System

Abstract

An object of the system according to the embodiment is to instantaneously compare various elements of a plurality of vehicle types.SOLUTION: A system according to an embodiment includes a price comparator, a fuel economy comparator, a quietness comparator, an acceleration feeling comparator, a tax comparator, an insurance comparator, and a travel fee comparator. The price comparison unit uses the generated AI to compare the prices of the plurality of vehicle types that the user is considering. The fuel efficiency comparison unit compares the fuel efficiencies of a plurality of vehicle types that the user is considering. The quietness comparator compares quietness of a plurality of vehicle types that the user is considering. The acceleration feeling comparison unit compares acceleration feelings of a plurality of vehicle types that the user is considering. The tax comparison unit compares taxes of a plurality of vehicle types that the user is considering. The insurance comparison unit compares insurances of a plurality of vehicle types that the user is considering. The travel fee comparator compares the travel fees of the plurality of vehicle types that the user is considering.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that comparing various aspects of multiple vehicle models takes time and effort.

[0005] The system according to the embodiment aims to instantly compare various elements of a plurality of vehicle models. [Means for solving the problem]

[0006] The system according to the embodiment includes a price comparison unit, a fuel efficiency comparison unit, a quietness comparison unit, an acceleration comparison unit, a tax comparison unit, an insurance comparison unit, and a mileage fee comparison unit. The price comparison unit uses a generation AI to compare the prices of multiple vehicle models that the user is considering. The fuel efficiency comparison unit compares the fuel efficiency of multiple vehicle models that the user is considering. The quietness comparison unit compares the quietness of multiple vehicle models that the user is considering. The acceleration comparison unit compares the acceleration feeling of multiple vehicle models that the user is considering. The tax comparison unit compares the taxes of multiple vehicle models that the user is considering. The insurance comparison unit compares the insurance for multiple vehicle models that the user is considering. The mileage fee comparison unit compares the mileage fees for multiple vehicle models that the user is considering. [Effects of the Invention]

[0007] The system according to the embodiment can instantly compare various factors of multiple vehicle models. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A vehicle comparison system according to an embodiment of the present invention is a system that allows users to instantly compare multiple factors, such as price, fuel economy, quietness, acceleration, taxes, insurance, and mileage fees, when considering purchasing a car. This system uses a generative AI to analyze these factors and propose the most suitable vehicle model to the user. This allows the user to instantly compare multiple vehicle models and select the most suitable one.

[0029] A vehicle comparison system according to an embodiment includes a price comparison unit, a fuel efficiency comparison unit, a quietness comparison unit, an acceleration comparison unit, a tax comparison unit, an insurance comparison unit, and a mileage fee comparison unit. The price comparison unit uses a generation AI to compare the prices of multiple vehicle models that a user is considering. For example, the price comparison unit receives as input a list of vehicle models that the user wants to compare, collects the prices of each vehicle model, and creates a comparison table. The fuel efficiency comparison unit uses a generation AI to compare the fuel efficiency of multiple vehicle models that the user is considering. For example, the fuel efficiency comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes fuel efficiency data for each vehicle model. The quietness comparison unit uses a generation AI to compare the quietness of multiple vehicle models that the user is considering. For example, the quietness comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes quietness data for each vehicle model. The acceleration comparison unit uses a generation AI to compare the acceleration feel of multiple vehicle models that the user is considering. For example, the acceleration comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes acceleration feel data for each vehicle model. The tax comparison unit uses a generation AI to compare taxes for multiple vehicle models that the user is considering. For example, the tax comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes tax data for each vehicle model. The insurance comparison unit uses a generation AI to compare insurance for multiple vehicle models that the user is considering. For example, the insurance comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes insurance premium data for each vehicle model. The mileage fee comparison unit uses a generation AI to compare mileage fees for multiple vehicle models that the user is considering. For example, the mileage fee comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes mileage fee data for each vehicle model. As a result, the vehicle model comparison system according to the embodiment allows the user to instantly compare multiple vehicle models and select the most suitable one.

[0030] The price comparison unit can use the generation AI to analyze past discount information and campaign information and predict future discounts. The price comparison unit, for example, uses the generation AI to collect and analyze past discount information and campaign information. For example, future discount predictions are made based on data on discount campaigns held at specific times. The price comparison unit also analyzes past discount information and predicts the amount of discount offered by a specific car model or dealer. For example, based on past data, it predicts when a specific car model will be discounted. The price comparison unit also analyzes campaign information and predicts future discount predictions. For example, based on data on campaigns held in the past by a specific dealer, it predicts the possibility of future campaigns. This makes it possible to predict future discounts, allowing users to purchase a car at the optimal time.

