system

Abstract

Provide a system. [Solution] a means for collecting a large amount of data from a database; a means of standardizing the collected data; a means for analyzing the standardized data; A means for calculating value based on the analysis results; and means for presenting the calculated value to a user.

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] This is to solve the problem that the value assessment of various products, services, and location information often relies on subjective and fragmented information. In particular, the lack of unified data from various sources makes it difficult to calculate consistent value and achieve fair and impartial assessment. The present invention aims to solve these problems and provide statistical and objective value assessment based on a wider range of information. [Means for solving the problem]

[0005] The system of the present invention includes a means for collecting a large amount of data from a database, a means for standardizing the collected data, a means for analyzing the standardized data, a means for calculating a value based on the analysis results, and a means for presenting the calculated value to a user. It also includes a means for removing inaccuracies in the collected data. Furthermore, it also includes a means for improving the accuracy and reliability of the system by collecting feedback from users and using that feedback to improve future data analysis. This provides a system that achieves fair and impartial value assessment based on a variety of information.

[0006] A "database" is a structured collection of information for centralized management and storage of data. This information is organized so that it can be later efficiently retrieved, updated, and managed.

[0007] "Data collection methods" are methods or systems for obtaining data from various sources, including web scraping, API access, user input, etc.

[0008] "Standardization" is the process of converting data provided in different formats and units into a consistent format, which makes data analysis easier and ensures data compatibility.

[0009] "Data analysis methods" are methods that apply statistical techniques and machine learning algorithms to collected data to extract useful information and patterns.

[0010] A "value calculation method" is a method for calculating the value of a particular object based on analyzed data, including the use of statistical models and metrics.

[0011] A "presentation vehicle" is a method or system for visually or documentarily displaying the calculated value to a user, such as a graph, chart, or report.

[0012] "Inaccuracy removal measures" are methods for identifying incomplete, erroneous, or invalid data and removing it from the system, thereby improving the accuracy and reliability of the data.

[0013] "User feedback" refers to information such as evaluations, opinions, and impressions provided by users regarding the system. Based on this information, the system is improved and adjusted.

[0014] "Data analysis improvement measures" are measures to improve the system's data analysis algorithms and methods based on collected feedback, etc. This will improve the accuracy of future analysis results. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Specifically, this system collects data, standardizes it, analyzes it, calculates its value, and presents the results. The following scenario will be described as an example of how this system operates.

[0037] Example: Used car valuation system

[0038] Data collection

[0039] Server: Uses APIs to collect data such as vehicle year, mileage, model, manufacturer, price, and user ratings from multiple websites that provide used car information. It also obtains information from open and proprietary databases.

[0040] User: Enters detailed information about the used car he owns (e.g., specific optional equipment and maintenance history) through his own device, allowing for more specific data to be collected.

[0041] Data Standardization

[0042] Server: The collected data comes from a variety of sources and is not in a uniform format. The server converts this data into a uniform format. For example, it standardizes the currency units of price information, standardizes rating scales, and aligns different field names and data types into a consistent format.

[0043] Data analysis

[0044] Server: Feeds the standardized data into analytics tools, which use statistical methods (e.g., mean, median, standard deviation) to calculate baseline characteristics. Additionally, machine learning algorithms (e.g., linear regression and clustering) are used to identify patterns and trends. For example, estimating the rate of depreciation for a vehicle of a particular model year after a certain number of miles.

[0045] Calculating value

[0046] Server: Based on the analysis results, the current market value of each used vehicle is calculated, taking into account the average price of the same model and year, the impact of specific conditions (such as mileage and optional equipment), market trends, and the balance of supply and demand.

[0047] Presentation of results

[0048] Server: The calculated value is formatted in a user-friendly format. The formatted data is sent to the user's device.

[0049] Device: The results are displayed on the user's device, using visual graphs and charts to clearly explain how each factor affects the value of a used car, such as a line graph showing how value varies by age and mileage.

[0050] Through this series of processes, users can objectively understand how much their used car is worth in the current market and obtain a fair and impartial valuation. This system can also be applied to valuing various products and services, and can provide highly accurate results by utilizing a wide range of data.

[0051] The processing flow will be explained below.

[0052] Step 1: Data collection

[0053] Server: Using APIs, the server obtains vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. It also uses scraping technology to extract the necessary information from web pages.

[0054] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0055] Step 2: Standardize the data

[0056] Server: The collected data exists in various formats, so it is first converted into a unified format. For example, the currency units for price information are unified and rating scales are aligned to a consistent standard.

[0057] Server: Additionally, it aggregates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0058] Step 3: Cleaning the data

[0059] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0060] Step 4: Analyze the data

[0061] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0062] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[0063] Step 5: Calculate value

[0064] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0065] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0066] Step 6: Generate and format the results

[0067] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0068] Step 7: Send and view results

[0069] Server: Sends the formatted data to the user's device.

[0070] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0071] Step 8: User Interaction

[0072] User: Can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) into the system.

[0073] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0074] Example 1

[0075] 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."

[0076] In conventional value assessment systems, data collection sources are limited, making it difficult to integrate and utilize information from diverse data sources. Furthermore, data standardization and analysis lacked standardized formats and insufficient application of machine learning algorithms, resulting in problems with reduced assessment accuracy. Furthermore, the results were not presented in a user-friendly manner, making it difficult for users to understand the information obtained.

[0077] 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.

[0078] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating a value based on the analysis results, means for presenting the calculated value to a user, means for collecting information from online sources and users, means for converting the data into a unified format, means for analyzing the data using a machine learning algorithm, and means for displaying the results in a visual format. This enables integrated analysis of information collected from various data sources, and improves analytical accuracy through the application of a unified format and machine learning. Furthermore, displaying the results in a user-friendly format allows users to easily understand and use the information.

[0079] A "database" is a system for systematically storing specific information and efficiently accessing and managing it.

[0080] "Data collection" is the process of obtaining necessary information from various sources.

[0081] "Standardization" is the process of unifying the format and units of collected data and managing the data in a consistent manner.

[0082] "Data analytics" is the process of analyzing collected and standardized data using statistical methods and machine learning algorithms to find useful information and patterns.

[0083] "Pricing" is the process of calculating the current market value of an object based on the results of data analysis.

[0084] "Presenting to the user" is the process of providing the calculated value to the user in a visually easy-to-understand format.

[0085] An "online source" is a data source accessible via the Internet.

[0086] "Information collection methods" are the technical means and identification methods used to obtain the required data from various sources.

[0087] "Format conversion" is the process of converting data of different formats and units into a unified format.

[0088] A "machine learning algorithm" is a computational model that learns from large amounts of data and automatically finds patterns and features.

[0089] A "visual format" is a format that presents data or information in an easy-to-read visual way, such as a graph or chart.

[0090] The system for implementing this invention collects a large amount of data from a database, standardizes it into a unified format, calculates value through analysis using a machine learning algorithm, and presents it to the user. A specific implementation method of this system is described below.

[0091] Data collection

[0092] Server: The server collects data from multiple websites that provide used car information. To do this, the server calls the API of each website to obtain data such as the vehicle's year, mileage, model, manufacturer, price, and user ratings. For example, it obtains JSON-formatted data from a website that provides data on a specific vehicle, parses it, and stores it in a local database. It is effective to use a relational database such as MySQL (registered trademark) or PostgreSQL as the database.

[0093] User: The user uses their own device to enter details about their used car, such as the model year, mileage, specific options, and maintenance history, through a dedicated application or web form. The data entered by the user is sent to the server in real time and integrated with the collected data.

[0094] Data Standardization

[0095] Server: The server handles the process of unifying the format and units of the collected data. For example, if price information is stored in different currencies, it converts it all to yen. It also applies specific mapping rules to unify different field names for data retrieved from multiple data sources. Specifically, it uses the Python pandas library to create a data frame and rename columns based on the specified mapping.

[0096] Data analysis

[0097] Server: To analyze the standardized data, the server uses machine learning algorithms. For example, it uses Python's scikit-learn library to perform linear regression models and clustering. The analysis method not only calculates basic statistics of the data (mean, median, standard deviation), but also evaluates the impact of different parameters on vehicle value. Linear regression can be used to model the impact of model year and mileage on price.

[0098] Calculating value

[0099] Server: Based on the analysis results, the server calculates the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific conditions (e.g., mileage, optional equipment). The server also adjusts the value to take real-time market trends into account. For example, it performs trend analysis on historical data sets to take into account price fluctuations over a certain period of time.

[0100] Presentation of results

[0101] Server: The calculated value is formatted in a user-friendly format and sent to the user's device. Visual graphs and charts are generated to clearly show how each factor affects the value of a used car. For example, the JSON formatted data can be interpreted on the client side and a visualization library such as Chart.js can be used to draw line graphs and bar charts.

[0102] Terminal: The terminal analyzes the received data and displays it to the user in an easy-to-understand format. A dedicated interface allows the user to intuitively understand the valuation results. For example, a line graph showing the fluctuations in value based on model year and mileage can be displayed, allowing the user to visually see the impact of each factor on the price.

[0103] Examples of concrete examples and prompts

[0104] For example, consider a user wanting to value their 2015 vehicle. Using a smartphone application, the user inputs information such as the model year, mileage, optional equipment, and maintenance history. This information is then aggregated and analyzed on a server along with collected online data. The analysis results are then sent to the user's device and presented in a visual format.

[0105] Example prompt sentence:

[0106] "Write a program to assess the value of used cars. Your program should collect data from multiple online sources, convert it into a unified format, and then use machine learning algorithms to analyze it and calculate a final market value. The system should also collect specific vehicle information from the user (year, mileage, model, maintenance history, etc.). The results of the analysis should be displayed visually."

[0107] According to the present invention, highly accurate value assessment using a wide range of diverse data is possible, and highly reliable assessment information can be provided to users.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1: Data collection

[0110] Input: API endpoint of online source, user-entered used car details (year, mileage, model, make, price, user ratings, etc.).

[0111] How it works: The server calls each website's API to retrieve the required vehicle data from online sources. For example, it uses the requests library to send a GET request and parses the JSON data received as a response. The vehicle information entered by the user through a dedicated application is sent to the server via HTTPS and stored in a database.

[0112] Output: Unified dataset, user input data.

[0113] Step 2: Standardize the data

[0114] Input: Integrated dataset, user input data.

[0115] Specific operation: If the format or units of collected data are not standardized, the server performs processing to standardize them. For example, it creates a data frame using the pandas library, converts all price information to yen, and applies mapping rules to standardize field names. It also standardizes different data types (e.g., converting strings to numbers).

[0116] Output: A standardized dataset.

[0117] Step 3: Analyze the data

[0118] Input: Standardized dataset.

[0119] What it does: The server feeds the standardized data to analytics tools. It uses Python's pandas library to calculate basic statistics (mean, median, standard deviation). It then uses the scikit-learn library to train machine learning models. For example, it uses a linear regression model to analyze the impact of vehicle age and mileage on price, and a clustering algorithm to group similar vehicles.

[0120] Output: Analysis results, machine learning model.

[0121] Step 4: Calculate value

[0122] Input: Analysis results, machine learning model.

[0123] How it works: The server uses the analysis results to calculate the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific factors (e.g., mileage and optional equipment). It also monitors market trends in real time and makes adjustments as needed. Python code is used to input new data into the predictive model and calculate prices.

[0124] Output: Final market value.

[0125] Step 5: Presenting the results

[0126] Input: Final market value.

[0127] What it does: The server formats the results in a user-friendly format and sends them to the user's device. The JSON formatted data is interpreted on the client side and visualized using a charting library (e.g. Chart.js, D3.js). The terminal application generates detailed graphs and charts for each factor to display the results to the user in an easy-to-understand manner.

[0128] Output: Visualized evaluation results.

[0129] This series of processes allows users to know the accurate market value of their used car in real time.

[0130] (Application example 1)

[0131] 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."

[0132] Conventional product price evaluation systems require users to perform multiple manual operations to obtain product information, making it difficult to provide real-time evaluations. Furthermore, the information obtained is often inaccurate, forcing users to rely on unreliable price information. As a result, consumers are unable to obtain fair and immediate price evaluations, hindering their purchasing decisions.

[0133] 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.

[0134] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for presenting the calculated value to the user, means for scanning product information in real time, means for analyzing the scanned information and calculating the value, and means for visually displaying the calculated value, thereby enabling users to instantly obtain reliable price information in the store and make fair and appropriate purchasing decisions.

[0135] A "database" is a system for managing and operating large amounts of electronically stored data.

[0136] "Means for collecting data" refers to the function for obtaining necessary information from external data sources.

[0137] "Means for standardizing data" refers to the function of converting collected data into a unified format and scale.

[0138] "Means of analyzing data" refers to functions that use statistical methods and machine learning algorithms to find patterns and trends in data.

[0139] "Means for calculating value" refers to a function for evaluating and calculating the market value of an object based on analyzed data.

[0140] The "means for presenting value to the user" is a function for displaying the calculated market value in a format that is easy for the user to understand.

[0141] "Means for scanning product information in real time" is a function that allows a user to instantly obtain information on an object as digital data by taking a picture of the object with a camera or the like.

[0142] "Means for analyzing scanned information and calculating value" refers to a function for analyzing and evaluating product value based on product data acquired in real time.

[0143] "Visual display means" refers to a function for providing analysis results and values ​​to users in a visual format such as a graph or chart.

[0144] The system for implementing this invention includes specific hardware and software components for data collection, standardization, analysis, value calculation, and result presentation. Specifically, it is a system that allows users to evaluate products in physical stores in real time using smart glasses and a smartphone. An example of its operation is described below.

[0145] Hardware Configuration

[0146] Smart glasses: Contains a camera for scanning product information and a display that visually displays the results to the user.

[0147] Smartphone: A device that works in conjunction with smart glasses, communicates with the server, and processes data.

[0148] Server: High-performance computing resources for data collection, normalization, analysis, and value calculation.

[0149] Software Configuration

[0150] API: An interface for retrieving product information from a database or external data source.

[0151] Data standardization tools: Software that converts collected data into a uniform format.

[0152] Analysis tools: Software that uses machine learning libraries such as TENSORFLOW® and Scikit-learn to analyze data and detect patterns.

[0153] User Interface: Software that generates graphs and charts for display on smart glasses and smartphones.

[0154] Program processing explanation

[0155] 1. Data Collection

[0156] The server uses APIs to collect product information from online marketplaces and specialty sites, including product names, prices, and ratings, as well as inventory data and pricing information from physical stores.

[0157] 2. Data Standardization

[0158] The server standardizes the collected data and converts it into a unified format, ensuring uniform currency units for pricing information and consistent rating scales.

[0159] 3. Data Analysis

[0160] The server analyzes the standardized data and uses statistical methods and machine learning algorithms to find patterns and trends, such as how certain characteristics affect the value of a product.

[0161] 4. Value calculation

[0162] The server calculates the market value of the product based on the analysis results, taking into account the average price of the same category and the influence of specific conditions (e.g., year of manufacture and features).

[0163] 5. Presentation of results

[0164] The analysis results from the server are sent back to the smart glasses via the smartphone, which overlay the results on the user's field of vision, providing detailed information in real time. Visual graphs and charts are also displayed, helping users understand how the product's value was calculated.

[0165] Specific examples

[0166] A user puts on smart glasses, walks through a store, and directs their gaze toward a particular product. The smart glasses' camera scans the product and recognizes its barcode or QR code. The scanned data is then sent via Bluetooth to a smartphone, which then communicates with a server. The server quickly calculates the product's value based on the collected and standardized data, and the result is sent back to the smart glasses via the smartphone. The user can then make the necessary purchasing decisions while looking at the information displayed in their field of vision.

[0167] Generative AI model prompt example

[0168] "This product is a new model manufactured in 2023. The market price is approximately 30,000 yen, but please calculate the value taking into account specific features (water resistance, battery life, etc.)."

[0169] As described above, the present invention allows for the instant acquisition of highly reliable price information in a store, thereby supporting fair and appropriate purchasing decisions.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] A user uses smart glasses to scan an item. The input is the item's barcode or QR code, and the output is digital data to send the product data to a smartphone. The camera in the smart glasses scans the item and sends the data to the smartphone via Bluetooth.

[0173] Step 2:

[0174] The smartphone receives the scanned product data and sends it to the server. The input is the product information that received the data, and the output is the data sent to the server. The smartphone sends the data to the server via the Internet.

[0175] Step 3:

[0176] The server uses APIs to collect additional product information from various databases. The input is the scanned product data, and the output is data containing detailed product information. The server makes API calls to obtain information such as product name, price, and ratings.

[0177] Step 4:

[0178] The server standardizes the collected data. The input is product information collected in various formats, and the output is data in a unified format. The server converts the data's currency units and rating scales into a consistent format, and standardizes the data's field names and data types.

[0179] Step 5:

[0180] The server analyzes the standardized data. The input is the standardized product information, and the output is data containing the analysis results. The server uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to perform statistical analysis and pattern detection.

[0181] Step 6:

[0182] The server calculates the market value of the product based on the analysis results. The input is the analyzed data, and the output is data containing the product's current market value. The server uses statistical methods to evaluate the value, taking into account the average price in the same category and the influence of specific conditions.

[0183] Step 7:

[0184] The server formats the calculated market value for the user interface. The input is the market value data of the product, and the output is the formatted data in a format that is easy for the user to understand. The server generates graphs and charts and formats the data in a visually easy-to-understand format.

