For example, the server predicts that the market value of a specific car model is 2 million yen.

[1322] 6. Emotional customization

[1323] The server customizes the presentation of predicted market value information based on the user's emotional state, for example, by displaying the information in a more visual and easy-to-understand format if the user is feeling stressed.

[1324] 7. Sending and Displaying Results

[1325] The server sends the customized market value information to the device, which then displays it to the user, using a rich interface developed using React and Vue.js.

[1326] 8. Feedback Processing

[1327] Users can provide feedback on the displayed market value information, which is used for the next model retraining, thereby contributing to improving the accuracy of the system.

[1328] Specific examples

[1329] For example, if a used car dealer uses this system, it operates as follows.

[1330] "A user enters information about the car they want to sell on a dealer's website (e.g., "2018 model, 50,000 km on the odometer, no accidents"). The device detects the user's stress from how they type, and the emotion engine generates emotional data. The device sends this data to a server, which collects and preprocesses the data and uses an AI model to predict the market value at 2 million yen. The server customizes the way the information is presented based on the emotional information and sends it to the device. The user then checks the price and provides feedback."

[1331] Example prompts for using generative AI models:

[1332] "Please explain the operating procedure of a system that allows a user to input information about a used car and predict and display its market value based on that information and the user's emotional state. The input vehicle information is a 2018 model with 50,000 km on the odometer and no accidents. The predicted market value is 2 million yen. Also, please explain how to display the results when the user is feeling stressed."

[1333] The above is the details of the "Mode for Carrying Out the Invention." This system makes it possible to provide value information according to the emotional state of the user, thereby improving user satisfaction.

[1334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1335] Step 1:

[1336] The user enters information about the used car (model, year of manufacture, mileage, accident history, repair history, etc.) through the terminal. For example, the user enters information such as "2018 vehicle, 50,000 km mileage, no accidents."

[1337] Input: Vehicle information (e.g., model, year of manufacture, mileage, accident history, repair history)

[1338] Output: Vehicle information is logged to the device.

[1339] Step 2:

[1340] The device monitors the user's input behavior in real time and sends the data to the emotion engine. The emotion engine estimates the user's emotional information from factors such as input speed and error rate. For example, if the input speed is slow and there are many errors, it can be determined that the user is feeling stressed.

[1341] Input: User input behavior (e.g., typing speed, error rate)

[1342] Output: Emotional information (e.g., stress level)

[1343] Step 3:

[1344] The device sends the vehicle information and emotion information entered by the user to the server in JSON format.

[1345] Input: Vehicle information and emotion information

[1346] Output: JSON formatted data package

[1347] Step 4:

[1348] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as market price and past sales history related to a "2018 Toyota Camry."

[1349] Input: Received data (e.g. vehicle information)

[1350] Output: Relevant data collected

[1351] Step 5:

[1352] The server preprocesses the collected data, specifically by imputing missing values ​​and removing outliers. For example, missing mileage data is imputed with the mean value.

[1353] Input: Collected data (e.g. market price, sales history)

[1354] Output: Preprocessed clean data

[1355] Step 6:

[1356] The server uses a generative AI model based on the preprocessed data to predict the market value of a vehicle. For example, the generative AI model predicts the market value of a "2018 model vehicle" to be 2 million yen.

[1357] Input: Preprocessed data

[1358] Output: Predicted market value (e.g., $20,000)

[1359] Step 7:

[1360] The server customizes the presentation of the predicted market value information based on the user's emotional information, for example, selecting a visually easy-to-understand graphical interface if the user is feeling stressed.

[1361] Input: Predicted market value, sentiment information

[1362] Output: Customized presentation

[1363] Step 8:

[1364] The server sends the customized information to the terminal, which then displays the information on a user interface, for example, displaying a predicted market value of 2 million yen. This display is customized according to the user's emotional state.