[0031] The price comparison unit can use the generation AI to perform comprehensive price comparisons that include not only the price of the car, but also the costs of optional equipment and after-sales service. For example, the price comparison unit uses the generation AI to collect the prices of optional equipment and after-sales service costs in addition to the base price of the car, and perform a comprehensive price comparison. For example, it performs a comparison that includes the prices of optional equipment such as a navigation system or a sunroof. The price comparison unit also analyzes the prices of optional equipment and presents a comprehensive price that includes the optional equipment selected by the user. For example, it automatically calculates the prices of the optional equipment selected by the user and displays the comprehensive price. The price comparison unit also performs price comparisons that include the costs of after-sales service. For example, it presents a comprehensive price that includes the costs of after-sales service such as regular inspections and repair costs. This allows the user to compare comprehensive prices and select the most suitable car model.

[0032] The fuel efficiency comparison unit can use the generation AI to predict actual fuel efficiency based on the user's driving style and driving environment. The fuel efficiency comparison unit, for example, uses the generation AI to predict actual fuel efficiency based on the user's driving style and driving environment. For example, it collects the user's driving data and predicts actual fuel efficiency. The fuel efficiency comparison unit also predicts actual fuel efficiency based on the user's driving environment. For example, it predicts fuel efficiency based on driving environments such as urban areas and suburban areas. The fuel efficiency comparison unit also predicts actual fuel efficiency based on the user's driving style. For example, it predicts fuel efficiency based on driving styles such as sudden acceleration and sudden braking. This makes it possible to predict actual fuel efficiency based on the user's driving style and driving environment.

[0033] The fuel efficiency comparison unit can use the generation AI to provide eco-driving advice in addition to fuel efficiency data and make specific suggestions for improving fuel efficiency. The fuel efficiency comparison unit, for example, uses the generation AI to provide eco-driving advice in addition to fuel efficiency data. For example, it may suggest specific driving methods for improving fuel efficiency. The fuel efficiency comparison unit also analyzes the user's driving data and provides eco-driving advice. For example, it may provide advice on avoiding sudden acceleration and sudden braking. The fuel efficiency comparison unit also makes specific suggestions for improving fuel efficiency. For example, it may suggest appropriate tire air pressure or engine maintenance methods. In this way, the user can receive eco-driving advice and obtain specific suggestions for improving fuel efficiency.

[0034] The quietness comparison unit can use the generation AI to collect and compare quietness data under different driving conditions. The quietness comparison unit, for example, uses the generation AI to collect and compare quietness data under different driving conditions. For example, it collects and compares quietness data under driving conditions such as highways, urban areas, and suburbs. The quietness comparison unit also analyzes quietness data under different driving conditions to enable the user to compare quietness under each driving condition. For example, it provides a function to compare quietness between highways and urban areas. The quietness comparison unit also suggests the most suitable vehicle model for the user based on quietness data under different driving conditions. For example, it suggests the quietest vehicle under driving conditions such as highways, urban areas, and suburbs. This makes it possible to compare quietness under different driving conditions.

[0035] The quietness comparison unit uses a generation AI to evaluate the acoustic environment inside the vehicle in addition to quietness, allowing for a comprehensive quietness evaluation. For example, the quietness comparison unit uses a generation AI to evaluate the acoustic environment, such as sound quality when playing music, in addition to quietness inside the vehicle. For example, it collects data on the acoustic environment inside the vehicle and performs a comprehensive evaluation of quietness and sound quality. The quietness comparison unit also analyzes the acoustic environment inside the vehicle and allows the user to compare both quietness and sound quality. For example, it provides a function to simultaneously evaluate sound quality and quietness when playing music. The quietness comparison unit also suggests the most suitable car model for the user based on the comprehensive evaluation of quietness and the acoustic environment. For example, it suggests a car that is both quiet and has good sound quality when playing music. This makes it possible to comprehensively evaluate quietness and the acoustic environment.