[0185] Step 8:

[0186] The smartphone transmits the data received from the server to the smart glasses. The input is the formatted product value data, and the output is data transmission to the smart glasses. The smartphone transmits the data to the smart glasses via Bluetooth or other communication means.

[0187] Step 9:

[0188] The smart glasses visually display the received data to the user. The input is formatted product value data, and the output is information overlaid on the user's field of view. The smart glasses display market value, graphs, charts, and other information on the display, allowing the user to make purchasing decisions.

[0189] Through the above steps, users can obtain product information in real time within a physical store and make purchasing decisions based on fair and reliable price information.

[0190] 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.

[0191] A system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Furthermore, by combining it with an emotion engine that recognizes user emotions, the accuracy and usefulness of user feedback can be improved. Specifically, this system performs data collection, standardization, analysis, value calculation, result presentation, and emotion analysis. The following scenario will be described as an example of how this system operates.

[0192] Example: Used car valuation system

[0193] Data collection

[0194] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[0195] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0196] Data Standardization

[0197] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[0198] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0199] Cleaning the data

[0200] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0201] Data analysis

[0202] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0203] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[0204] Calculating value

[0205] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0206] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0207] Generating and formatting results

[0208] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0209] Sending and displaying results

[0210] Server: Sends the formatted data to the user's device.

[0211] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0212] Introducing the Emotion Engine

[0213] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[0214] Server: Analyzed emotional information is stored in a database to improve the accuracy and usefulness of user feedback.

[0215] Emotion-Based Adjustment

[0216] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[0217] User Interaction

[0218] User: The user can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) to the system. Based on the emotional information analyzed by the emotion engine, appropriate feedback is requested.

[0219] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0220] Through this series of processes, users can not only objectively understand how much their used car is worth in the current market, but also obtain a more accurate value assessment by taking into account the emotional information in the feedback.

[0221] The processing flow will be explained below.

[0222] Step 1: Data collection

[0223] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[0224] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0225] Step 2: Standardize the data

[0226] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[0227] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0228] Step 3: Cleaning the data

[0229] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0230] Step 4: Analyze the data

[0231] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0232] Server: Uses machine learning algorithms to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation due to a particular model year and mileage.

[0233] Step 5: Calculate value

[0234] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0235] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0236] Step 6: Generate and format the results

[0237] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0238] Step 7: Send and view results

[0239] Server: Sends the formatted data to the user's device.

[0240] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0241] Step 8: Implementing the Emotion Engine

[0242] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[0243] Server: Stores the analyzed emotional information in a database to improve the accuracy and usefulness of feedback.

[0244] Step 9: Emotional Adjustment

[0245] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[0246] Step 10: User Interaction

[0247] User: Review the information provided and can enter feedback or additional information into the system (e.g., further vehicle details or comments) based on the emotional information analyzed by the emotion engine.

[0248] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0249] Example 2

[0250] 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."

[0251] In conventional data analysis systems, the inaccuracy and incompleteness of collected data affects the analysis results, making it difficult to perform highly accurate value assessments. Furthermore, user feedback was not properly collected, making further analysis and adjustments based on emotional information difficult. This made improving the user experience a challenge.

[0252] 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.

[0253] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for cleaning the standardized data, means for analyzing the cleaned data, means for calculating value based on the analysis results, means for presenting the calculated value to the user, means for analyzing the user's emotions, and means for adjusting the value calculation process and presentation content based on the analyzed emotional information. This makes it possible to improve the accuracy of the collected data and to evaluate value taking user emotional information into consideration.

[0254] A "database" is a system for efficiently storing and managing a large amount of data.

[0255] "Collection" is the process of gathering the necessary data from multiple sources.

[0256] "Standardization" is the process of converting data that exists in different formats into a unified format.

[0257] "Cleaning" is the process of detecting and removing inaccurate or incomplete data.

[0258] "Analysis" is the process of analyzing data and extracting valuable information and patterns.

[0259] "Value calculation" is the process of quantifying the value of data based on collected data and analysis results.

[0260] "Presentation" is the process of displaying calculated values ​​and analytical results in a user-friendly format.

[0261] "Sentiment analysis" is the process of recognizing and analyzing user emotions based on user feedback and data.

[0262] "Tuning" is the process of improving a process or display based on the results of analysis or calculations.

[0263] A system for implementing this invention calculates the market value of, for example, a used car based on information provided by users and data on the Internet. This system includes specific hardware and software components, enabling improved accuracy of collected data and value assessment that takes user emotion information into account.

[0264] Hardware and Software Configuration

[0265] Server: Retrieves required information from multiple websites and databases using APIs, scrapes information from web pages using Python's Beautiful Soup and Scrapy, standardizes and cleans data using Python's Pandas and Numpy, and performs data analysis using Scikit-Learn and TensorFlow.

[0266] Terminal: Provides an interface for users to input information. This interface includes a form for users to enter details about their used car. The information entered is sent to a database and analyzed by the server.

[0267] Emotion Engine: Analyzes emotions from user feedback using NLP libraries (e.g., NLTK and spaCy) and TensorFlow, and stores the user's emotional information in a database for further tuning and improving the data analysis algorithm.

[0268] Specific examples

[0269] As an example of how this system works, we will explain a used car value assessment system. The server obtains detailed vehicle information (year, mileage, model, manufacturer, price, user ratings, etc.) via API from, for example, "used car information site A" or "used car transaction database B." Python's Beautiful Soup and Scrapy are used to automatically extract the necessary information from web pages.

[0270] Users use their own devices to open a dedicated input form and enter detailed information about their used car (e.g., specific optional equipment and maintenance history). This information is sent to the server and stored in a database.

[0271] The server standardizes and cleans the collected data using Pandas and Numpy to remove inaccurate or incomplete data, then performs data analysis using Scikit-Learn and TensorFlow to extract specific patterns and trends. Based on the analysis results, the server calculates the market value of each used car in an unbiased and objective manner.

[0272] The server then formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, using Matplotlib or Plotly to generate graphs and charts, and converts them to JSON format.

[0273] The server sends this formatted data to the user's device, which then uses JavaScript (registered trademark) D3.js to draw a line graph showing the fluctuations in value based on model year and mileage, as well as a histogram of market prices.

[0274] The emotion engine analyzes text and voice data to recognize user emotions (e.g., satisfaction, dissatisfaction, excitement, etc.). This emotion information is also stored in the database and used to improve the accuracy and usefulness of user feedback.

[0275] Prompt Sentence Examples

[0276] "Evaluate the market value of a used car based on its age and mileage. Include any specific optional equipment and maintenance history in your evaluation."

[0277] "Reassess the value of used cars taking into account user emotional feedback and suggest improvements."

[0278] This system not only allows users to objectively understand how much their used car is worth in the current market, but also allows them to receive a more accurate value assessment based on emotional information.

[0279] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0280] Step 1:

[0281] Data collection

[0282] The server uses APIs to obtain detailed vehicle information from multiple websites and databases that provide used car information. Specifically, it sends requests to the APIs of each website to obtain data including model year, mileage, model, manufacturer, price, user ratings, etc. The input is the API request parameters and search conditions, and the output is vehicle information data in JSON format.

[0283] The server uses Python's Beautiful Soup or Scrapy to scrape information from web pages. It parses the HTML of the web page and extracts the required information. The input is the web page's URL or HTML source, and the output is the extracted text data or table data.

[0284] A user opens a dedicated input form on their device and enters the details of their used car. The input is the vehicle information (e.g., year, model, mileage, etc.) that the user fills in the form, and the output is structured data (e.g., JSON format) received by the server.

[0285] Step 2:

[0286] Data Standardization

[0287] The server converts the collected data from various formats into a single unified format using the Pandas library. Specifically, it standardizes the currency units of the pricing information (e.g., converting everything to USD) and converts the rating scale to a consistent standard. The input is vehicle data in different formats, and the output is a data frame in a unified format.

[0288] The server aggregates identical information fields (e.g., year and model) from different data sources to create a consistent dataset. The input is multiple data frames of vehicle data from different sources, and the output is an aggregated data frame.

[0289] Step 3:

[0290] Cleaning the data

[0291] The server detects and filters out inaccurate or incomplete data from the collected data. Specifically, it uses Pandas to detect NAN values ​​and outliers and remove or correct them. The input is a standardized data frame, and the output is a clean dataset with inaccurate data removed.

[0292] Step 4:

[0293] Data analysis

[0294] The server analyzes the standardized and cleaned data, first calculating basic statistics (mean, median, standard deviation, etc.) using Scikit-Learn or StatsModels. The input is the clean dataset, and the output is the statistical analysis results.

[0295] The server uses machine learning algorithms to extract patterns and trends, applying linear regression or random forests to analyze the relationship between specific model years and mileage. The input is the clean dataset, and the output is the predictions of the machine learning model.

[0296] Step 5:

[0297] Calculating value

[0298] The server calculates the current market value of the used car based on the analysis results. Specifically, it evaluates the value based on the average and median market prices of vehicles of the same age and condition. The inputs are the predictions of the machine learning model and market data, and the output is the calculated market value.

[0299] The server adjusts the final value, taking into account market trends and supply and demand balances. The inputs are the calculated market value and additional economic indicator data, and the output is the adjusted market value.

[0300] Step 6:

[0301] Generating and formatting results

[0302] The server formats the calculated value in a user-friendly format. It uses Matplotlib or Plotly to generate graphs and charts and converts them to JSON format. The input is the adjusted market value, and the output is the formatted data (JSON format).

[0303] Step 7:

[0304] Sending and displaying results

[0305] The server sends the formatted data to the user's device. The input is the formatted data (JSON format) and the output is the sent response.

[0306] The terminal analyzes the received data and displays it to the user. Using JavaScript D3.js, it draws line graphs showing the fluctuations in value depending on the model year and mileage, as well as histograms of market prices. The input is the received data (in JSON format), and the output is the visualized graph or chart.

[0307] Step 8:

[0308] Introducing the Emotion Engine

[0309] The server uses NLP libraries and TensorFlow to analyze emotions from the feedback provided by the user. Specifically, it processes text and voice data and recognizes emotions such as satisfaction, dissatisfaction, and excitement. The input is the user's feedback data, and the output is the analyzed emotional information.

[0310] The server stores the analyzed emotion information in a database. The input is the analyzed emotion information, and the output is a stored database entry.

[0311] Step 9:

[0312] Emotion-Based Adjustment

[0313] The server adjusts the value calculation process and presentation content based on the user's emotional information. It also adjusts the algorithm parameters based on dissatisfaction information about specific factors. The inputs are the emotional information and the parameters of the value assessment process, and the output is the adjusted value calculation result.

[0314] Step 10:

[0315] User Interaction

[0316] The user reviews the information provided and provides feedback and additional information to the system, for example, providing further vehicle details or comments. The input is the user's feedback and additional information, and the output is the data sent to the server.

[0317] The server collects user feedback and stores it in a database, which is used to adjust and improve future data analysis algorithms. The input is the user feedback data, and the output is the stored database entry.

[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 value assessment systems only standardize and analyze collected data, making it difficult to appropriately reflect user feedback. Furthermore, because they do not take user emotions or satisfaction into account, it is difficult to improve the user experience or the quality of feedback. Therefore, there is a need to provide a more accurate and user-friendly value assessment system that recognizes user emotions and reflects them in feedback.

[0321] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0322] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating value based on the analysis results, means for analyzing user emotions, and means for adjusting feedback based on the analyzed emotions, thereby enabling more accurate value assessment that takes user emotions into consideration and improving user satisfaction.

[0323] A "database" is a system for systematically managing, storing, and retrieving large amounts of data.

[0324] "Collection methods" refers to the methods and techniques used to obtain data from various sources.

[0325] "Standardization measures" are methods for converting data that exists in different formats and units into a unified format.

[0326] "Means of analysis" refers to a method of analyzing collected and standardized data using statistical and machine learning techniques.

[0327] "Means of calculating value" refers to the method of calculating the market value of goods or services based on the results of the analysis.

[0328] "Means for presenting to the user" is a method for displaying the calculated value in a user-friendly format.

[0329] "Means for analyzing emotions" refers to technology that uses text data and voice data from users to recognize their emotional state.

[0330] The "means for adjusting feedback" is a method for adjusting the content of the user's feedback based on the analyzed emotional information.

[0331] "Inaccuracy removal measures" are methods for identifying and removing erroneous or incomplete information from collected data.

[0332] "Means for collecting feedback" refers to methods for collecting opinions and evaluation information from users.

[0333] "Means for storing feedback in a database" refers to a method for storing collected feedback information in a database.

[0334] "Means for improving analysis" are techniques that use stored feedback information to improve data analysis algorithms and methods.

[0335] The system for implementing this invention collects a large amount of data from a database, standardizes and analyzes it, calculates a value based on the results, and presents it to the user. Furthermore, it analyzes the user's emotions and adjusts feedback based on the results, thereby providing a more accurate and user-friendly value assessment.

[0336] The main components of the system include a server, a terminal, and a user.

[0337] server

[0338] Data collection method: The server collects a large amount of data from the database using APIs (Application Programming Interfaces) and other methods. Specifically, product information and market value data is obtained from multiple websites and databases. In some cases, scraping technology is used to extract information.

[0339] Data standardization measures: As the collected data exists in various formats, the currency units and evaluation scales are standardized. This is a process to maintain data consistency.

[0340] Data analysis methods: Standardized data is analyzed using statistical methods and machine learning algorithms to calculate statistical values ​​such as the mean, median, and standard deviation, and to identify specific trends and patterns.

[0341] Value calculation method: Based on the analysis results, we calculate the market value of each product in a fair and objective manner, using the average or median market price of products of the same age and condition.

[0342] Result presentation method: Generates data to present the calculated value to the user and sends it to the terminal in JSON format, graphs, charts, etc.

[0343] Sentiment analysis means: An emotion engine is used to analyze user feedback text and voice data to recognize the user's emotional state (e.g., satisfied, dissatisfied, excited).

[0344] Feedback adjustment: Adjust the feedback content and value calculation process based on the analyzed emotional information. For example, adjust the value for a specific factor that the user expressed dissatisfaction with or provide additional information.

[0345] Terminal

[0346] Data display means: Receives data sent from the server and displays the results using a user-friendly UI, such as graphs showing product age and price fluctuations, or recommendations based on user feedback.

[0347] User

[0348] Providing feedback: Users can input detailed product information and feedback into the system to improve the accuracy of data collection. Furthermore, the emotion engine analyzes the emotional information and provides appropriate feedback.

[0349] Specific examples

[0350] For example, if a user provides feedback such as "This book has great content and was reasonably priced," the server sends this text data to a sentiment analysis engine to analyze positive sentiment. This analysis information is reflected in the next value calculation process as an upward correction to the value.

[0351] Example prompt sentence:

[0352] This book is excellent and was reasonably priced.

[0353] In this way, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

[0354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0355] Step 1:

[0356] The server collects product information and market value data from the database using APIs. The collected data is obtained from multiple websites and databases, sometimes using scraping techniques. The input is from multiple data sources, and the output is data in different formats.

[0357] Step 2:

[0358] The server normalizes the collected data, specifically by standardizing the currency unit (e.g., converting all prices to USD) and the rating scale. The input is the raw data collected in step 1, and the output is the normalized data converted into a consistent format.

[0359] Step 3:

[0360] The server analyzes the standardized data using statistical methods and machine learning algorithms to calculate statistics such as the mean, median, and standard deviation. It also extracts specific trends and patterns. The input is the standardized data, and the output is the statistical analysis results.

[0361] Step 4:

[0362] The server calculates the value based on the analysis results. It calculates the market value of each item in a fair and objective manner, and calculates the value using the average or median market price of items of the same age and condition. The input is the analysis result from Step 3, and the output is the calculated market value.

[0363] Step 5:

[0364] The server formats the data to present the calculated value to the user. The generated value data is sent to the terminal in a UI format that is easy for the user to understand (e.g., JSON format, graphs, charts). The input is market value data, and the output is the formatted data.

[0365] Step 6:

[0366] The terminal receives the data sent from the server and displays the results in a user-friendly UI. The displayed content includes graphs showing the model year and price fluctuations of products, as well as recommendations based on user feedback. The input is the formatted data, and the output is the results displayed in the UI.

[0367] Step 7:

[0368] Users input detailed product information and feedback into the system, for example, by providing impressions and ratings in text format, which improves the accuracy of data collection. The input is the user-provided feedback, and the output is the feedback data sent to the server.

[0369] Step 8:

[0370] The server sends the user's feedback text or voice data to the emotion analysis engine, which analyzes the user's emotional state (e.g., satisfied, dissatisfied, excited). The input is text or voice data, and the output is the analyzed emotional information.

[0371] Step 9:

[0372] The server adjusts the feedback content and value calculation process based on the analyzed emotion information. Specifically, it adjusts the value for specific factors that the user expressed dissatisfaction with and presents additional information. The input is emotion analysis information, and the output is the adjusted value data and additional information.

[0373] Through the above processing steps, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

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

[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] The system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Specifically, this system collects data, standardizes it, analyzes it, calculates its value, and presents the results. The following scenario will be described as an example of how this system operates.

[0391] Example: Used car valuation system

[0392] Data collection

[0393] Server: Uses APIs to collect data such as vehicle year, mileage, model, manufacturer, price, and user ratings from multiple websites that provide used car information. It also obtains information from open and proprietary databases.