[1365] Input: Customized Presentation

[1366] Output: Market value information displayed in the user interface

[1367] Step 9:

[1368] Users can provide feedback on the displayed market value information, which is sent to the server and used for the next model retraining.

[1369] Input: Feedback information

[1370] Output: Feedback stored in a database

[1371] It is through these process steps that the invention is embodied.

[1372] (Application example 2)

[1373] 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."

[1374] Conventional used car market value prediction systems predict market value based on information provided by the user, but because they do not take the user's emotional state into account, the presentation method is uniform, resulting in a low quality user experience.While it is necessary to provide appropriate information depending on whether the user is feeling stressed or relaxed, the lack of technology to achieve this is a problem.

[1375] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving vehicle information from a user, means for collecting relevant information from multiple databases based on the vehicle information, means for preprocessing the collected information, means for predicting market value using a machine learning model based on the preprocessed information, means for evaluating the emotional state of the user and customizing the method for presenting the market value based on the evaluation result, and means for providing the predicted market value to the user in a customized format. This makes it possible to provide appropriate information according to the emotional state of the user, thereby improving the quality of the user experience.

[1376] A "user" is an individual or entity that provides vehicle information to the system.

[1377] "Vehicle information" refers to information about vehicle details, including model, year, mileage, accident history, and repair history.

[1378] "Database" means an internal or external information source for collecting information related to user-provided vehicle information.

[1379] "Preprocessing" is the process of filling in missing information from the collected information and removing outliers.

[1380] A "machine learning model" is a system consisting of a learning algorithm for predicting market value using preprocessed information.

[1381] "Market Value" is the vehicle's estimated value in the current market.

[1382] The "emotional state" refers to the psychological state, such as stress or relaxation, that the user feels when inputting information.

[1383] "Evaluation" is the act of quantitatively measuring and judging the user's emotional state.

[1384] "Customization" refers to tailoring the way information is presented based on the user's emotional state.

[1385] "Offering" is the act of presenting the predicted market value to the user.

[1386] The system for realizing this invention has the following hardware and software configuration: First, a user inputs vehicle information using a smartphone. Next, the device transmits this information to a server, which simultaneously evaluates and digitizes the user's emotional state. Based on the received vehicle information and emotional state information, the server collects relevant information from multiple databases and performs preprocessing. Then, based on the preprocessed data, the server predicts the market value using a machine learning model. Finally, the server provides the user with the market value in a format customized based on the emotional state. This process is described in detail below.

[1387] Enter user information

[1388] The user inputs vehicle information (model, year, mileage, accident history, repair history, etc.) via smartphone. For example, the user inputs a 2018 self-driving car (mileage 50,000 km).

[1389] Recognition of emotional information

[1390] The device monitors the user's input behavior and interface usage in real time to obtain information about the user's emotions. Specifically, the emotion engine estimates the user's stress level and satisfaction level based on data such as input speed and error rate.

[1391] Data transmission

[1392] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format.

[1393] Data collection and preprocessing

[1394] The server collects data related to the vehicle information received in the previous step from multiple internal and external databases. For example, it retrieves past sales history and market price data for autonomous vehicles manufactured in 2018. Next, the server preprocesses the collected data, imputing missing values ​​with averages or estimated values ​​and removing outliers.

[1395] Model-based value prediction

[1396] The server uses machine learning models (linear regression models, deep learning models, etc.) based on the preprocessed data to calculate the market value of the vehicle. For example, the AI ​​model predicts that the market value of an autonomous vehicle manufactured in 2018 is 2 million yen.

[1397] Emotion-based customization

[1398] The server customizes the presentation of the predicted market value information based on the user's emotional state. For example, if the user is stressed, the server selects a more polite and easy-to-understand presentation, whereas if the user is relaxed, the server presents the information in a standard presentation.

[1399] Sending and viewing results

[1400] The server converts the market value information customized based on the emotion information into a data package and transmits it to the terminal, which interprets the data package and displays it on a user interface.