[0036] The acceleration feeling comparison unit can use the generation AI to collect and compare acceleration feeling data under different driving conditions. For example, the acceleration feeling comparison unit uses the generation AI to collect and compare acceleration feeling data under different driving conditions. For example, it collects and compares acceleration feeling data under driving conditions such as highways, urban areas, and suburbs. The acceleration feeling comparison unit also analyzes the acceleration feeling data under different driving conditions to allow the user to compare the acceleration feeling for each driving condition. For example, it provides a function to compare acceleration feeling on highways and urban areas. The acceleration feeling comparison unit also suggests the most suitable vehicle model for the user based on the acceleration feeling data under different driving conditions. For example, it suggests the vehicle with the best acceleration feeling under driving conditions such as highways, urban areas, and suburbs. This makes it possible to compare acceleration feeling under different driving conditions.

[0037] The acceleration feeling comparison unit uses generation AI to evaluate braking performance and handling performance in addition to acceleration feeling, allowing for a comprehensive driving feel evaluation. The acceleration feeling comparison unit, for example, uses generation AI to evaluate braking performance and handling performance in addition to acceleration feeling. For example, it collects data on a vehicle's braking performance and handling performance to perform a comprehensive driving feel evaluation. The acceleration feeling comparison unit also analyzes braking performance and handling performance, allowing the user to compare the comprehensive driving feel along with the acceleration feeling. For example, it provides a function to simultaneously evaluate acceleration feeling, braking performance, and handling performance. The acceleration feeling comparison unit also suggests the most suitable vehicle model for the user based on a comprehensive evaluation of acceleration feeling, braking performance, and handling performance. For example, it suggests a vehicle with a good acceleration feeling and excellent braking performance and handling performance. This makes it possible to comprehensively evaluate acceleration feeling, braking performance, and handling performance.

[0038] The tax comparison unit can use generation AI to collect and compare tax data from different regions and countries. For example, the tax comparison unit uses generation AI to collect and compare car tax data from different regions and countries. For example, it collects and compares tax data from regions such as the United States, Europe, and Asia. The tax comparison unit also analyzes tax data from different regions and countries to allow users to compare taxes by region. For example, it compares how taxes on a specific car model vary by region. The tax comparison unit also suggests the most suitable car model for the user based on a global tax comparison. For example, it suggests the most cost-effective car model based on tax data from different regions and countries. This allows taxes from different regions and countries to be compared.

[0039] The tax comparison unit can use the generation AI to perform a comprehensive cost assessment that takes into account subsidies and tax reduction systems in addition to taxes. For example, the tax comparison unit uses the generation AI to collect information on subsidies and tax reduction systems in addition to vehicle taxes and perform a comprehensive cost assessment. For example, it collects information on subsidies and tax reduction systems offered in a specific region or country and performs a comprehensive cost assessment. The tax comparison unit also analyzes information on subsidies and tax reduction systems and allows users to compare overall costs in addition to taxes. For example, it provides a function to display overall costs taking into account subsidies and tax reduction systems. The tax comparison unit also suggests the optimal vehicle model for the user based on subsidies and tax reduction systems. For example, it suggests a vehicle with high overall cost performance taking into account subsidies and tax reduction systems. This makes it possible to perform a comprehensive cost assessment that takes into account subsidies and tax reduction systems in addition to taxes.

[0040] The insurance comparison unit can use the generation AI to collect and compare insurance premium data from different insurance companies. The insurance comparison unit, for example, uses the generation AI to collect and compare insurance premium data from different insurance companies. For example, it collects and compares insurance premium data from multiple insurance companies. The insurance comparison unit also analyzes insurance premium data from different insurance companies to enable users to compare insurance premiums. For example, it provides a function to compare insurance premiums from multiple insurance companies. The insurance comparison unit also suggests the most suitable insurance plan to the user based on the insurance premium data. For example, it suggests an insurance plan with low premiums and wide coverage. This allows insurance premiums from different insurance companies to be compared.

[0041] The insurance comparison unit can use generation AI to evaluate insurance coverage and service content in addition to insurance premiums, and perform comprehensive insurance evaluations. The insurance comparison unit, for example, uses generation AI to collect insurance coverage and service content in addition to insurance premiums, and perform comprehensive insurance evaluations. For example, it collects insurance coverage and service content and performs comprehensive insurance evaluations. The insurance comparison unit also analyzes insurance coverage and service content, allowing users to compare comprehensive insurance evaluations along with insurance premiums. For example, it provides a function to evaluate insurance coverage and service content. The insurance comparison unit also proposes the optimal insurance plan to the user based on the comprehensive evaluation of insurance coverage and service content. For example, it proposes an insurance plan with low premiums and wide coverage. This makes it possible to perform comprehensive insurance evaluations that evaluate coverage and service content in addition to insurance premiums.