[0394] User: Enters detailed information about the used car he owns (e.g., specific optional equipment and maintenance history) through his own device, allowing for more specific data to be collected.

[0395] Data Standardization

[0396] Server: The collected data comes from a variety of sources and is not in a uniform format. The server converts this data into a uniform format. For example, it standardizes the currency units of price information, standardizes rating scales, and aligns different field names and data types into a consistent format.

[0397] Data analysis

[0398] Server: Feeds the standardized data into analytics tools, which use statistical methods (e.g., mean, median, standard deviation) to calculate baseline characteristics. Additionally, machine learning algorithms (e.g., linear regression and clustering) are used to identify patterns and trends. For example, estimating the rate of depreciation for a vehicle of a particular model year after a certain number of miles.

[0399] Calculating value

[0400] Server: Based on the analysis results, the current market value of each used vehicle is calculated, taking into account the average price of the same model and year, the impact of specific conditions (such as mileage and optional equipment), market trends, and the balance of supply and demand.

[0401] Presentation of results

[0402] Server: The calculated value is formatted in a user-friendly format. The formatted data is sent to the user's device.

[0403] Device: The results are displayed on the user's device, using visual graphs and charts to clearly explain how each factor affects the value of a used car, such as a line graph showing how value varies by age and mileage.

[0404] Through this series of processes, users can objectively understand how much their used car is worth in the current market and obtain a fair and impartial valuation. This system can also be applied to valuing various products and services, and can provide highly accurate results by utilizing a wide range of data.

[0405] The processing flow will be explained below.

[0406] Step 1: Data collection

[0407] Server: Using APIs, the server obtains vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. It also uses scraping technology to extract the necessary information from web pages.

[0408] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0409] Step 2: Standardize the data

[0410] Server: The collected data exists in various formats, so it is first converted into a unified format. For example, the currency units for price information are unified and rating scales are aligned to a consistent standard.

[0411] Server: Additionally, it aggregates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0412] Step 3: Cleaning the data

[0413] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0414] Step 4: Analyze the data

[0415] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0416] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[0417] Step 5: Calculate value

[0418] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0419] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0420] Step 6: Generate and format the results

[0421] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0422] Step 7: Send and view results

[0423] Server: Sends the formatted data to the user's device.

[0424] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0425] Step 8: User Interaction

[0426] User: Can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) into the system.

[0427] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0428] Example 1

[0429] 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."

[0430] In conventional value assessment systems, data collection sources are limited, making it difficult to integrate and utilize information from diverse data sources. Furthermore, data standardization and analysis lacked standardized formats and insufficient application of machine learning algorithms, resulting in problems with reduced assessment accuracy. Furthermore, the results were not presented in a user-friendly manner, making it difficult for users to understand the information obtained.

[0431] 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.

[0432] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating a value based on the analysis results, means for presenting the calculated value to a user, means for collecting information from online sources and users, means for converting the data into a unified format, means for analyzing the data using a machine learning algorithm, and means for displaying the results in a visual format. This enables integrated analysis of information collected from various data sources, and improves analytical accuracy through the application of a unified format and machine learning. Furthermore, displaying the results in a user-friendly format allows users to easily understand and use the information.

[0433] A "database" is a system for systematically storing specific information and efficiently accessing and managing it.

[0434] "Data collection" is the process of obtaining necessary information from various sources.

[0435] "Standardization" is the process of unifying the format and units of collected data and managing the data in a consistent manner.

[0436] "Data analytics" is the process of analyzing collected and standardized data using statistical methods and machine learning algorithms to find useful information and patterns.

[0437] "Pricing" is the process of calculating the current market value of an object based on the results of data analysis.

[0438] "Presenting to the user" is the process of providing the calculated value to the user in a visually easy-to-understand format.

[0439] An "online source" is a data source accessible via the Internet.

[0440] "Information collection methods" are the technical means and identification methods used to obtain the required data from various sources.

[0441] "Format conversion" is the process of converting data of different formats and units into a unified format.

[0442] A "machine learning algorithm" is a computational model that learns from large amounts of data and automatically finds patterns and features.

[0443] A "visual format" is a format that presents data or information in an easy-to-read visual way, such as a graph or chart.

[0444] The system for implementing this invention collects a large amount of data from a database, standardizes it into a unified format, calculates value through analysis using a machine learning algorithm, and presents it to the user. A specific implementation method of this system is described below.

[0445] Data collection

[0446] Server: The server collects data from multiple websites that provide used car information. To do this, the server calls the API of each website to obtain data such as the vehicle's year, mileage, model, manufacturer, price, and user ratings. For example, it obtains JSON-formatted data from a website that provides data on a specific vehicle, parses it, and stores it in a local database. It is effective to use a relational database such as MySQL or PostgreSQL as the database.

[0447] User: The user uses their own device to enter details about their used car, such as the model year, mileage, specific options, and maintenance history, through a dedicated application or web form. The data entered by the user is sent to the server in real time and integrated with the collected data.

[0448] Data Standardization

[0449] Server: The server handles the process of unifying the format and units of the collected data. For example, if price information is stored in different currencies, it converts it all to yen. It also applies specific mapping rules to unify different field names for data retrieved from multiple data sources. Specifically, it uses the Python pandas library to create a data frame and rename columns based on the specified mapping.

[0450] Data analysis

[0451] Server: To analyze the standardized data, the server uses machine learning algorithms. For example, it uses Python's scikit-learn library to perform linear regression models and clustering. The analysis method not only calculates basic statistics of the data (mean, median, standard deviation), but also evaluates the impact of different parameters on vehicle value. Linear regression can be used to model the impact of model year and mileage on price.

[0452] Calculating value

[0453] Server: Based on the analysis results, the server calculates the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific conditions (e.g., mileage, optional equipment). The server also adjusts the value to take real-time market trends into account. For example, it performs trend analysis on historical data sets to take into account price fluctuations over a certain period of time.

[0454] Presentation of results

[0455] Server: The calculated value is formatted in a user-friendly format and sent to the user's device. Visual graphs and charts are generated to clearly show how each factor affects the value of a used car. For example, the JSON formatted data can be interpreted on the client side and a visualization library such as Chart.js can be used to draw line graphs and bar charts.

[0456] Terminal: The terminal analyzes the received data and displays it to the user in an easy-to-understand format. A dedicated interface allows the user to intuitively understand the valuation results. For example, a line graph showing the fluctuations in value based on model year and mileage can be displayed, allowing the user to visually see the impact of each factor on the price.

[0457] Examples of concrete examples and prompts

[0458] For example, consider a user wanting to value their 2015 vehicle. Using a smartphone application, the user inputs information such as the model year, mileage, optional equipment, and maintenance history. This information is then aggregated and analyzed on a server along with collected online data. The analysis results are then sent to the user's device and presented in a visual format.

[0459] Example prompt sentence:

[0460] "Write a program to assess the value of used cars. Your program should collect data from multiple online sources, convert it into a unified format, and then use machine learning algorithms to analyze it and calculate a final market value. The system should also collect specific vehicle information from the user (year, mileage, model, maintenance history, etc.). The results of the analysis should be displayed visually."

[0461] According to the present invention, highly accurate value assessment using a wide range of diverse data is possible, and highly reliable assessment information can be provided to users.

[0462] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0463] Step 1: Data collection

[0464] Input: API endpoint of online source, user-entered used car details (year, mileage, model, make, price, user ratings, etc.).

[0465] How it works: The server calls each website's API to retrieve the required vehicle data from online sources. For example, it uses the requests library to send a GET request and parses the JSON data received as a response. The vehicle information entered by the user through a dedicated application is sent to the server via HTTPS and stored in a database.

[0466] Output: Unified dataset, user input data.

[0467] Step 2: Standardize the data

[0468] Input: Integrated dataset, user input data.

[0469] Specific operation: If the format or units of collected data are not standardized, the server performs processing to standardize them. For example, it creates a data frame using the pandas library, converts all price information to yen, and applies mapping rules to standardize field names. It also standardizes different data types (e.g., converting strings to numbers).

[0470] Output: A standardized dataset.

[0471] Step 3: Analyze the data

[0472] Input: Standardized dataset.

[0473] What it does: The server feeds the standardized data to analytics tools. It uses Python's pandas library to calculate basic statistics (mean, median, standard deviation). It then uses the scikit-learn library to train machine learning models. For example, it uses a linear regression model to analyze the impact of vehicle age and mileage on price, and a clustering algorithm to group similar vehicles.

[0474] Output: Analysis results, machine learning model.

[0475] Step 4: Calculate value

[0476] Input: Analysis results, machine learning model.

[0477] How it works: The server uses the analysis results to calculate the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific factors (e.g., mileage and optional equipment). It also monitors market trends in real time and makes adjustments as needed. Python code is used to input new data into the predictive model and calculate prices.

[0478] Output: Final market value.

[0479] Step 5: Presenting the results

[0480] Input: Final market value.

[0481] What it does: The server formats the results in a user-friendly format and sends them to the user's device. The JSON formatted data is interpreted on the client side and visualized using a charting library (e.g. Chart.js, D3.js). The terminal application generates detailed graphs and charts for each factor to display the results to the user in an easy-to-understand manner.

[0482] Output: Visualized evaluation results.

[0483] This series of processes allows users to know the accurate market value of their used car in real time.

[0484] (Application example 1)

[0485] 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."

[0486] Conventional product price evaluation systems require users to perform multiple manual operations to obtain product information, making it difficult to provide real-time evaluations. Furthermore, the information obtained is often inaccurate, forcing users to rely on unreliable price information. As a result, consumers are unable to obtain fair and immediate price evaluations, hindering their purchasing decisions.

[0487] 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.

[0488] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for presenting the calculated value to the user, means for scanning product information in real time, means for analyzing the scanned information and calculating the value, and means for visually displaying the calculated value, thereby enabling users to instantly obtain reliable price information in the store and make fair and appropriate purchasing decisions.

[0489] A "database" is a system for managing and operating large amounts of electronically stored data.

[0490] "Means for collecting data" refers to the function for obtaining necessary information from external data sources.

[0491] "Means for standardizing data" refers to the function of converting collected data into a unified format and scale.

[0492] "Means of analyzing data" refers to functions that use statistical methods and machine learning algorithms to find patterns and trends in data.

[0493] "Means for calculating value" refers to a function for evaluating and calculating the market value of an object based on analyzed data.

[0494] The "means for presenting value to the user" is a function for displaying the calculated market value in a format that is easy for the user to understand.

[0495] "Means for scanning product information in real time" is a function that allows a user to instantly obtain information on an object as digital data by taking a picture of the object with a camera or the like.

[0496] "Means for analyzing scanned information and calculating value" refers to a function for analyzing and evaluating product value based on product data acquired in real time.

[0497] "Visual display means" refers to a function for providing analysis results and values ​​to users in a visual format such as a graph or chart.

[0498] The system for implementing this invention includes specific hardware and software components for data collection, standardization, analysis, value calculation, and result presentation. Specifically, it is a system that allows users to evaluate products in physical stores in real time using smart glasses and a smartphone. An example of its operation is described below.

[0499] Hardware Configuration

[0500] Smart glasses: Contains a camera for scanning product information and a display that visually displays the results to the user.

[0501] Smartphone: A device that works in conjunction with smart glasses, communicates with the server, and processes data.

[0502] Server: High-performance computing resources for data collection, normalization, analysis, and value calculation.

[0503] Software Configuration

[0504] API: An interface for retrieving product information from a database or external data source.

[0505] Data standardization tools: Software that converts collected data into a uniform format.

[0506] Analysis tools: Software that uses machine learning libraries such as TensorFlow and Scikit-learn to analyze data and find patterns.

[0507] User Interface: Software that generates graphs and charts for display on smart glasses and smartphones.

[0508] Program processing explanation

[0509] 1. Data Collection

[0510] The server uses APIs to collect product information from online marketplaces and specialty sites, including product names, prices, and ratings, as well as inventory data and pricing information from physical stores.

[0511] 2. Data Standardization

[0512] The server standardizes the collected data and converts it into a unified format, ensuring uniform currency units for pricing information and consistent rating scales.

[0513] 3. Data Analysis

[0514] The server analyzes the standardized data and uses statistical methods and machine learning algorithms to find patterns and trends, such as how certain characteristics affect the value of a product.

[0515] 4. Value calculation

[0516] The server calculates the market value of the product based on the analysis results, taking into account the average price of the same category and the influence of specific conditions (e.g., year of manufacture and features).

[0517] 5. Presentation of results

[0518] The analysis results from the server are sent back to the smart glasses via the smartphone, which overlay the results on the user's field of vision, providing detailed information in real time. Visual graphs and charts are also displayed, helping users understand how the product's value was calculated.

[0519] Specific examples

[0520] A user puts on smart glasses, walks through a store, and focuses their gaze on a particular product. The smart glasses' camera scans the product and recognizes its barcode or QR code. The scanned data is then sent via Bluetooth to a smartphone, which then communicates with a server. The server quickly calculates the product's value based on the collected and standardized data, and the result is sent back to the smart glasses via the smartphone. The user can then make the necessary purchasing decisions while looking at the information displayed in their field of vision.

[0521] Generative AI model prompt example

[0522] "This product is a new model manufactured in 2023. The market price is approximately 30,000 yen, but please calculate the value taking into account specific features (water resistance, battery life, etc.)."

[0523] As described above, the present invention allows for the instant acquisition of highly reliable price information in a store, thereby supporting fair and appropriate purchasing decisions.

[0524] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0525] Step 1:

[0526] A user uses smart glasses to scan an item. The input is the item's barcode or QR code, and the output is digital data to send the product data to a smartphone. The camera in the smart glasses scans the item and sends the data to the smartphone via Bluetooth.

[0527] Step 2:

[0528] The smartphone receives the scanned product data and sends it to the server. The input is the product information that received the data, and the output is the data sent to the server. The smartphone sends the data to the server via the Internet.

[0529] Step 3:

[0530] The server uses APIs to collect additional product information from various databases. The input is the scanned product data, and the output is data containing detailed product information. The server makes API calls to obtain information such as product name, price, and ratings.

[0531] Step 4:

[0532] The server standardizes the collected data. The input is product information collected in various formats, and the output is data in a unified format. The server converts the data's currency units and rating scales into a consistent format, and standardizes the data's field names and data types.

[0533] Step 5:

[0534] The server analyzes the standardized data. The input is the standardized product information, and the output is data containing the analysis results. The server uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to perform statistical analysis and pattern detection.

[0535] Step 6:

[0536] The server calculates the market value of the product based on the analysis results. The input is the analyzed data, and the output is data containing the product's current market value. The server uses statistical methods to evaluate the value, taking into account the average price in the same category and the influence of specific conditions.

[0537] Step 7:

[0538] The server formats the calculated market value for the user interface. The input is the market value data of the product, and the output is the formatted data in a format that is easy for the user to understand. The server generates graphs and charts and formats the data in a visually easy-to-understand format.

[0539] Step 8:

[0540] The smartphone transmits the data received from the server to the smart glasses. The input is the formatted product value data, and the output is data transmission to the smart glasses. The smartphone transmits the data to the smart glasses via Bluetooth or other communication means.

[0541] Step 9:

[0542] The smart glasses visually display the received data to the user. The input is formatted product value data, and the output is information overlaid on the user's field of view. The smart glasses display market value, graphs, charts, and other information on the display, allowing the user to make purchasing decisions.

[0543] Through the above steps, users can obtain product information in real time within a physical store and make purchasing decisions based on fair and reliable price information.

[0544] 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.

[0545] A system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Furthermore, by combining it with an emotion engine that recognizes user emotions, the accuracy and usefulness of user feedback can be improved. Specifically, this system performs data collection, standardization, analysis, value calculation, result presentation, and emotion analysis. The following scenario will be described as an example of how this system operates.

[0546] Example: Used car valuation system

[0547] Data collection

[0548] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[0549] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0550] Data Standardization

[0551] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[0552] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0553] Cleaning the data

[0554] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0555] Data analysis

[0556] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0557] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[0558] Calculating value

[0559] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0560] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0561] Generating and formatting results

[0562] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0563] Sending and displaying results

[0564] Server: Sends the formatted data to the user's device.

[0565] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0566] Introducing the Emotion Engine

[0567] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[0568] Server: Analyzed emotional information is stored in a database to improve the accuracy and usefulness of user feedback.

[0569] Emotion-Based Adjustment

[0570] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[0571] User Interaction

[0572] User: The user can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) to the system. Based on the emotional information analyzed by the emotion engine, appropriate feedback is requested.

[0573] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0574] Through this series of processes, users can not only objectively understand how much their used car is worth in the current market, but also obtain a more accurate value assessment by taking into account the emotional information in the feedback.

[0575] The processing flow will be explained below.

[0576] Step 1: Data collection

[0577] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[0578] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0579] Step 2: Standardize the data

[0580] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[0581] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0582] Step 3: Cleaning the data

[0583] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0584] Step 4: Analyze the data

[0585] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0586] Server: Uses machine learning algorithms to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation due to a particular model year and mileage.

[0587] Step 5: Calculate value

[0588] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0589] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0590] Step 6: Generate and format the results

[0591] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0592] Step 7: Send and view results

[0593] Server: Sends the formatted data to the user's device.

[0594] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0595] Step 8: Implementing the Emotion Engine

[0596] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[0597] Server: Stores the analyzed emotional information in a database to improve the accuracy and usefulness of feedback.