[1401] Feedback Processing

[1402] Users can provide feedback on the displayed market value. This feedback can be about their satisfaction with the system or whether the price is fair. The server stores the feedback provided by users in a database and uses it for the next retraining of the AI ​​model. This improves the accuracy of the model and enables more accurate predictions.

[1403] Examples and prompts

[1404] For example, if a user types into their smartphone that they want to sell a "2018 self-driving car (50,000 km)" and the emotion engine determines that the user is stressed based on their input speed and error rate, the system will provide an interface that explains the market value more clearly.If a prompt such as "Please tell me the value of a 2018 self-driving car. I need this information urgently, so please explain it as clearly as possible" is entered, the system will be able to provide the appropriate information.

[1405] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1406] Step 1:

[1407] The user uses a smartphone to input vehicle information (model, year, mileage, accident history, repair history, etc.). At this time, the user inputs the information through the UI, and after input is complete, the information is sent to the device. The input information is first saved on the user's device.

[1408] Step 2:

[1409] The device monitors the user's input behavior (input speed, error rate, etc.) in real time and obtains emotional information. An emotion engine then works to estimate stress levels and satisfaction levels. This evaluates whether the user is relaxed or stressed. This information is also saved as a data package.

[1410] Step 3:

[1411] The device sends the vehicle information and emotion information entered by the user to the server as a data package in JSON or XML format, which includes all the vehicle information and emotion evaluation entered by the user.

[1412] Step 4:

[1413] Based on the received vehicle information, the server collects relevant data from multiple internal and external databases, such as past sales history and market price data, using REST APIs and SQL queries. This information is temporarily stored in a data store.

[1414] Step 5:

[1415] The server preprocesses the collected data, completing missing values ​​with averages or estimated values ​​and removing outliers. The preprocessed data is then passed to the next machine learning model. For example, the Pandas library is used to cleanse the data.

[1416] Step 6:

[1417] The server inputs the preprocessed data into a machine learning model to predict market value. The model used can be, for example, a linear regression model or a deep learning model. The predicted market value obtained here is passed on to the next step. The model prediction is made using a library such as Scikit-learn.

[1418] Step 7:

[1419] The server customizes the presentation of the predicted market value information based on the user's emotional information. For example, if the server determines that the user is stressed, it selects an interface with detailed and thorough explanations, and if the user is relaxed, it selects a simplified interface.

[1420] Step 8:

[1421] The server converts the customized market value information into a data package and transmits it to the terminal, where the data package includes the market value prediction result along with the customized layout.

[1422] Step 9:

[1423] The terminal interprets the data package received from the server and displays it on a user interface, allowing the user to view the estimated market value of the autonomous vehicle in a customized format.

[1424] Step 10:

[1425] The user provides feedback on the displayed market value, for example, by inputting opinions on satisfaction and fairness of the price. This feedback is again transmitted to the server via the terminal.

[1426] Step 11:

[1427] The server stores the feedback provided by users in a database and uses it to retrain the AI ​​model in the future, thereby improving its accuracy.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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).

[1435] 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.

[1436] 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."

[1437] 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.

[1438] 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).

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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.

[1449] The following is further disclosed regarding the above embodiment.

[1450] (Claim 1)

[1451] means for receiving used car information from a user;

[1452] means for collecting relevant data from a plurality of databases based on the used car information;

[1453] means for pre-processing the collected data;

[1454] A method for predicting the market value of used cars using AI models based on pre-processed data;

[1455] a means for providing the predicted market value to a user;

[1456] A system including:

[1457] (Claim 2)

[1458] The system according to claim 1, wherein the used car information includes the vehicle model, year, mileage, accident history, and repair history.

[1459] (Claim 3)

[1460] The system of claim 1 , wherein the preprocessing means performs missing value imputation and outlier removal.

[1461] (Claim 4)

[1462] 2. The system of claim 1, wherein the AI ​​model is a regression analysis or deep learning model.