[0042] The mileage fare comparison unit can use generation AI to collect and compare mileage fare data under different driving conditions. For example, the mileage fare comparison unit uses generation AI to collect and compare mileage fare data under different driving conditions. For example, it collects and compares mileage fare data under driving conditions such as highways, urban areas, and suburbs. The mileage fare comparison unit also analyzes mileage fare data under different driving conditions to enable users to compare mileage fare for each driving condition. For example, it provides a function to compare mileage fare between highways and urban areas. The mileage fare comparison unit also suggests the most suitable vehicle model for the user based on mileage fare data under different driving conditions. For example, it suggests the vehicle with the lowest mileage fare under driving conditions such as highways, urban areas, and suburbs. This makes it possible to compare mileage fare under different driving conditions.

[0043] The mileage fee comparison unit uses generation AI to evaluate maintenance costs and consumable costs in addition to mileage fees, allowing for a comprehensive cost evaluation. The mileage fee comparison unit, for example, uses generation AI to collect maintenance costs and consumable costs in addition to mileage fees, and performs a comprehensive cost evaluation. For example, it collects regular inspection and repair costs, and consumable costs such as tires and oil, and performs a comprehensive cost evaluation. The mileage fee comparison unit also analyzes maintenance costs and consumable costs, allowing users to compare overall costs in addition to mileage fees. For example, it provides a function to evaluate maintenance costs and consumable costs. The mileage fee comparison unit also suggests the most suitable vehicle model for the user based on a comprehensive evaluation of maintenance costs and consumable costs. For example, it suggests a vehicle with low mileage fees, low maintenance costs, and consumable costs. This makes it possible to perform a comprehensive cost evaluation that evaluates maintenance costs and consumable costs in addition to mileage fees.

[0044] The price comparison unit uses the generation AI to add a price comparison function with other high-priced items, thereby assisting the user in making a purchasing decision. For example, the price comparison unit uses the generation AI to collect and compare price information for other high-priced items in addition to the price of a car. For example, it collects price information for home appliances and real estate and compares it with the price of a car. The price comparison unit also analyzes price information for other high-priced items, allowing the user to compare the price of a car with other items. For example, it provides a function to compare the prices of home appliances and real estate with the price of a car. The price comparison unit also supports the user's purchasing decision based on price information for other high-priced items. For example, it provides price information for home appliances and real estate, allowing the user to compare the price of a car with other items. This allows the user to make a purchasing decision by comparing it with other high-priced items.

[0045] The price comparison unit can use generation AI to collect price information from different regions and countries and perform global price comparisons. For example, the price comparison unit uses generation AI to collect and compare car price information from different regions and countries. For example, it collects and compares price information from regions such as the United States, Europe, and Asia. The price comparison unit also analyzes price information from different regions and countries and performs global price comparisons. For example, it compares how the price of a specific car model varies from region to region. The price comparison unit also suggests the most suitable car model to the user based on the global price comparison. For example, it suggests the car model with the best cost performance based on price information from different regions and countries. This makes it possible to collect price information from different regions and countries and perform global price comparisons.

[0046] The fuel efficiency comparison unit uses the generation AI to add a function for comparing fuel efficiency with other energy-consuming products, thereby increasing the user's eco-consciousness. For example, the fuel efficiency comparison unit uses the generation AI to collect and compare fuel efficiency information of other energy-consuming products in addition to the vehicle's fuel efficiency. For example, it collects fuel efficiency information of home appliances and heating appliances and compares it with the vehicle's fuel efficiency. The fuel efficiency comparison unit also analyzes the fuel efficiency information of other energy-consuming products, allowing the user to compare the vehicle's fuel efficiency with other products. For example, it provides a function for comparing the fuel efficiency of home appliances and heating appliances with the vehicle's fuel efficiency. The fuel efficiency comparison unit also increases the user's eco-consciousness based on the fuel efficiency information of other energy-consuming products. For example, it provides fuel efficiency information of home appliances and heating appliances, allowing the user to compare the vehicle's fuel efficiency with other products. This allows the user to increase their eco-consciousness by comparing with other energy-consuming products.