[0598] Step 9: Emotional Adjustment

[0599] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[0600] Step 10: User Interaction

[0601] User: Review the information provided and can enter feedback or additional information into the system (e.g., further vehicle details or comments) based on the emotional information analyzed by the emotion engine.

[0602] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0603] Example 2

[0604] 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."

[0605] In conventional data analysis systems, the inaccuracy and incompleteness of collected data affects the analysis results, making it difficult to perform highly accurate value assessments. Furthermore, user feedback was not properly collected, making further analysis and adjustments based on emotional information difficult. This made improving the user experience a challenge.

[0606] 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.

[0607] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for cleaning the standardized data, means for analyzing the cleaned data, means for calculating value based on the analysis results, means for presenting the calculated value to the user, means for analyzing the user's emotions, and means for adjusting the value calculation process and presentation content based on the analyzed emotional information. This makes it possible to improve the accuracy of the collected data and to evaluate value taking user emotional information into consideration.

[0608] A "database" is a system for efficiently storing and managing a large amount of data.

[0609] "Collection" is the process of gathering the necessary data from multiple sources.

[0610] "Standardization" is the process of converting data that exists in different formats into a unified format.

[0611] "Cleaning" is the process of detecting and removing inaccurate or incomplete data.

[0612] "Analysis" is the process of analyzing data and extracting valuable information and patterns.

[0613] "Value calculation" is the process of quantifying the value of data based on collected data and analysis results.

[0614] "Presentation" is the process of displaying calculated values ​​and analytical results in a user-friendly format.

[0615] "Sentiment analysis" is the process of recognizing and analyzing user emotions based on user feedback and data.

[0616] "Tuning" is the process of improving a process or display based on the results of analysis or calculations.

[0617] A system for implementing this invention calculates the market value of, for example, a used car based on information provided by users and data on the Internet. This system includes specific hardware and software components, enabling improved accuracy of collected data and value assessment that takes user emotion information into account.

[0618] Hardware and Software Configuration

[0619] Server: Retrieves required information from multiple websites and databases using APIs, scrapes information from web pages using Python's Beautiful Soup and Scrapy, standardizes and cleans data using Python's Pandas and Numpy, and performs data analysis using Scikit-Learn and TensorFlow.

[0620] Terminal: Provides an interface for users to input information. This interface includes a form for users to enter details about their used car. The information entered is sent to a database and analyzed by the server.

[0621] Emotion Engine: Analyzes emotions from user feedback using NLP libraries (e.g., NLTK and spaCy) and TensorFlow, and stores the user's emotional information in a database for further tuning and improving the data analysis algorithm.

[0622] Specific examples

[0623] As an example of how this system works, we will explain a used car value assessment system. The server obtains detailed vehicle information (year, mileage, model, manufacturer, price, user ratings, etc.) via API from, for example, "used car information site A" or "used car transaction database B." Python's Beautiful Soup and Scrapy are used to automatically extract the necessary information from web pages.

[0624] Users use their own devices to open a dedicated input form and enter detailed information about their used car (e.g., specific optional equipment and maintenance history). This information is sent to the server and stored in a database.

[0625] The server standardizes and cleans the collected data using Pandas and Numpy to remove inaccurate or incomplete data, then performs data analysis using Scikit-Learn and TensorFlow to extract specific patterns and trends. Based on the analysis results, the server calculates the market value of each used car in an unbiased and objective manner.

[0626] The server then formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, using Matplotlib or Plotly to generate graphs and charts, and converts them to JSON format.

[0627] The server sends this formatted data to the user's device, which then uses the JavaScript D3.js to draw a line graph showing the fluctuations in value based on model year and mileage, as well as a histogram of market prices.

[0628] The emotion engine analyzes text and voice data to recognize user emotions (e.g., satisfaction, dissatisfaction, excitement, etc.). This emotion information is also stored in the database and used to improve the accuracy and usefulness of user feedback.

[0629] Prompt Sentence Examples

[0630] "Evaluate the market value of a used car based on its age and mileage. Include any specific optional equipment and maintenance history in your evaluation."

[0631] "Reassess the value of used cars taking into account user emotional feedback and suggest improvements."

[0632] This system not only allows users to objectively understand how much their used car is worth in the current market, but also allows them to receive a more accurate value assessment based on emotional information.

[0633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0634] Step 1:

[0635] Data collection

[0636] The server uses APIs to obtain detailed vehicle information from multiple websites and databases that provide used car information. Specifically, it sends requests to the APIs of each website to obtain data including model year, mileage, model, manufacturer, price, user ratings, etc. The input is the API request parameters and search conditions, and the output is vehicle information data in JSON format.

[0637] The server uses Python's Beautiful Soup or Scrapy to scrape information from web pages. It parses the HTML of the web page and extracts the required information. The input is the web page's URL or HTML source, and the output is the extracted text data or table data.

[0638] A user opens a dedicated input form on their device and enters the details of their used car. The input is the vehicle information (e.g., year, model, mileage, etc.) that the user fills in the form, and the output is structured data (e.g., JSON format) received by the server.

[0639] Step 2:

[0640] Data Standardization

[0641] The server converts the collected data from various formats into a single unified format using the Pandas library. Specifically, it standardizes the currency units of the pricing information (e.g., converting everything to USD) and converts the rating scale to a consistent standard. The input is vehicle data in different formats, and the output is a data frame in a unified format.

[0642] The server aggregates identical information fields (e.g., year and model) from different data sources to create a consistent dataset. The input is multiple data frames of vehicle data from different sources, and the output is an aggregated data frame.

[0643] Step 3:

[0644] Cleaning the data

[0645] The server detects and filters out inaccurate or incomplete data from the collected data. Specifically, it uses Pandas to detect NAN values ​​and outliers and remove or correct them. The input is a standardized data frame, and the output is a clean dataset with inaccurate data removed.

[0646] Step 4:

[0647] Data analysis

[0648] The server analyzes the standardized and cleaned data, first calculating basic statistics (mean, median, standard deviation, etc.) using Scikit-Learn or StatsModels. The input is the clean dataset, and the output is the statistical analysis results.

[0649] The server uses machine learning algorithms to extract patterns and trends, applying linear regression or random forests to analyze the relationship between specific model years and mileage. The input is the clean dataset, and the output is the predictions of the machine learning model.

[0650] Step 5:

[0651] Calculating value

[0652] The server calculates the current market value of the used car based on the analysis results. Specifically, it evaluates the value based on the average and median market prices of vehicles of the same age and condition. The inputs are the predictions of the machine learning model and market data, and the output is the calculated market value.

[0653] The server adjusts the final value, taking into account market trends and supply and demand balances. The inputs are the calculated market value and additional economic indicator data, and the output is the adjusted market value.

[0654] Step 6:

[0655] Generating and formatting results

[0656] The server formats the calculated value in a user-friendly format. It uses Matplotlib or Plotly to generate graphs and charts and converts them to JSON format. The input is the adjusted market value, and the output is the formatted data (JSON format).

[0657] Step 7:

[0658] Sending and displaying results

[0659] The server sends the formatted data to the user's device. The input is the formatted data (JSON format) and the output is the sent response.

[0660] The terminal analyzes the received data and displays it to the user. Using JavaScript D3.js, it draws line graphs showing the fluctuations in value depending on the model year and mileage, as well as histograms of market prices. The input is the received data (in JSON format), and the output is the visualized graph or chart.

[0661] Step 8:

[0662] Introducing the Emotion Engine

[0663] The server uses NLP libraries and TensorFlow to analyze emotions from the feedback provided by the user. Specifically, it processes text and voice data and recognizes emotions such as satisfaction, dissatisfaction, and excitement. The input is the user's feedback data, and the output is the analyzed emotional information.

[0664] The server stores the analyzed emotion information in a database. The input is the analyzed emotion information, and the output is a stored database entry.

[0665] Step 9:

[0666] Emotion-Based Adjustment

[0667] The server adjusts the value calculation process and presentation content based on the user's emotional information. It also adjusts the algorithm parameters based on dissatisfaction information about specific factors. The inputs are the emotional information and the parameters of the value assessment process, and the output is the adjusted value calculation result.

[0668] Step 10:

[0669] User Interaction

[0670] The user reviews the information provided and provides feedback and additional information to the system, for example, providing further vehicle details or comments. The input is the user's feedback and additional information, and the output is the data sent to the server.

[0671] The server collects user feedback and stores it in a database, which is used to adjust and improve future data analysis algorithms. The input is the user feedback data, and the output is the stored database entry.

[0672] (Application example 2)

[0673] 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."

[0674] Conventional value assessment systems only standardize and analyze collected data, making it difficult to appropriately reflect user feedback. Furthermore, because they do not take user emotions or satisfaction into account, it is difficult to improve the user experience or the quality of feedback. Therefore, there is a need to provide a more accurate and user-friendly value assessment system that recognizes user emotions and reflects them in feedback.

[0675] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0676] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating value based on the analysis results, means for analyzing user emotions, and means for adjusting feedback based on the analyzed emotions, thereby enabling more accurate value assessment that takes user emotions into consideration and improving user satisfaction.

[0677] A "database" is a system for systematically managing, storing, and retrieving large amounts of data.

[0678] "Collection methods" refers to the methods and techniques used to obtain data from various sources.

[0679] "Standardization measures" are methods for converting data that exists in different formats and units into a unified format.

[0680] "Means of analysis" refers to a method of analyzing collected and standardized data using statistical and machine learning techniques.

[0681] "Means of calculating value" refers to the method of calculating the market value of goods or services based on the results of the analysis.

[0682] "Means for presenting to the user" is a method for displaying the calculated value in a user-friendly format.

[0683] "Means for analyzing emotions" refers to technology that uses text data and voice data from users to recognize their emotional state.

[0684] The "means for adjusting feedback" is a method for adjusting the content of the user's feedback based on the analyzed emotional information.

[0685] "Inaccuracy removal measures" are methods for identifying and removing erroneous or incomplete information from collected data.

[0686] "Means for collecting feedback" refers to methods for collecting opinions and evaluation information from users.

[0687] "Means for storing feedback in a database" refers to a method for storing collected feedback information in a database.

[0688] "Means for improving analysis" are techniques that use stored feedback information to improve data analysis algorithms and methods.

[0689] The system for implementing this invention collects a large amount of data from a database, standardizes and analyzes it, calculates a value based on the results, and presents it to the user. Furthermore, it analyzes the user's emotions and adjusts feedback based on the results, thereby providing a more accurate and user-friendly value assessment.

[0690] The main components of the system include a server, a terminal, and a user.

[0691] server

[0692] Data collection method: The server collects a large amount of data from the database using APIs (Application Programming Interfaces) and other methods. Specifically, product information and market value data is obtained from multiple websites and databases. In some cases, scraping technology is used to extract information.

[0693] Data standardization measures: As the collected data exists in various formats, the currency units and evaluation scales are standardized. This is a process to maintain data consistency.

[0694] Data analysis methods: Standardized data is analyzed using statistical methods and machine learning algorithms to calculate statistical values ​​such as the mean, median, and standard deviation, and to identify specific trends and patterns.

[0695] Value calculation method: Based on the analysis results, we calculate the market value of each product in a fair and objective manner, using the average or median market price of products of the same age and condition.

[0696] Result presentation method: Generates data to present the calculated value to the user and sends it to the terminal in JSON format, graphs, charts, etc.

[0697] Sentiment analysis means: An emotion engine is used to analyze user feedback text and voice data to recognize the user's emotional state (e.g., satisfied, dissatisfied, excited).

[0698] Feedback adjustment: Adjust the feedback content and value calculation process based on the analyzed emotional information. For example, adjust the value for a specific factor that the user expressed dissatisfaction with or provide additional information.

[0699] Terminal

[0700] Data display means: Receives data sent from the server and displays the results using a user-friendly UI, such as graphs showing product age and price fluctuations, or recommendations based on user feedback.

[0701] User

[0702] Providing feedback: Users can input detailed product information and feedback into the system to improve the accuracy of data collection. Furthermore, the emotion engine analyzes the emotional information and provides appropriate feedback.

[0703] Specific examples

[0704] For example, if a user provides feedback such as "This book has great content and was reasonably priced," the server sends this text data to a sentiment analysis engine to analyze positive sentiment. This analysis information is reflected in the next value calculation process as an upward correction to the value.

[0705] Example prompt sentence:

[0706] This book is excellent and was reasonably priced.

[0707] In this way, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

[0708] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0709] Step 1:

[0710] The server collects product information and market value data from the database using APIs. The collected data is obtained from multiple websites and databases, sometimes using scraping techniques. The input is from multiple data sources, and the output is data in different formats.

[0711] Step 2:

[0712] The server normalizes the collected data, specifically by standardizing the currency unit (e.g., converting all prices to USD) and the rating scale. The input is the raw data collected in step 1, and the output is the normalized data converted into a consistent format.

[0713] Step 3:

[0714] The server analyzes the standardized data using statistical methods and machine learning algorithms to calculate statistics such as the mean, median, and standard deviation. It also extracts specific trends and patterns. The input is the standardized data, and the output is the statistical analysis results.

[0715] Step 4:

[0716] The server calculates the value based on the analysis results. It calculates the market value of each item in a fair and objective manner, and calculates the value using the average or median market price of items of the same age and condition. The input is the analysis result from Step 3, and the output is the calculated market value.

[0717] Step 5:

[0718] The server formats the data to present the calculated value to the user. The generated value data is sent to the terminal in a UI format that is easy for the user to understand (e.g., JSON format, graphs, charts). The input is market value data, and the output is the formatted data.

[0719] Step 6:

[0720] The terminal receives the data sent from the server and displays the results in a user-friendly UI. The displayed content includes graphs showing the model year and price fluctuations of products, as well as recommendations based on user feedback. The input is the formatted data, and the output is the results displayed in the UI.

[0721] Step 7:

[0722] Users input detailed product information and feedback into the system, for example, by providing impressions and ratings in text format, which improves the accuracy of data collection. The input is the user-provided feedback, and the output is the feedback data sent to the server.

[0723] Step 8:

[0724] The server sends the user's feedback text or voice data to the emotion analysis engine, which analyzes the user's emotional state (e.g., satisfied, dissatisfied, excited). The input is text or voice data, and the output is the analyzed emotional information.

[0725] Step 9:

[0726] The server adjusts the feedback content and value calculation process based on the analyzed emotion information. Specifically, it adjusts the value for specific factors that the user expressed dissatisfaction with and presents additional information. The input is emotion analysis information, and the output is the adjusted value data and additional information.

[0727] Through the above processing steps, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] [Third embodiment]

[0732] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0733] 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.

[0734] 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).

[0735] 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.

[0736] 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.

[0737] 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).

[0738] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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."

[0744] The system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Specifically, this system collects data, standardizes it, analyzes it, calculates its value, and presents the results. The following scenario will be described as an example of how this system operates.

[0745] Example: Used car valuation system

[0746] Data collection

[0747] Server: Uses APIs to collect data such as vehicle year, mileage, model, manufacturer, price, and user ratings from multiple websites that provide used car information. It also obtains information from open and proprietary databases.

[0748] User: Enters detailed information about the used car he owns (e.g., specific optional equipment and maintenance history) through his own device, allowing for more specific data to be collected.

[0749] Data Standardization

[0750] Server: The collected data comes from a variety of sources and is not in a uniform format. The server converts this data into a uniform format. For example, it standardizes the currency units of price information, standardizes rating scales, and aligns different field names and data types into a consistent format.

[0751] Data analysis

[0752] Server: Feeds the standardized data into analytics tools, which use statistical methods (e.g., mean, median, standard deviation) to calculate baseline characteristics. Additionally, machine learning algorithms (e.g., linear regression and clustering) are used to identify patterns and trends. For example, estimating the rate of depreciation for a vehicle of a particular model year after a certain number of miles.

[0753] Calculating value

[0754] Server: Based on the analysis results, the current market value of each used vehicle is calculated, taking into account the average price of the same model and year, the impact of specific conditions (such as mileage and optional equipment), market trends, and the balance of supply and demand.

[0755] Presentation of results

[0756] Server: The calculated value is formatted in a user-friendly format. The formatted data is sent to the user's device.

[0757] Device: The results are displayed on the user's device, using visual graphs and charts to clearly explain how each factor affects the value of a used car, such as a line graph showing how value varies by age and mileage.

[0758] Through this series of processes, users can objectively understand how much their used car is worth in the current market and obtain a fair and impartial valuation. This system can also be applied to valuing various products and services, and can provide highly accurate results by utilizing a wide range of data.

[0759] The processing flow will be explained below.

[0760] Step 1: Data collection

[0761] Server: Using APIs, the server obtains vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. It also uses scraping technology to extract the necessary information from web pages.

[0762] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0763] Step 2: Standardize the data

[0764] Server: The collected data exists in various formats, so it is first converted into a unified format. For example, the currency units for price information are unified and rating scales are aligned to a consistent standard.

[0765] Server: Additionally, it aggregates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0766] Step 3: Cleaning the data

[0767] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0768] Step 4: Analyze the data

[0769] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0770] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[0771] Step 5: Calculate value

[0772] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0773] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0774] Step 6: Generate and format the results

[0775] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0776] Step 7: Send and view results

[0777] Server: Sends the formatted data to the user's device.