[1463] (Claim 5)

[1464] 10. The system of claim 1, further comprising means for storing the user-provided feedback for use in subsequent model retraining.

[1465] "Example 1"

[1466] (Claim 1)

[1467] means for receiving used car information from a user;

[1468] means for collecting relevant data from a plurality of databases based on the used car information;

[1469] means for pre-processing the collected data;

[1470] A means of predicting the market value of used cars using a generative AI model based on pre-processed data; and

[1471] a means for providing the predicted market value to a user;

[1472] means for receiving feedback from a user and retraining the generative AI model based on the feedback;

[1473] A system including:

[1474] (Claim 2)

[1475] The system according to claim 1, wherein the used car information includes the vehicle model, year, mileage, accident history, and repair history.

[1476] (Claim 3)

[1477] The system of claim 1 , wherein the preprocessing means performs missing value imputation and outlier removal.

[1478] "Application Example 1"

[1479] (Claim 1)

[1480] means for receiving used car information from a user;

[1481] means for collecting relevant data from a plurality of databases based on the used car information;

[1482] means for pre-processing the collected data;

[1483] A means of predicting the market value of used cars using a generative AI model based on pre-processed data; and

[1484] means for providing the predicted market value on a user interface;

[1485] a means for collecting user-provided feedback;

[1486] means for interfacing with an electronic payment instrument to effect real-time settlement of said market value;

[1487] A system including:

[1488] (Claim 2)

[1489] The system according to claim 1, wherein the used car information includes the vehicle model, year, mileage, accident history, and repair history.

[1490] (Claim 3)

[1491] The system of claim 1 , wherein the preprocessing means performs missing value imputation and outlier removal.

[1492] "Example 2: Combining Emotion Engines"

[1493] (Claim 1)

[1494] means for receiving vehicle information from a user;

[1495] means for collecting relevant data from a plurality of databases based on the vehicle information;

[1496] means for pre-processing the collected data;

[1497] A means of predicting vehicle value using a generative AI model based on pre-processed data; and

[1498] A means for monitoring a user's operation state in real time and acquiring emotion information;

[1499] a means for customizing the presentation of the predicted market value information based on the obtained sentiment information;

[1500] means for providing customized market value information to a user;

[1501] A system including:

[1502] (Claim 2)

[1503] 2. The system of claim 1, wherein the vehicle information includes vehicle model, year of manufacture, mileage, accident history, and repair history.

[1504] (Claim 3)

[1505] The system of claim 1 , wherein the preprocessing means performs missing value imputation and outlier removal.

[1506] "Application example 2 when combining emotion engines"

[1507] (Claim 1)

[1508] means for receiving vehicle information from a user;

[1509] means for collecting relevant information from a plurality of databases based on the vehicle information;

[1510] means for preprocessing the collected information;

[1511] A means for predicting market value using a machine learning model based on preprocessed information;

[1512] means for assessing the emotional state of the user and customizing the presentation of market value based on the assessment result;

[1513] means for providing the predicted market value to a user in a customized format;

[1514] A system including:

[1515] (Claim 2)

[1516] 2. The system of claim 1, wherein the vehicle information includes vehicle model, year, mileage, accident history, and repair history.

[1517] (Claim 3)

[1518] 2. The system according to claim 1, wherein the preprocessing means performs completion of missing information and removal of outliers. [Explanation of symbols]

[1519] 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. means for receiving used car information from a user; means for collecting relevant data from a plurality of databases based on the used car information; means for pre-processing the collected data; A method for predicting the market value of used cars using AI models based on pre-processed data; a means for providing the predicted market value to a user; A system including:

2. The system according to claim 1 , wherein the used car information includes the model, year, mileage, accident history, and repair history.

3. The system of claim 1 , wherein the preprocessing means performs missing value imputation and outlier removal.

4. The system of claim 1 , wherein the AI ​​model is a regression analysis or deep learning model.

5. The system of claim 1 , further comprising means for storing the user-provided feedback for use in subsequent model retraining.

Images