[0778] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0779] Step 8: User Interaction

[0780] User: Can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) into the system.

[0781] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0782] Example 1

[0783] 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."

[0784] In conventional value assessment systems, data collection sources are limited, making it difficult to integrate and utilize information from diverse data sources. Furthermore, data standardization and analysis lacked standardized formats and insufficient application of machine learning algorithms, resulting in problems with reduced assessment accuracy. Furthermore, the results were not presented in a user-friendly manner, making it difficult for users to understand the information obtained.

[0785] 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.

[0786] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating a value based on the analysis results, means for presenting the calculated value to a user, means for collecting information from online sources and users, means for converting the data into a unified format, means for analyzing the data using a machine learning algorithm, and means for displaying the results in a visual format. This enables integrated analysis of information collected from various data sources, and improves analytical accuracy through the application of a unified format and machine learning. Furthermore, displaying the results in a user-friendly format allows users to easily understand and use the information.

[0787] A "database" is a system for systematically storing specific information and efficiently accessing and managing it.

[0788] "Data collection" is the process of obtaining necessary information from various sources.

[0789] "Standardization" is the process of unifying the format and units of collected data and managing the data in a consistent manner.

[0790] "Data analytics" is the process of analyzing collected and standardized data using statistical methods and machine learning algorithms to find useful information and patterns.

[0791] "Pricing" is the process of calculating the current market value of an object based on the results of data analysis.

[0792] "Presenting to the user" is the process of providing the calculated value to the user in a visually easy-to-understand format.

[0793] An "online source" is a data source accessible via the Internet.

[0794] "Information collection methods" are the technical means and identification methods used to obtain the required data from various sources.

[0795] "Format conversion" is the process of converting data of different formats and units into a unified format.

[0796] A "machine learning algorithm" is a computational model that learns from large amounts of data and automatically finds patterns and features.

[0797] A "visual format" is a format that presents data or information in an easy-to-read visual way, such as a graph or chart.

[0798] The system for implementing this invention collects a large amount of data from a database, standardizes it into a unified format, calculates value through analysis using a machine learning algorithm, and presents it to the user. A specific implementation method of this system is described below.

[0799] Data collection

[0800] Server: The server collects data from multiple websites that provide used car information. To do this, the server calls the API of each website to obtain data such as the vehicle's year, mileage, model, manufacturer, price, and user ratings. For example, it obtains JSON-formatted data from a website that provides data on a specific vehicle, parses it, and stores it in a local database. It is effective to use a relational database such as MySQL or PostgreSQL as the database.

[0801] User: The user uses their own device to enter details about their used car, such as the model year, mileage, specific options, and maintenance history, through a dedicated application or web form. The data entered by the user is sent to the server in real time and integrated with the collected data.

[0802] Data Standardization

[0803] Server: The server handles the process of unifying the format and units of the collected data. For example, if price information is stored in different currencies, it converts it all to yen. It also applies specific mapping rules to unify different field names for data retrieved from multiple data sources. Specifically, it uses the Python pandas library to create a data frame and rename columns based on the specified mapping.

[0804] Data analysis

[0805] Server: To analyze the standardized data, the server uses machine learning algorithms. For example, it uses Python's scikit-learn library to perform linear regression models and clustering. The analysis method not only calculates basic statistics of the data (mean, median, standard deviation), but also evaluates the impact of different parameters on vehicle value. Linear regression can be used to model the impact of model year and mileage on price.

[0806] Calculating value

[0807] Server: Based on the analysis results, the server calculates the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific conditions (e.g., mileage, optional equipment). The server also adjusts the value to take real-time market trends into account. For example, it performs trend analysis on historical data sets to take into account price fluctuations over a certain period of time.

[0808] Presentation of results

[0809] Server: The calculated value is formatted in a user-friendly format and sent to the user's device. Visual graphs and charts are generated to clearly show how each factor affects the value of a used car. For example, the JSON formatted data can be interpreted on the client side and a visualization library such as Chart.js can be used to draw line graphs and bar charts.

[0810] Terminal: The terminal analyzes the received data and displays it to the user in an easy-to-understand format. A dedicated interface allows the user to intuitively understand the valuation results. For example, a line graph showing the fluctuations in value based on model year and mileage can be displayed, allowing the user to visually see the impact of each factor on the price.

[0811] Examples of concrete examples and prompts

[0812] For example, consider a user wanting to value their 2015 vehicle. Using a smartphone application, the user inputs information such as the model year, mileage, optional equipment, and maintenance history. This information is then aggregated and analyzed on a server along with collected online data. The analysis results are then sent to the user's device and presented in a visual format.

[0813] Example prompt sentence:

[0814] "Write a program to assess the value of used cars. Your program should collect data from multiple online sources, convert it into a unified format, and then use machine learning algorithms to analyze it and calculate a final market value. The system should also collect specific vehicle information from the user (year, mileage, model, maintenance history, etc.). The results of the analysis should be displayed visually."

[0815] According to the present invention, highly accurate value assessment using a wide range of diverse data is possible, and highly reliable assessment information can be provided to users.

[0816] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0817] Step 1: Data collection

[0818] Input: API endpoint of online source, user-entered used car details (year, mileage, model, make, price, user ratings, etc.).

[0819] How it works: The server calls each website's API to retrieve the required vehicle data from online sources. For example, it uses the requests library to send a GET request and parses the JSON data received as a response. The vehicle information entered by the user through a dedicated application is sent to the server via HTTPS and stored in a database.

[0820] Output: Unified dataset, user input data.

[0821] Step 2: Standardize the data

[0822] Input: Integrated dataset, user input data.

[0823] Specific operation: If the format or units of collected data are not standardized, the server performs processing to standardize them. For example, it creates a data frame using the pandas library, converts all price information to yen, and applies mapping rules to standardize field names. It also standardizes different data types (e.g., converting strings to numbers).

[0824] Output: A standardized dataset.

[0825] Step 3: Analyze the data

[0826] Input: Standardized dataset.

[0827] What it does: The server feeds the standardized data to analytics tools. It uses Python's pandas library to calculate basic statistics (mean, median, standard deviation). It then uses the scikit-learn library to train machine learning models. For example, it uses a linear regression model to analyze the impact of vehicle age and mileage on price, and a clustering algorithm to group similar vehicles.

[0828] Output: Analysis results, machine learning model.

[0829] Step 4: Calculate value

[0830] Input: Analysis results, machine learning model.

[0831] How it works: The server uses the analysis results to calculate the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific factors (e.g., mileage and optional equipment). It also monitors market trends in real time and makes adjustments as needed. Python code is used to input new data into the predictive model and calculate prices.

[0832] Output: Final market value.

[0833] Step 5: Presenting the results

[0834] Input: Final market value.

[0835] What it does: The server formats the results in a user-friendly format and sends them to the user's device. The JSON formatted data is interpreted on the client side and visualized using a charting library (e.g. Chart.js, D3.js). The terminal application generates detailed graphs and charts for each factor to display the results to the user in an easy-to-understand manner.

[0836] Output: Visualized evaluation results.

[0837] This series of processes allows users to know the accurate market value of their used car in real time.

[0838] (Application example 1)

[0839] 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."

[0840] Conventional product price evaluation systems require users to perform multiple manual operations to obtain product information, making it difficult to provide real-time evaluations. Furthermore, the information obtained is often inaccurate, forcing users to rely on unreliable price information. As a result, consumers are unable to obtain fair and immediate price evaluations, hindering their purchasing decisions.

[0841] 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.

[0842] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for presenting the calculated value to the user, means for scanning product information in real time, means for analyzing the scanned information and calculating the value, and means for visually displaying the calculated value, thereby enabling users to instantly obtain reliable price information in the store and make fair and appropriate purchasing decisions.

[0843] A "database" is a system for managing and operating large amounts of electronically stored data.

[0844] "Means for collecting data" refers to the function for obtaining necessary information from external data sources.

[0845] "Means for standardizing data" refers to the function of converting collected data into a unified format and scale.

[0846] "Means of analyzing data" refers to functions that use statistical methods and machine learning algorithms to find patterns and trends in data.

[0847] "Means for calculating value" refers to a function for evaluating and calculating the market value of an object based on analyzed data.

[0848] The "means for presenting value to the user" is a function for displaying the calculated market value in a format that is easy for the user to understand.

[0849] "Means for scanning product information in real time" is a function that allows a user to instantly obtain information on an object as digital data by taking a picture of the object with a camera or the like.

[0850] "Means for analyzing scanned information and calculating value" refers to a function for analyzing and evaluating product value based on product data acquired in real time.

[0851] "Visual display means" refers to a function for providing analysis results and values ​​to users in a visual format such as a graph or chart.

[0852] The system for implementing this invention includes specific hardware and software components for data collection, standardization, analysis, value calculation, and result presentation. Specifically, it is a system that allows users to evaluate products in physical stores in real time using smart glasses and a smartphone. An example of its operation is described below.

[0853] Hardware Configuration

[0854] Smart glasses: Contains a camera for scanning product information and a display that visually displays the results to the user.

[0855] Smartphone: A device that works in conjunction with smart glasses, communicates with the server, and processes data.

[0856] Server: High-performance computing resources for data collection, normalization, analysis, and value calculation.

[0857] Software Configuration

[0858] API: An interface for retrieving product information from a database or external data source.

[0859] Data standardization tools: Software that converts collected data into a uniform format.

[0860] Analysis tools: Software that uses machine learning libraries such as TensorFlow and Scikit-learn to analyze data and find patterns.

[0861] User Interface: Software that generates graphs and charts for display on smart glasses and smartphones.

[0862] Program processing explanation

[0863] 1. Data Collection

[0864] The server uses APIs to collect product information from online marketplaces and specialty sites, including product names, prices, and ratings, as well as inventory data and pricing information from physical stores.

[0865] 2. Data Standardization

[0866] The server standardizes the collected data and converts it into a unified format, ensuring uniform currency units for pricing information and consistent rating scales.

[0867] 3. Data Analysis

[0868] The server analyzes the standardized data and uses statistical methods and machine learning algorithms to find patterns and trends, such as how certain characteristics affect the value of a product.

[0869] 4. Value calculation

[0870] The server calculates the market value of the product based on the analysis results, taking into account the average price of the same category and the influence of specific conditions (e.g., year of manufacture and features).

[0871] 5. Presentation of results

[0872] The analysis results from the server are sent back to the smart glasses via the smartphone, which overlay the results on the user's field of vision, providing detailed information in real time. Visual graphs and charts are also displayed, helping users understand how the product's value was calculated.

[0873] Specific examples

[0874] A user puts on smart glasses, walks through a store, and focuses their gaze on a particular product. The smart glasses' camera scans the product and recognizes its barcode or QR code. The scanned data is then sent via Bluetooth to a smartphone, which then communicates with a server. The server quickly calculates the product's value based on the collected and standardized data, and the result is sent back to the smart glasses via the smartphone. The user can then make the necessary purchasing decisions while looking at the information displayed in their field of vision.

[0875] Generative AI model prompt example

[0876] "This product is a new model manufactured in 2023. The market price is approximately 30,000 yen, but please calculate the value taking into account specific features (water resistance, battery life, etc.)."

[0877] As described above, the present invention allows for the instant acquisition of highly reliable price information in a store, thereby supporting fair and appropriate purchasing decisions.

[0878] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0879] Step 1:

[0880] A user uses smart glasses to scan an item. The input is the item's barcode or QR code, and the output is digital data to send the product data to a smartphone. The camera in the smart glasses scans the item and sends the data to the smartphone via Bluetooth.

[0881] Step 2:

[0882] The smartphone receives the scanned product data and sends it to the server. The input is the product information that received the data, and the output is the data sent to the server. The smartphone sends the data to the server via the Internet.

[0883] Step 3:

[0884] The server uses APIs to collect additional product information from various databases. The input is the scanned product data, and the output is data containing detailed product information. The server makes API calls to obtain information such as product name, price, and ratings.

[0885] Step 4:

[0886] The server standardizes the collected data. The input is product information collected in various formats, and the output is data in a unified format. The server converts the data's currency units and rating scales into a consistent format, and standardizes the data's field names and data types.

[0887] Step 5:

[0888] The server analyzes the standardized data. The input is the standardized product information, and the output is data containing the analysis results. The server uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to perform statistical analysis and pattern detection.

[0889] Step 6:

[0890] The server calculates the market value of the product based on the analysis results. The input is the analyzed data, and the output is data containing the product's current market value. The server uses statistical methods to evaluate the value, taking into account the average price in the same category and the influence of specific conditions.

[0891] Step 7:

[0892] The server formats the calculated market value for the user interface. The input is the market value data of the product, and the output is the formatted data in a format that is easy for the user to understand. The server generates graphs and charts and formats the data in a visually easy-to-understand format.

[0893] Step 8:

[0894] The smartphone transmits the data received from the server to the smart glasses. The input is the formatted product value data, and the output is data transmission to the smart glasses. The smartphone transmits the data to the smart glasses via Bluetooth or other communication means.

[0895] Step 9:

[0896] The smart glasses visually display the received data to the user. The input is formatted product value data, and the output is information overlaid on the user's field of view. The smart glasses display market value, graphs, charts, and other information on the display, allowing the user to make purchasing decisions.

[0897] Through the above steps, users can obtain product information in real time within a physical store and make purchasing decisions based on fair and reliable price information.

[0898] 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.

[0899] A system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Furthermore, by combining it with an emotion engine that recognizes user emotions, the accuracy and usefulness of user feedback can be improved. Specifically, this system performs data collection, standardization, analysis, value calculation, result presentation, and emotion analysis. The following scenario will be described as an example of how this system operates.

[0900] Example: Used car valuation system

[0901] Data collection

[0902] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[0903] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0904] Data Standardization

[0905] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[0906] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0907] Cleaning the data

[0908] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0909] Data analysis

[0910] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0911] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[0912] Calculating value

[0913] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0914] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0915] Generating and formatting results

[0916] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0917] Sending and displaying results

[0918] Server: Sends the formatted data to the user's device.

[0919] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0920] Introducing the Emotion Engine

[0921] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[0922] Server: Analyzed emotional information is stored in a database to improve the accuracy and usefulness of user feedback.

[0923] Emotion-Based Adjustment

[0924] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[0925] User Interaction

[0926] User: The user can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) to the system. Based on the emotional information analyzed by the emotion engine, appropriate feedback is requested.

[0927] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0928] Through this series of processes, users can not only objectively understand how much their used car is worth in the current market, but also obtain a more accurate value assessment by taking into account the emotional information in the feedback.

[0929] The processing flow will be explained below.

[0930] Step 1: Data collection

[0931] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[0932] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[0933] Step 2: Standardize the data

[0934] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[0935] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[0936] Step 3: Cleaning the data

[0937] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[0938] Step 4: Analyze the data

[0939] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[0940] Server: Uses machine learning algorithms to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation due to a particular model year and mileage.

[0941] Step 5: Calculate value

[0942] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[0943] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[0944] Step 6: Generate and format the results

[0945] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[0946] Step 7: Send and view results

[0947] Server: Sends the formatted data to the user's device.

[0948] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[0949] Step 8: Implementing the Emotion Engine

[0950] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[0951] Server: Stores the analyzed emotional information in a database to improve the accuracy and usefulness of feedback.

[0952] Step 9: Emotional Adjustment

[0953] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[0954] Step 10: User Interaction

[0955] User: Review the information provided and can enter feedback or additional information into the system (e.g., further vehicle details or comments) based on the emotional information analyzed by the emotion engine.

[0956] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[0957] Example 2

[0958] 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."

[0959] In conventional data analysis systems, the inaccuracy and incompleteness of collected data affects the analysis results, making it difficult to perform highly accurate value assessments. Furthermore, user feedback was not properly collected, making further analysis and adjustments based on emotional information difficult. This made improving the user experience a challenge.

[0960] 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.

[0961] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for cleaning the standardized data, means for analyzing the cleaned data, means for calculating value based on the analysis results, means for presenting the calculated value to the user, means for analyzing the user's emotions, and means for adjusting the value calculation process and presentation content based on the analyzed emotional information. This makes it possible to improve the accuracy of the collected data and to evaluate value taking user emotional information into consideration.

[0962] A "database" is a system for efficiently storing and managing a large amount of data.

[0963] "Collection" is the process of gathering the necessary data from multiple sources.

[0964] "Standardization" is the process of converting data that exists in different formats into a unified format.

[0965] "Cleaning" is the process of detecting and removing inaccurate or incomplete data.

[0966] "Analysis" is the process of analyzing data and extracting valuable information and patterns.

[0967] "Value calculation" is the process of quantifying the value of data based on collected data and analysis results.

[0968] "Presentation" is the process of displaying calculated values ​​and analytical results in a user-friendly format.

[0969] "Sentiment analysis" is the process of recognizing and analyzing user emotions based on user feedback and data.

[0970] "Tuning" is the process of improving a process or display based on the results of analysis or calculations.

[0971] A system for implementing this invention calculates the market value of, for example, a used car based on information provided by users and data on the Internet. This system includes specific hardware and software components, enabling improved accuracy of collected data and value assessment that takes user emotion information into account.

[0972] Hardware and Software Configuration

[0973] Server: Retrieves required information from multiple websites and databases using APIs, scrapes information from web pages using Python's Beautiful Soup and Scrapy, standardizes and cleans data using Python's Pandas and Numpy, and performs data analysis using Scikit-Learn and TensorFlow.

[0974] Terminal: Provides an interface for users to input information. This interface includes a form for users to enter details about their used car. The information entered is sent to a database and analyzed by the server.

[0975] Emotion Engine: Analyzes emotions from user feedback using NLP libraries (e.g., NLTK and spaCy) and TensorFlow, and stores the user's emotional information in a database for further tuning and improving the data analysis algorithm.

[0976] Specific examples

[0977] As an example of how this system works, we will explain a used car value assessment system. The server obtains detailed vehicle information (year, mileage, model, manufacturer, price, user ratings, etc.) via API from, for example, "used car information site A" or "used car transaction database B." Python's Beautiful Soup and Scrapy are used to automatically extract the necessary information from web pages.

[0978] Users use their own devices to open a dedicated input form and enter detailed information about their used car (e.g., specific optional equipment and maintenance history). This information is sent to the server and stored in a database.

[0979] The server standardizes and cleans the collected data using Pandas and Numpy to remove inaccurate or incomplete data, then performs data analysis using Scikit-Learn and TensorFlow to extract specific patterns and trends. Based on the analysis results, the server calculates the market value of each used car in an unbiased and objective manner.

[0980] The server then formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, using Matplotlib or Plotly to generate graphs and charts, and converts them to JSON format.

[0981] The server sends this formatted data to the user's device, which then uses the JavaScript D3.js to draw a line graph showing the fluctuations in value based on model year and mileage, as well as a histogram of market prices.

[0982] The emotion engine analyzes text and voice data to recognize user emotions (e.g., satisfaction, dissatisfaction, excitement, etc.). This emotion information is also stored in the database and used to improve the accuracy and usefulness of user feedback.

[0983] Prompt Sentence Examples

[0984] "Evaluate the market value of a used car based on its age and mileage. Include any specific optional equipment and maintenance history in your evaluation."

[0985] "Reassess the value of used cars taking into account user emotional feedback and suggest improvements."

[0986] This system not only allows users to objectively understand how much their used car is worth in the current market, but also allows them to receive a more accurate value assessment based on emotional information.

[0987] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0988] Step 1:

[0989] Data collection

[0990] The server uses APIs to obtain detailed vehicle information from multiple websites and databases that provide used car information. Specifically, it sends requests to the APIs of each website to obtain data including model year, mileage, model, manufacturer, price, user ratings, etc. The input is the API request parameters and search conditions, and the output is vehicle information data in JSON format.

[0991] The server uses Python's Beautiful Soup or Scrapy to scrape information from web pages. It parses the HTML of the web page and extracts the required information. The input is the web page's URL or HTML source, and the output is the extracted text data or table data.

[0992] A user opens a dedicated input form on their device and enters the details of their used car. The input is the vehicle information (e.g., year, model, mileage, etc.) that the user fills in the form, and the output is structured data (e.g., JSON format) received by the server.

[0993] Step 2:

[0994] Data Standardization

[0995] The server converts the collected data from various formats into a single unified format using the Pandas library. Specifically, it standardizes the currency units of the pricing information (e.g., converting everything to USD) and converts the rating scale to a consistent standard. The input is vehicle data in different formats, and the output is a data frame in a unified format.

[0996] The server aggregates identical information fields (e.g., year and model) from different data sources to create a consistent dataset. The input is multiple data frames of vehicle data from different sources, and the output is an aggregated data frame.

[0997] Step 3:

[0998] Cleaning the data

[0999] The server detects and filters out inaccurate or incomplete data from the collected data. Specifically, it uses Pandas to detect NAN values ​​and outliers and remove or correct them. The input is a standardized data frame, and the output is a clean dataset with inaccurate data removed.

[1000] Step 4:

[1001] Data analysis

[1002] The server analyzes the standardized and cleaned data, first calculating basic statistics (mean, median, standard deviation, etc.) using Scikit-Learn or StatsModels. The input is the clean dataset, and the output is the statistical analysis results.

[1003] The server uses machine learning algorithms to extract patterns and trends, applying linear regression or random forests to analyze the relationship between specific model years and mileage. The input is the clean dataset, and the output is the predictions of the machine learning model.

[1004] Step 5:

[1005] Calculating value

[1006] The server calculates the current market value of the used car based on the analysis results. Specifically, it evaluates the value based on the average and median market prices of vehicles of the same age and condition. The inputs are the predictions of the machine learning model and market data, and the output is the calculated market value.

[1007] The server adjusts the final value, taking into account market trends and supply and demand balances. The inputs are the calculated market value and additional economic indicator data, and the output is the adjusted market value.

[1008] Step 6:

[1009] Generating and formatting results

[1010] The server formats the calculated value in a user-friendly format. It uses Matplotlib or Plotly to generate graphs and charts and converts them to JSON format. The input is the adjusted market value, and the output is the formatted data (JSON format).

[1011] Step 7:

[1012] Sending and displaying results

[1013] The server sends the formatted data to the user's device. The input is the formatted data (JSON format) and the output is the sent response.

[1014] The terminal analyzes the received data and displays it to the user. Using JavaScript D3.js, it draws line graphs showing the fluctuations in value depending on the model year and mileage, as well as histograms of market prices. The input is the received data (in JSON format), and the output is the visualized graph or chart.

[1015] Step 8:

[1016] Introducing the Emotion Engine

[1017] The server uses NLP libraries and TensorFlow to analyze emotions from the feedback provided by the user. Specifically, it processes text and voice data and recognizes emotions such as satisfaction, dissatisfaction, and excitement. The input is the user's feedback data, and the output is the analyzed emotional information.

[1018] The server stores the analyzed emotion information in a database. The input is the analyzed emotion information, and the output is a stored database entry.

[1019] Step 9:

[1020] Emotion-Based Adjustment

[1021] The server adjusts the value calculation process and presentation content based on the user's emotional information. It also adjusts the algorithm parameters based on dissatisfaction information about specific factors. The inputs are the emotional information and the parameters of the value assessment process, and the output is the adjusted value calculation result.

[1022] Step 10:

[1023] User Interaction

[1024] The user reviews the information provided and provides feedback and additional information to the system, for example, providing further vehicle details or comments. The input is the user's feedback and additional information, and the output is the data sent to the server.

[1025] The server collects user feedback and stores it in a database, which is used to adjust and improve future data analysis algorithms. The input is the user feedback data, and the output is the stored database entry.

[1026] (Application example 2)

[1027] 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."

[1028] Conventional value assessment systems only standardize and analyze collected data, making it difficult to appropriately reflect user feedback. Furthermore, because they do not take user emotions or satisfaction into account, it is difficult to improve the user experience or the quality of feedback. Therefore, there is a need to provide a more accurate and user-friendly value assessment system that recognizes user emotions and reflects them in feedback.

[1029] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1030] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating value based on the analysis results, means for analyzing user emotions, and means for adjusting feedback based on the analyzed emotions, thereby enabling more accurate value assessment that takes user emotions into consideration and improving user satisfaction.

[1031] A "database" is a system for systematically managing, storing, and retrieving large amounts of data.

[1032] "Collection methods" refers to the methods and techniques used to obtain data from various sources.

[1033] "Standardization measures" are methods for converting data that exists in different formats and units into a unified format.

[1034] "Means of analysis" refers to a method of analyzing collected and standardized data using statistical and machine learning techniques.

[1035] "Means of calculating value" refers to the method of calculating the market value of goods or services based on the results of the analysis.

[1036] "Means for presenting to the user" is a method for displaying the calculated value in a user-friendly format.

[1037] "Means for analyzing emotions" refers to technology that uses text data and voice data from users to recognize their emotional state.

[1038] The "means for adjusting feedback" is a method for adjusting the content of the user's feedback based on the analyzed emotional information.

[1039] "Inaccuracy removal measures" are methods for identifying and removing erroneous or incomplete information from collected data.

[1040] "Means for collecting feedback" refers to methods for collecting opinions and evaluation information from users.

[1041] "Means for storing feedback in a database" refers to a method for storing collected feedback information in a database.

[1042] "Means for improving analysis" are techniques that use stored feedback information to improve data analysis algorithms and methods.

[1043] The system for implementing this invention collects a large amount of data from a database, standardizes and analyzes it, calculates a value based on the results, and presents it to the user. Furthermore, it analyzes the user's emotions and adjusts feedback based on the results, thereby providing a more accurate and user-friendly value assessment.

[1044] The main components of the system include a server, a terminal, and a user.

[1045] server

[1046] Data collection method: The server collects a large amount of data from the database using APIs (Application Programming Interfaces) and other methods. Specifically, product information and market value data is obtained from multiple websites and databases. In some cases, scraping technology is used to extract information.

[1047] Data standardization measures: As the collected data exists in various formats, the currency units and evaluation scales are standardized. This is a process to maintain data consistency.

[1048] Data analysis methods: Standardized data is analyzed using statistical methods and machine learning algorithms to calculate statistical values ​​such as the mean, median, and standard deviation, and to identify specific trends and patterns.

[1049] Value calculation method: Based on the analysis results, we calculate the market value of each product in a fair and objective manner, using the average or median market price of products of the same age and condition.

[1050] Result presentation method: Generates data to present the calculated value to the user and sends it to the terminal in JSON format, graphs, charts, etc.

[1051] Sentiment analysis means: An emotion engine is used to analyze user feedback text and voice data to recognize the user's emotional state (e.g., satisfied, dissatisfied, excited).

[1052] Feedback adjustment: Adjust the feedback content and value calculation process based on the analyzed emotional information. For example, adjust the value for a specific factor that the user expressed dissatisfaction with or provide additional information.

[1053] Terminal

[1054] Data display means: Receives data sent from the server and displays the results using a user-friendly UI, such as graphs showing product age and price fluctuations, or recommendations based on user feedback.

[1055] User

[1056] Providing feedback: Users can input detailed product information and feedback into the system to improve the accuracy of data collection. Furthermore, the emotion engine analyzes the emotional information and provides appropriate feedback.

[1057] Specific examples

[1058] For example, if a user provides feedback such as "This book has great content and was reasonably priced," the server sends this text data to a sentiment analysis engine to analyze positive sentiment. This analysis information is reflected in the next value calculation process as an upward correction to the value.

[1059] Example prompt sentence:

[1060] This book is excellent and was reasonably priced.

[1061] In this way, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

[1062] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1063] Step 1:

[1064] The server collects product information and market value data from the database using APIs. The collected data is obtained from multiple websites and databases, sometimes using scraping techniques. The input is from multiple data sources, and the output is data in different formats.

[1065] Step 2:

[1066] The server normalizes the collected data, specifically by standardizing the currency unit (e.g., converting all prices to USD) and the rating scale. The input is the raw data collected in step 1, and the output is the normalized data converted into a consistent format.

[1067] Step 3:

[1068] The server analyzes the standardized data using statistical methods and machine learning algorithms to calculate statistics such as the mean, median, and standard deviation. It also extracts specific trends and patterns. The input is the standardized data, and the output is the statistical analysis results.

[1069] Step 4:

[1070] The server calculates the value based on the analysis results. It calculates the market value of each item in a fair and objective manner, and calculates the value using the average or median market price of items of the same age and condition. The input is the analysis result from Step 3, and the output is the calculated market value.

[1071] Step 5:

[1072] The server formats the data to present the calculated value to the user. The generated value data is sent to the terminal in a UI format that is easy for the user to understand (e.g., JSON format, graphs, charts). The input is market value data, and the output is the formatted data.

[1073] Step 6:

[1074] The terminal receives the data sent from the server and displays the results in a user-friendly UI. The displayed content includes graphs showing the model year and price fluctuations of products, as well as recommendations based on user feedback. The input is the formatted data, and the output is the results displayed in the UI.

[1075] Step 7:

[1076] Users input detailed product information and feedback into the system, for example, by providing impressions and ratings in text format, which improves the accuracy of data collection. The input is the user-provided feedback, and the output is the feedback data sent to the server.

[1077] Step 8:

[1078] The server sends the user's feedback text or voice data to the emotion analysis engine, which analyzes the user's emotional state (e.g., satisfied, dissatisfied, excited). The input is text or voice data, and the output is the analyzed emotional information.

[1079] Step 9:

[1080] The server adjusts the feedback content and value calculation process based on the analyzed emotion information. Specifically, it adjusts the value for specific factors that the user expressed dissatisfaction with and presents additional information. The input is emotion analysis information, and the output is the adjusted value data and additional information.

[1081] Through the above processing steps, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

[1082] 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.

[1083] 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.

[1084] 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.

[1085] [Fourth embodiment]

[1086] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1087] 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.

[1088] 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).

[1089] 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.

[1090] 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.

[1091] 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).

[1092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1093] 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.

[1094] 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.

[1095] 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.

[1096] 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.

[1097] 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.

[1098] 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."

[1099] The system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Specifically, this system collects data, standardizes it, analyzes it, calculates its value, and presents the results. The following scenario will be described as an example of how this system operates.

[1100] Example: Used car valuation system

[1101] Data collection

[1102] Server: Uses APIs to collect data such as vehicle year, mileage, model, manufacturer, price, and user ratings from multiple websites that provide used car information. It also obtains information from open and proprietary databases.

[1103] User: Enters detailed information about the used car he owns (e.g., specific optional equipment and maintenance history) through his own device, allowing for more specific data to be collected.

[1104] Data Standardization

[1105] Server: The collected data comes from a variety of sources and is not in a uniform format. The server converts this data into a uniform format. For example, it standardizes the currency units of price information, standardizes rating scales, and aligns different field names and data types into a consistent format.

[1106] Data analysis

[1107] Server: Feeds the standardized data into analytics tools, which use statistical methods (e.g., mean, median, standard deviation) to calculate baseline characteristics. Additionally, machine learning algorithms (e.g., linear regression and clustering) are used to identify patterns and trends. For example, estimating the rate of depreciation for a vehicle of a particular model year after a certain number of miles.

[1108] Calculating value

[1109] Server: Based on the analysis results, the current market value of each used vehicle is calculated, taking into account the average price of the same model and year, the impact of specific conditions (such as mileage and optional equipment), market trends, and the balance of supply and demand.

[1110] Presentation of results

[1111] Server: The calculated value is formatted in a user-friendly format. The formatted data is sent to the user's device.

[1112] Device: The results are displayed on the user's device, using visual graphs and charts to clearly explain how each factor affects the value of a used car, such as a line graph showing how value varies by age and mileage.

[1113] Through this series of processes, users can objectively understand how much their used car is worth in the current market and obtain a fair and impartial valuation. This system can also be applied to valuing various products and services, and can provide highly accurate results by utilizing a wide range of data.

[1114] The processing flow will be explained below.

[1115] Step 1: Data collection

[1116] Server: Using APIs, the server obtains vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. It also uses scraping technology to extract the necessary information from web pages.

[1117] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[1118] Step 2: Standardize the data

[1119] Server: The collected data exists in various formats, so it is first converted into a unified format. For example, the currency units for price information are unified and rating scales are aligned to a consistent standard.

[1120] Server: Additionally, it aggregates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[1121] Step 3: Cleaning the data

[1122] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[1123] Step 4: Analyze the data

[1124] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[1125] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[1126] Step 5: Calculate value

[1127] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[1128] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[1129] Step 6: Generate and format the results

[1130] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[1131] Step 7: Send and view results

[1132] Server: Sends the formatted data to the user's device.

[1133] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[1134] Step 8: User Interaction

[1135] User: Can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) into the system.

[1136] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[1137] Example 1

[1138] 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."

[1139] In conventional value assessment systems, data collection sources are limited, making it difficult to integrate and utilize information from diverse data sources. Furthermore, data standardization and analysis lacked standardized formats and insufficient application of machine learning algorithms, resulting in problems with reduced assessment accuracy. Furthermore, the results were not presented in a user-friendly manner, making it difficult for users to understand the information obtained.

[1140] 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.

[1141] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating a value based on the analysis results, means for presenting the calculated value to a user, means for collecting information from online sources and users, means for converting the data into a unified format, means for analyzing the data using a machine learning algorithm, and means for displaying the results in a visual format. This enables integrated analysis of information collected from various data sources, and improves analytical accuracy through the application of a unified format and machine learning. Furthermore, displaying the results in a user-friendly format allows users to easily understand and use the information.

[1142] A "database" is a system for systematically storing specific information and efficiently accessing and managing it.

[1143] "Data collection" is the process of obtaining necessary information from various sources.

[1144] "Standardization" is the process of unifying the format and units of collected data and managing the data in a consistent manner.

[1145] "Data analytics" is the process of analyzing collected and standardized data using statistical methods and machine learning algorithms to find useful information and patterns.

[1146] "Pricing" is the process of calculating the current market value of an object based on the results of data analysis.

[1147] "Presenting to the user" is the process of providing the calculated value to the user in a visually easy-to-understand format.

[1148] An "online source" is a data source accessible via the Internet.

[1149] "Information collection methods" are the technical means and identification methods used to obtain the required data from various sources.

[1150] "Format conversion" is the process of converting data of different formats and units into a unified format.

[1151] A "machine learning algorithm" is a computational model that learns from large amounts of data and automatically finds patterns and features.

[1152] A "visual format" is a format that presents data or information in an easy-to-read visual way, such as a graph or chart.

[1153] The system for implementing this invention collects a large amount of data from a database, standardizes it into a unified format, calculates value through analysis using a machine learning algorithm, and presents it to the user. A specific implementation method of this system is described below.

[1154] Data collection

[1155] Server: The server collects data from multiple websites that provide used car information. To do this, the server calls the API of each website to obtain data such as the vehicle's year, mileage, model, manufacturer, price, and user ratings. For example, it obtains JSON-formatted data from a website that provides data on a specific vehicle, parses it, and stores it in a local database. It is effective to use a relational database such as MySQL or PostgreSQL as the database.

[1156] User: The user uses their own device to enter details about their used car, such as the model year, mileage, specific options, and maintenance history, through a dedicated application or web form. The data entered by the user is sent to the server in real time and integrated with the collected data.

[1157] Data Standardization

[1158] Server: The server handles the process of unifying the format and units of the collected data. For example, if price information is stored in different currencies, it converts it all to yen. It also applies specific mapping rules to unify different field names for data retrieved from multiple data sources. Specifically, it uses the Python pandas library to create a data frame and rename columns based on the specified mapping.

[1159] Data analysis

[1160] Server: To analyze the standardized data, the server uses machine learning algorithms. For example, it uses Python's scikit-learn library to perform linear regression models and clustering. The analysis method not only calculates basic statistics of the data (mean, median, standard deviation), but also evaluates the impact of different parameters on vehicle value. Linear regression can be used to model the impact of model year and mileage on price.

[1161] Calculating value

[1162] Server: Based on the analysis results, the server calculates the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific conditions (e.g., mileage, optional equipment). The server also adjusts the value to take real-time market trends into account. For example, it performs trend analysis on historical data sets to take into account price fluctuations over a certain period of time.

[1163] Presentation of results

[1164] Server: The calculated value is formatted in a user-friendly format and sent to the user's device. Visual graphs and charts are generated to clearly show how each factor affects the value of a used car. For example, the JSON formatted data can be interpreted on the client side and a visualization library such as Chart.js can be used to draw line graphs and bar charts.

[1165] Terminal: The terminal analyzes the received data and displays it to the user in an easy-to-understand format. A dedicated interface allows the user to intuitively understand the valuation results. For example, a line graph showing the fluctuations in value based on model year and mileage can be displayed, allowing the user to visually see the impact of each factor on the price.

[1166] Examples of concrete examples and prompts

[1167] For example, consider a user wanting to value their 2015 vehicle. Using a smartphone application, the user inputs information such as the model year, mileage, optional equipment, and maintenance history. This information is then aggregated and analyzed on a server along with collected online data. The analysis results are then sent to the user's device and presented in a visual format.

[1168] Example prompt sentence:

[1169] "Write a program to assess the value of used cars. Your program should collect data from multiple online sources, convert it into a unified format, and then use machine learning algorithms to analyze it and calculate a final market value. The system should also collect specific vehicle information from the user (year, mileage, model, maintenance history, etc.). The results of the analysis should be displayed visually."

[1170] According to the present invention, highly accurate value assessment using a wide range of diverse data is possible, and highly reliable assessment information can be provided to users.

[1171] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1172] Step 1: Data collection

[1173] Input: API endpoint of online source, user-entered used car details (year, mileage, model, make, price, user ratings, etc.).

[1174] How it works: The server calls each website's API to retrieve the required vehicle data from online sources. For example, it uses the requests library to send a GET request and parses the JSON data received as a response. The vehicle information entered by the user through a dedicated application is sent to the server via HTTPS and stored in a database.

[1175] Output: Unified dataset, user input data.

[1176] Step 2: Standardize the data

[1177] Input: Integrated dataset, user input data.

[1178] Specific operation: If the format or units of collected data are not standardized, the server performs processing to standardize them. For example, it creates a data frame using the pandas library, converts all price information to yen, and applies mapping rules to standardize field names. It also standardizes different data types (e.g., converting strings to numbers).

[1179] Output: A standardized dataset.

[1180] Step 3: Analyze the data

[1181] Input: Standardized dataset.

[1182] What it does: The server feeds the standardized data to analytics tools. It uses Python's pandas library to calculate basic statistics (mean, median, standard deviation). It then uses the scikit-learn library to train machine learning models. For example, it uses a linear regression model to analyze the impact of vehicle age and mileage on price, and a clustering algorithm to group similar vehicles.

[1183] Output: Analysis results, machine learning model.

[1184] Step 4: Calculate value

[1185] Input: Analysis results, machine learning model.

[1186] How it works: The server uses the analysis results to calculate the current market value of each used car, taking into account the average price of the same model and year, as well as the impact of specific factors (e.g., mileage and optional equipment). It also monitors market trends in real time and makes adjustments as needed. Python code is used to input new data into the predictive model and calculate prices.

[1187] Output: Final market value.

[1188] Step 5: Presenting the results

[1189] Input: Final market value.

[1190] What it does: The server formats the results in a user-friendly format and sends them to the user's device. The JSON formatted data is interpreted on the client side and visualized using a charting library (e.g. Chart.js, D3.js). The terminal application generates detailed graphs and charts for each factor to display the results to the user in an easy-to-understand manner.

[1191] Output: Visualized evaluation results.

[1192] This series of processes allows users to know the accurate market value of their used car in real time.

[1193] (Application example 1)

[1194] 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."

[1195] Conventional product price evaluation systems require users to perform multiple manual operations to obtain product information, making it difficult to provide real-time evaluations. Furthermore, the information obtained is often inaccurate, forcing users to rely on unreliable price information. As a result, consumers are unable to obtain fair and immediate price evaluations, hindering their purchasing decisions.

[1196] 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.

[1197] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for presenting the calculated value to the user, means for scanning product information in real time, means for analyzing the scanned information and calculating the value, and means for visually displaying the calculated value, thereby enabling users to instantly obtain reliable price information in the store and make fair and appropriate purchasing decisions.

[1198] A "database" is a system for managing and operating large amounts of electronically stored data.

[1199] "Means for collecting data" refers to the function for obtaining necessary information from external data sources.

[1200] "Means for standardizing data" refers to the function of converting collected data into a unified format and scale.

[1201] "Means of analyzing data" refers to functions that use statistical methods and machine learning algorithms to find patterns and trends in data.

[1202] "Means for calculating value" refers to a function for evaluating and calculating the market value of an object based on analyzed data.

[1203] The "means for presenting value to the user" is a function for displaying the calculated market value in a format that is easy for the user to understand.

[1204] "Means for scanning product information in real time" is a function that allows a user to instantly obtain information on an object as digital data by taking a picture of the object with a camera or the like.

[1205] "Means for analyzing scanned information and calculating value" refers to a function for analyzing and evaluating product value based on product data acquired in real time.

[1206] "Visual display means" refers to a function for providing analysis results and values ​​to users in a visual format such as a graph or chart.

[1207] The system for implementing this invention includes specific hardware and software components for data collection, standardization, analysis, value calculation, and result presentation. Specifically, it is a system that allows users to evaluate products in physical stores in real time using smart glasses and a smartphone. An example of its operation is described below.

[1208] Hardware Configuration

[1209] Smart glasses: Contains a camera for scanning product information and a display that visually displays the results to the user.

[1210] Smartphone: A device that works in conjunction with smart glasses, communicates with the server, and processes data.

[1211] Server: High-performance computing resources for data collection, normalization, analysis, and value calculation.

[1212] Software Configuration

[1213] API: An interface for retrieving product information from a database or external data source.

[1214] Data standardization tools: Software that converts collected data into a uniform format.

[1215] Analysis tools: Software that uses machine learning libraries such as TensorFlow and Scikit-learn to analyze data and find patterns.

[1216] User Interface: Software that generates graphs and charts for display on smart glasses and smartphones.

[1217] Program processing explanation

[1218] 1. Data Collection

[1219] The server uses APIs to collect product information from online marketplaces and specialty sites, including product names, prices, and ratings, as well as inventory data and pricing information from physical stores.

[1220] 2. Data Standardization

[1221] The server standardizes the collected data and converts it into a unified format, ensuring uniform currency units for pricing information and consistent rating scales.

[1222] 3. Data Analysis

[1223] The server analyzes the standardized data and uses statistical methods and machine learning algorithms to find patterns and trends, such as how certain characteristics affect the value of a product.

[1224] 4. Value calculation

[1225] The server calculates the market value of the product based on the analysis results, taking into account the average price of the same category and the influence of specific conditions (e.g., year of manufacture and features).

[1226] 5. Presentation of results

[1227] The analysis results from the server are sent back to the smart glasses via the smartphone, which overlay the results on the user's field of vision, providing detailed information in real time. Visual graphs and charts are also displayed, helping users understand how the product's value was calculated.

[1228] Specific examples

[1229] A user puts on smart glasses, walks through a store, and focuses their gaze on a particular product. The smart glasses' camera scans the product and recognizes its barcode or QR code. The scanned data is then sent via Bluetooth to a smartphone, which then communicates with a server. The server quickly calculates the product's value based on the collected and standardized data, and the result is sent back to the smart glasses via the smartphone. The user can then make the necessary purchasing decisions while looking at the information displayed in their field of vision.

[1230] Generative AI model prompt example

[1231] "This product is a new model manufactured in 2023. The market price is approximately 30,000 yen, but please calculate the value taking into account specific features (water resistance, battery life, etc.)."

[1232] As described above, the present invention allows for the instant acquisition of highly reliable price information in a store, thereby supporting fair and appropriate purchasing decisions.

[1233] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1234] Step 1:

[1235] A user uses smart glasses to scan an item. The input is the item's barcode or QR code, and the output is digital data to send the product data to a smartphone. The camera in the smart glasses scans the item and sends the data to the smartphone via Bluetooth.

[1236] Step 2:

[1237] The smartphone receives the scanned product data and sends it to the server. The input is the product information that received the data, and the output is the data sent to the server. The smartphone sends the data to the server via the Internet.

[1238] Step 3:

[1239] The server uses APIs to collect additional product information from various databases. The input is the scanned product data, and the output is data containing detailed product information. The server makes API calls to obtain information such as product name, price, and ratings.

[1240] Step 4:

[1241] The server standardizes the collected data. The input is product information collected in various formats, and the output is data in a unified format. The server converts the data's currency units and rating scales into a consistent format, and standardizes the data's field names and data types.

[1242] Step 5:

[1243] The server analyzes the standardized data. The input is the standardized product information, and the output is data containing the analysis results. The server uses machine learning algorithms (e.g., TensorFlow or Scikit-learn) to perform statistical analysis and pattern detection.

[1244] Step 6:

[1245] The server calculates the market value of the product based on the analysis results. The input is the analyzed data, and the output is data containing the product's current market value. The server uses statistical methods to evaluate the value, taking into account the average price in the same category and the influence of specific conditions.

[1246] Step 7:

[1247] The server formats the calculated market value for the user interface. The input is the market value data of the product, and the output is the formatted data in a format that is easy for the user to understand. The server generates graphs and charts and formats the data in a visually easy-to-understand format.

[1248] Step 8:

[1249] The smartphone transmits the data received from the server to the smart glasses. The input is the formatted product value data, and the output is data transmission to the smart glasses. The smartphone transmits the data to the smart glasses via Bluetooth or other communication means.

[1250] Step 9:

[1251] The smart glasses visually display the received data to the user. The input is formatted product value data, and the output is information overlaid on the user's field of view. The smart glasses display market value, graphs, charts, and other information on the display, allowing the user to make purchasing decisions.

[1252] Through the above steps, users can obtain product information in real time within a physical store and make purchasing decisions based on fair and reliable price information.

[1253] 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.

[1254] A system for implementing this invention includes specific hardware and software components for statistically calculating the value of any object, such as an object, service, or location. Furthermore, by combining it with an emotion engine that recognizes user emotions, the accuracy and usefulness of user feedback can be improved. Specifically, this system performs data collection, standardization, analysis, value calculation, result presentation, and emotion analysis. The following scenario will be described as an example of how this system operates.

[1255] Example: Used car valuation system

[1256] Data collection

[1257] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[1258] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[1259] Data Standardization

[1260] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[1261] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[1262] Cleaning the data

[1263] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[1264] Data analysis

[1265] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[1266] Server: Additionally, machine learning algorithms are used to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation associated with specific model years and mileage.

[1267] Calculating value

[1268] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[1269] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[1270] Generating and formatting results

[1271] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[1272] Sending and displaying results

[1273] Server: Sends the formatted data to the user's device.

[1274] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[1275] Introducing the Emotion Engine

[1276] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[1277] Server: Analyzed emotional information is stored in a database to improve the accuracy and usefulness of user feedback.

[1278] Emotion-Based Adjustment

[1279] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[1280] User Interaction

[1281] User: The user can review the information provided and provide feedback or additional information (e.g., further vehicle details or comments) to the system. Based on the emotional information analyzed by the emotion engine, appropriate feedback is requested.

[1282] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[1283] Through this series of processes, users can not only objectively understand how much their used car is worth in the current market, but also obtain a more accurate value assessment by taking into account the emotional information in the feedback.

[1284] The processing flow will be explained below.

[1285] Step 1: Data collection

[1286] Server: Uses APIs to obtain vehicle details (year, mileage, model, manufacturer, price, user ratings, etc.) from multiple websites and databases that provide used car information. Also, uses scraping technology to extract the necessary information from web pages.

[1287] Users use their own devices to enter detailed information about their used vehicles (e.g., specific options and maintenance history), which increases the accuracy of the collected data.

[1288] Step 2: Standardize the data

[1289] Server: The collected data exists in various formats, so it is converted into a unified format. For example, the currency units for price information are standardized and rating scales are aligned to a consistent standard.

[1290] Server: Consolidates identical fields of information (e.g., year and model) from different data sources to create a consistent data set.

[1291] Step 3: Cleaning the data

[1292] Server: Detects and filters out inaccurate or incomplete data collected, for example, eliminating obviously incorrect price or model year information.

[1293] Step 4: Analyze the data

[1294] Server: Feeds the standardized and cleaned data into the analysis tool and calculates basic statistics (e.g., mean, median, standard deviation).

[1295] Server: Uses machine learning algorithms to analyze the data and extract specific patterns and trends, such as identifying trends in depreciation due to a particular model year and mileage.

[1296] Step 5: Calculate value

[1297] Server: Based on the analysis, we use an unbiased and objective method to calculate the current market value of each used vehicle, using the average or median market value of vehicles of the same age and condition.

[1298] Server: Adjust the final value taking into account market trends and the balance of supply and demand.

[1299] Step 6: Generate and format the results

[1300] Server: Formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, formatting the result data in JSON format including graphs and charts.

[1301] Step 7: Send and view results

[1302] Server: Sends the formatted data to the user's device.

[1303] Terminal: Analyzes the received data and displays the results in a user-friendly UI, such as a line graph showing the fluctuations in value by model year and mileage, or a histogram of market prices.

[1304] Step 8: Implementing the Emotion Engine

[1305] Server: Analyzes the feedback provided by the user to the system using an emotion engine. Specifically, it recognizes the user's emotions (e.g., satisfaction, dissatisfaction, excitement, etc.) based on text and voice data.

[1306] Server: Stores the analyzed emotional information in a database to improve the accuracy and usefulness of feedback.

[1307] Step 9: Emotional Adjustment

[1308] Server: Based on the user's emotional information, the server adjusts the further value calculation process and presentation content. For example, it adjusts the value for specific factors that the user expressed dissatisfaction with, or presents additional information to improve user satisfaction.

[1309] Step 10: User Interaction

[1310] User: Review the information provided and can enter feedback or additional information into the system (e.g., further vehicle details or comments) based on the emotional information analyzed by the emotion engine.

[1311] Server: Collects user feedback and stores it in a database, which can be used to adjust and improve data analysis algorithms in the future.

[1312] Example 2

[1313] 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."

[1314] In conventional data analysis systems, the inaccuracy and incompleteness of collected data affects the analysis results, making it difficult to perform highly accurate value assessments. Furthermore, user feedback was not properly collected, making further analysis and adjustments based on emotional information difficult. This made improving the user experience a challenge.

[1315] 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.

[1316] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for cleaning the standardized data, means for analyzing the cleaned data, means for calculating value based on the analysis results, means for presenting the calculated value to the user, means for analyzing the user's emotions, and means for adjusting the value calculation process and presentation content based on the analyzed emotional information. This makes it possible to improve the accuracy of the collected data and to evaluate value taking user emotional information into consideration.

[1317] A "database" is a system for efficiently storing and managing a large amount of data.

[1318] "Collection" is the process of gathering the necessary data from multiple sources.

[1319] "Standardization" is the process of converting data that exists in different formats into a unified format.

[1320] "Cleaning" is the process of detecting and removing inaccurate or incomplete data.

[1321] "Analysis" is the process of analyzing data and extracting valuable information and patterns.

[1322] "Value calculation" is the process of quantifying the value of data based on collected data and analysis results.

[1323] "Presentation" is the process of displaying calculated values ​​and analytical results in a user-friendly format.

[1324] "Sentiment analysis" is the process of recognizing and analyzing user emotions based on user feedback and data.

[1325] "Tuning" is the process of improving a process or display based on the results of analysis or calculations.

[1326] A system for implementing this invention calculates the market value of, for example, a used car based on information provided by users and data on the Internet. This system includes specific hardware and software components, enabling improved accuracy of collected data and value assessment that takes user emotion information into account.

[1327] Hardware and Software Configuration

[1328] Server: Retrieves required information from multiple websites and databases using APIs, scrapes information from web pages using Python's Beautiful Soup and Scrapy, standardizes and cleans data using Python's Pandas and Numpy, and performs data analysis using Scikit-Learn and TensorFlow.

[1329] Terminal: Provides an interface for users to input information. This interface includes a form for users to enter details about their used car. The information entered is sent to a database and analyzed by the server.

[1330] Emotion Engine: Analyzes emotions from user feedback using NLP libraries (e.g., NLTK and spaCy) and TensorFlow, and stores the user's emotional information in a database for further tuning and improving the data analysis algorithm.

[1331] Specific examples

[1332] As an example of how this system works, we will explain a used car value assessment system. The server obtains detailed vehicle information (year, mileage, model, manufacturer, price, user ratings, etc.) via API from, for example, "used car information site A" or "used car transaction database B." Python's Beautiful Soup and Scrapy are used to automatically extract the necessary information from web pages.

[1333] Users use their own devices to open a dedicated input form and enter detailed information about their used car (e.g., specific optional equipment and maintenance history). This information is sent to the server and stored in a database.

[1334] The server standardizes and cleans the collected data using Pandas and Numpy to remove inaccurate or incomplete data, then performs data analysis using Scikit-Learn and TensorFlow to extract specific patterns and trends. Based on the analysis results, the server calculates the market value of each used car in an unbiased and objective manner.

[1335] The server then formats the calculated values ​​in a user-friendly format and generates the data for the response, for example, using Matplotlib or Plotly to generate graphs and charts, and converts them to JSON format.

[1336] The server sends this formatted data to the user's device, which then uses the JavaScript D3.js to draw a line graph showing the fluctuations in value based on model year and mileage, as well as a histogram of market prices.

[1337] The emotion engine analyzes text and voice data to recognize user emotions (e.g., satisfaction, dissatisfaction, excitement, etc.). This emotion information is also stored in the database and used to improve the accuracy and usefulness of user feedback.

[1338] Prompt Sentence Examples

[1339] "Evaluate the market value of a used car based on its age and mileage. Include any specific optional equipment and maintenance history in your evaluation."

[1340] "Reassess the value of used cars taking into account user emotional feedback and suggest improvements."

[1341] This system not only allows users to objectively understand how much their used car is worth in the current market, but also allows them to receive a more accurate value assessment based on emotional information.

[1342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1343] Step 1:

[1344] Data collection

[1345] The server uses APIs to obtain detailed vehicle information from multiple websites and databases that provide used car information. Specifically, it sends requests to the APIs of each website to obtain data including model year, mileage, model, manufacturer, price, user ratings, etc. The input is the API request parameters and search conditions, and the output is vehicle information data in JSON format.

[1346] The server uses Python's Beautiful Soup or Scrapy to scrape information from web pages. It parses the HTML of the web page and extracts the required information. The input is the web page's URL or HTML source, and the output is the extracted text data or table data.

[1347] A user opens a dedicated input form on their device and enters the details of their used car. The input is the vehicle information (e.g., year, model, mileage, etc.) that the user fills in the form, and the output is structured data (e.g., JSON format) received by the server.

[1348] Step 2:

[1349] Data Standardization

[1350] The server converts the collected data from various formats into a single unified format using the Pandas library. Specifically, it standardizes the currency units of the pricing information (e.g., converting everything to USD) and converts the rating scale to a consistent standard. The input is vehicle data in different formats, and the output is a data frame in a unified format.

[1351] The server aggregates identical information fields (e.g., year and model) from different data sources to create a consistent dataset. The input is multiple data frames of vehicle data from different sources, and the output is an aggregated data frame.

[1352] Step 3:

[1353] Cleaning the data

[1354] The server detects and filters out inaccurate or incomplete data from the collected data. Specifically, it uses Pandas to detect NAN values ​​and outliers and remove or correct them. The input is a standardized data frame, and the output is a clean dataset with inaccurate data removed.

[1355] Step 4:

[1356] Data analysis

[1357] The server analyzes the standardized and cleaned data, first calculating basic statistics (mean, median, standard deviation, etc.) using Scikit-Learn or StatsModels. The input is the clean dataset, and the output is the statistical analysis results.

[1358] The server uses machine learning algorithms to extract patterns and trends, applying linear regression or random forests to analyze the relationship between specific model years and mileage. The input is the clean dataset, and the output is the predictions of the machine learning model.

[1359] Step 5:

[1360] Calculating value

[1361] The server calculates the current market value of the used car based on the analysis results. Specifically, it evaluates the value based on the average and median market prices of vehicles of the same age and condition. The inputs are the predictions of the machine learning model and market data, and the output is the calculated market value.

[1362] The server adjusts the final value, taking into account market trends and supply and demand balances. The inputs are the calculated market value and additional economic indicator data, and the output is the adjusted market value.

[1363] Step 6:

[1364] Generating and formatting results

[1365] The server formats the calculated value in a user-friendly format. It uses Matplotlib or Plotly to generate graphs and charts and converts them to JSON format. The input is the adjusted market value, and the output is the formatted data (JSON format).

[1366] Step 7:

[1367] Sending and displaying results

[1368] The server sends the formatted data to the user's device. The input is the formatted data (JSON format) and the output is the sent response.

[1369] The terminal analyzes the received data and displays it to the user. Using JavaScript D3.js, it draws line graphs showing the fluctuations in value depending on the model year and mileage, as well as histograms of market prices. The input is the received data (in JSON format), and the output is the visualized graph or chart.

[1370] Step 8:

[1371] Introducing the Emotion Engine

[1372] The server uses NLP libraries and TensorFlow to analyze emotions from the feedback provided by the user. Specifically, it processes text and voice data and recognizes emotions such as satisfaction, dissatisfaction, and excitement. The input is the user's feedback data, and the output is the analyzed emotional information.

[1373] The server stores the analyzed emotion information in a database. The input is the analyzed emotion information, and the output is a stored database entry.

[1374] Step 9:

[1375] Emotion-Based Adjustment

[1376] The server adjusts the value calculation process and presentation content based on the user's emotional information. It also adjusts the algorithm parameters based on dissatisfaction information about specific factors. The inputs are the emotional information and the parameters of the value assessment process, and the output is the adjusted value calculation result.

[1377] Step 10:

[1378] User Interaction

[1379] The user reviews the information provided and provides feedback and additional information to the system, for example, providing further vehicle details or comments. The input is the user's feedback and additional information, and the output is the data sent to the server.

[1380] The server collects user feedback and stores it in a database, which is used to adjust and improve future data analysis algorithms. The input is the user feedback data, and the output is the stored database entry.

[1381] (Application example 2)

[1382] 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."

[1383] Conventional value assessment systems only standardize and analyze collected data, making it difficult to appropriately reflect user feedback. Furthermore, because they do not take user emotions or satisfaction into account, it is difficult to improve the user experience or the quality of feedback. Therefore, there is a need to provide a more accurate and user-friendly value assessment system that recognizes user emotions and reflects them in feedback.

[1384] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1385] In this invention, the server includes means for collecting a large amount of data from a database, means for standardizing the collected data, means for analyzing the standardized data, means for calculating value based on the analysis results, means for analyzing user emotions, and means for adjusting feedback based on the analyzed emotions, thereby enabling more accurate value assessment that takes user emotions into consideration and improving user satisfaction.

[1386] A "database" is a system for systematically managing, storing, and retrieving large amounts of data.

[1387] "Collection methods" refers to the methods and techniques used to obtain data from various sources.

[1388] "Standardization measures" are methods for converting data that exists in different formats and units into a unified format.

[1389] "Means of analysis" refers to a method of analyzing collected and standardized data using statistical and machine learning techniques.

[1390] "Means of calculating value" refers to the method of calculating the market value of goods or services based on the results of the analysis.

[1391] "Means for presenting to the user" is a method for displaying the calculated value in a user-friendly format.

[1392] "Means for analyzing emotions" refers to technology that uses text data and voice data from users to recognize their emotional state.

[1393] The "means for adjusting feedback" is a method for adjusting the content of the user's feedback based on the analyzed emotional information.

[1394] "Inaccuracy removal measures" are methods for identifying and removing erroneous or incomplete information from collected data.

[1395] "Means for collecting feedback" refers to methods for collecting opinions and evaluation information from users.

[1396] "Means for storing feedback in a database" refers to a method for storing collected feedback information in a database.

[1397] "Means for improving analysis" are techniques that use stored feedback information to improve data analysis algorithms and methods.

[1398] The system for implementing this invention collects a large amount of data from a database, standardizes and analyzes it, calculates a value based on the results, and presents it to the user. Furthermore, it analyzes the user's emotions and adjusts feedback based on the results, thereby providing a more accurate and user-friendly value assessment.

[1399] The main components of the system include a server, a terminal, and a user.

[1400] server

[1401] Data collection method: The server collects a large amount of data from the database using APIs (Application Programming Interfaces) and other methods. Specifically, product information and market value data is obtained from multiple websites and databases. In some cases, scraping technology is used to extract information.

[1402] Data standardization measures: As the collected data exists in various formats, the currency units and evaluation scales are standardized. This is a process to maintain data consistency.

[1403] Data analysis methods: Standardized data is analyzed using statistical methods and machine learning algorithms to calculate statistical values ​​such as the mean, median, and standard deviation, and to identify specific trends and patterns.

[1404] Value calculation method: Based on the analysis results, we calculate the market value of each product in a fair and objective manner, using the average or median market price of products of the same age and condition.

[1405] Result presentation method: Generates data to present the calculated value to the user and sends it to the terminal in JSON format, graphs, charts, etc.

[1406] Sentiment analysis means: An emotion engine is used to analyze user feedback text and voice data to recognize the user's emotional state (e.g., satisfied, dissatisfied, excited).

[1407] Feedback adjustment: Adjust the feedback content and value calculation process based on the analyzed emotional information. For example, adjust the value for a specific factor that the user expressed dissatisfaction with or provide additional information.

[1408] Terminal

[1409] Data display means: Receives data sent from the server and displays the results using a user-friendly UI, such as graphs showing product age and price fluctuations, or recommendations based on user feedback.

[1410] User

[1411] Providing feedback: Users can input detailed product information and feedback into the system to improve the accuracy of data collection. Furthermore, the emotion engine analyzes the emotional information and provides appropriate feedback.

[1412] Specific examples

[1413] For example, if a user provides feedback such as "This book has great content and was reasonably priced," the server sends this text data to a sentiment analysis engine to analyze positive sentiment. This analysis information is reflected in the next value calculation process as an upward correction to the value.

[1414] Example prompt sentence:

[1415] This book is excellent and was reasonably priced.

[1416] In this way, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

[1417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1418] Step 1:

[1419] The server collects product information and market value data from the database using APIs. The collected data is obtained from multiple websites and databases, sometimes using scraping techniques. The input is from multiple data sources, and the output is data in different formats.

[1420] Step 2:

[1421] The server normalizes the collected data, specifically by standardizing the currency unit (e.g., converting all prices to USD) and the rating scale. The input is the raw data collected in step 1, and the output is the normalized data converted into a consistent format.

[1422] Step 3:

[1423] The server analyzes the standardized data using statistical methods and machine learning algorithms to calculate statistics such as the mean, median, and standard deviation. It also extracts specific trends and patterns. The input is the standardized data, and the output is the statistical analysis results.

[1424] Step 4:

[1425] The server calculates the value based on the analysis results. It calculates the market value of each item in a fair and objective manner, and calculates the value using the average or median market price of items of the same age and condition. The input is the analysis result from Step 3, and the output is the calculated market value.

[1426] Step 5:

[1427] The server formats the data to present the calculated value to the user. The generated value data is sent to the terminal in a UI format that is easy for the user to understand (e.g., JSON format, graphs, charts). The input is market value data, and the output is the formatted data.

[1428] Step 6:

[1429] The terminal receives the data sent from the server and displays the results in a user-friendly UI. The displayed content includes graphs showing the model year and price fluctuations of products, as well as recommendations based on user feedback. The input is the formatted data, and the output is the results displayed in the UI.

[1430] Step 7:

[1431] Users input detailed product information and feedback into the system, for example, by providing impressions and ratings in text format, which improves the accuracy of data collection. The input is the user-provided feedback, and the output is the feedback data sent to the server.

[1432] Step 8:

[1433] The server sends the user's feedback text or voice data to the emotion analysis engine, which analyzes the user's emotional state (e.g., satisfied, dissatisfied, excited). The input is text or voice data, and the output is the analyzed emotional information.

[1434] Step 9:

[1435] The server adjusts the feedback content and value calculation process based on the analyzed emotion information. Specifically, it adjusts the value for specific factors that the user expressed dissatisfaction with and presents additional information. The input is emotion analysis information, and the output is the adjusted value data and additional information.

[1436] Through the above processing steps, the system can provide a more accurate value assessment using feedback that reflects the user's emotions.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] FIG. 9 illustrates 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 behaviors 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.

[1442] 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.

[1443] 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).

[1444] 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.

[1445] 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."

[1446] 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.

[1447] 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).

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] The following is further disclosed regarding the above embodiment.

[1459] (Claim 1)

[1460] a means for collecting a large amount of data from a database;

[1461] a means of standardizing the collected data;

[1462] a means for analyzing the standardized data;

[1463] A means for calculating value based on the analysis results;

[1464] The system includes a means for presenting the calculated value to a user.

[1465] (Claim 2)

[1466] 10. The system of claim 1, further comprising means for filtering out inaccuracies in the collected data.

[1467] (Claim 3)

[1468] a means for collecting feedback from users;

[1469] a means for storing the collected feedback in a database;

[1470] 10. The system of claim 1, further comprising means for improving future data analysis based on the stored feedback.

[1471] "Example 1"

[1472] (Claim 1)

[1473] a means for collecting a large amount of data from a database;

[1474] a means of standardizing the collected data;

[1475] a means for analyzing the standardized data;

[1476] A means for calculating value based on the analysis results;

[1477] A means for presenting the calculated value to the user;

[1478] a means of collecting information from online sources and users;

[1479] a means of converting the data into a unified format;

[1480] a means for analyzing the data using a machine learning algorithm;

[1481] The system includes a means for displaying the results in a visual format.

[1482] (Claim 2)

[1483] 10. The system of claim 1, further comprising means for filtering out inaccuracies in the collected data.

[1484] (Claim 3)

[1485] a means for collecting feedback from users;

[1486] a means for storing the collected feedback in a database;

[1487] 10. The system of claim 1, further comprising means for improving future data analysis based on the stored feedback.

[1488] "Application Example 1"

[1489] (Claim 1)

[1490] a means for collecting a large amount of data from a database;

[1491] a means of standardizing the collected data;

[1492] a means for analyzing the standardized data;

[1493] A means for calculating value based on the analysis results;

[1494] A means for presenting the calculated value to the user;

[1495] A means of scanning product information in real time;

[1496] A means of analyzing the scanned information and calculating its value;

[1497] The system includes a means for visually displaying the calculated value.

[1498] (Claim 2)

[1499] 10. The system of claim 1, further comprising means for filtering out inaccuracies in the collected data.

[1500] (Claim 3)

[1501] a means for collecting feedback from users;

[1502] a means for storing the collected feedback in a database;

[1503] 10. The system of claim 1, further comprising means for improving future data analysis based on the stored feedback.

[1504] "Example 2: Combining Emotion Engines"

[1505] (Claim 1)

[1506] a means for collecting a large amount of data from a database;

[1507] a means of standardizing the collected data;

[1508] a means of cleaning the standardized data;

[1509] a means for analyzing the cleaned data;

[1510] A means for calculating value based on the analysis results;

[1511] A means for presenting the calculated value to the user;

[1512] means for analyzing user emotions;

[1513] A system that includes a means for adjusting the value calculation process and presentation content based on analyzed emotional information.

[1514] (Claim 2)

[1515] 10. The system of claim 1, further comprising means for filtering out inaccuracies in the collected data.

[1516] (Claim 3)

[1517] a means for collecting feedback from users;

[1518] a means for storing the collected feedback in a database;

[1519] 10. The system of claim 1, further comprising means for improving future data analysis based on the stored feedback and the analyzed emotional information.

[1520] "Application example 2 when combining emotion engines"

[1521] (Claim 1)

[1522] a means for collecting a large amount of data from a database;

[1523] a means of standardizing the collected data;

[1524] a means for analyzing the standardized data;

[1525] A means for calculating value based on the analysis results;

[1526] A means for presenting the calculated value to the user;

[1527] means for analyzing user emotions;

[1528] The system includes a means for adjusting feedback based on the analyzed emotions.

[1529] (Claim 2)

[1530] 10. The system of claim 1, further comprising means for filtering out inaccuracies in the collected data.

[1531] (Claim 3)

[1532] a means for collecting feedback from users;

[1533] a means for storing the collected feedback in a database;

[1534] A means to improve future data analysis based on stored feedback; and

[1535] a means for standardizing and analyzing data extracted from the stored feedback;

[1536] 10. The system of claim 1, further comprising means for adjusting the feedback stored in the database based on the sentiment analysis results. [Explanation of symbols]

[1537] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting a large amount of data from a database; a means of standardizing the collected data; a means for analyzing the standardized data; A means for calculating value based on the analysis results; and means for presenting the calculated value to a user.

2. 10. The system of claim 1, further comprising means for filtering out inaccuracies in the collected data.

3. a means for collecting feedback from users; a means for storing the collected feedback in a database; and means for improving future data analysis based on the stored feedback.

Images