[0047] The fuel efficiency comparison unit can use the generation AI to compare the fuel efficiency of different fuel types. For example, the fuel efficiency comparison unit uses the generation AI to collect and compare fuel efficiency information for vehicles with different fuel types. For example, it collects and compares fuel efficiency information for gasoline vehicles, diesel vehicles, and electric vehicles. The fuel efficiency comparison unit also analyzes the fuel efficiency information for different fuel types to enable the user to compare the fuel efficiency of each fuel type. For example, it provides a function to compare the fuel efficiency of gasoline vehicles and electric vehicles. The fuel efficiency comparison unit also suggests the vehicle with the most optimal fuel type to the user based on the fuel efficiency information for different fuel types. For example, it suggests the vehicle with the best fuel efficiency from among gasoline vehicles, diesel vehicles, and electric vehicles. This makes it possible to compare the fuel efficiency of different fuel types.

[0048] The quietness comparison unit uses the generation AI to add a quietness comparison function with other quiet products, thereby increasing the user's awareness of quietness. The quietness comparison unit, for example, uses the generation AI to collect and compare quietness information of other quiet products in addition to the quietness of the car. For example, it collects quietness information of home appliances and office equipment and compares it with the quietness of the car. The quietness comparison unit also analyzes the quietness information of other quiet products, allowing the user to compare the quietness of the car with other products. For example, it provides a function to compare the quietness of home appliances and office equipment with the quietness of the car. The quietness comparison unit also increases the user's awareness of quietness based on the quietness information of other quiet products. For example, it provides quietness information of home appliances and office equipment, allowing the user to compare the quietness of the car with other products. This allows the user to increase their awareness of quietness by comparing with other quiet products.

[0049] The quietness comparison unit can use the generation AI to collect quietness data for different vehicle models and display it in a ranking format. The quietness comparison unit, for example, uses the generation AI to collect quietness data for different vehicle models and display it in a ranking format. For example, it displays the quietest vehicle models in a ranking format. The quietness comparison unit also analyzes the quietness data for different vehicle models and allows the user to easily compare the quietest vehicle models. For example, it provides a function to display the quietest vehicle models in a ranking format. The quietness comparison unit also suggests the most suitable vehicle model for the user based on the quietness data. For example, it displays the quietest vehicle models in a ranking format, making it easier for the user to make a selection. This makes it possible to collect quietness data for different vehicle models and display it in a ranking format.

[0050] The acceleration feeling comparison unit uses a generation AI to add a performance comparison function with other high-performance products, thereby increasing the user's awareness of performance. The acceleration feeling comparison unit, for example, uses a generation AI to collect and compare performance information of other high-performance products in addition to the acceleration feeling of the car. For example, it collects performance information of sporting goods and home appliances and compares it with the acceleration feeling of the car. The acceleration feeling comparison unit also analyzes the performance information of other high-performance products to allow the user to compare the acceleration feeling of the car with other products. For example, it provides a function to compare the performance of sporting goods and home appliances with the acceleration feeling of the car. The acceleration feeling comparison unit also increases the user's awareness of performance based on the performance information of other high-performance products. For example, it provides performance information of sporting goods and home appliances to allow the user to compare the acceleration feeling of the car with other products. This allows the user to increase their awareness of performance by comparing with other high-performance products.

[0051] The acceleration feeling comparison unit can use the generation AI to collect acceleration feeling data of different vehicle models and display it in a ranking format. The acceleration feeling comparison unit, for example, uses the generation AI to collect acceleration feeling data of different vehicle models and display it in a ranking format. For example, it displays vehicle models with good acceleration feeling in a ranking format. The acceleration feeling comparison unit also analyzes the acceleration feeling data of different vehicle models and allows the user to easily compare vehicle models with good acceleration feeling. For example, it provides a function to display vehicle models with good acceleration feeling in a ranking format. The acceleration feeling comparison unit also suggests the vehicle model that is best suited to the user based on the acceleration feeling data. For example, it displays vehicle models with good acceleration feeling in a ranking format to make it easier for the user to select. This allows acceleration feeling data of different vehicle models to be collected and displayed in a ranking format.

[0052] The tax comparison unit uses the generation AI to add a tax comparison function with other tax-related products, thereby increasing the user's tax awareness. For example, the tax comparison unit uses the generation AI to collect and compare tax information for other tax-related products in addition to car taxes. For example, it collects tax information for real estate and high-value items and compares it with car taxes. The tax comparison unit also analyzes the tax information for other tax-related products to allow the user to compare car taxes with other products. For example, it provides a function to compare the taxes for real estate and high-value items with car taxes. The tax comparison unit also increases the user's tax awareness based on the tax information for other tax-related products. For example, it provides tax information for real estate and high-value items to allow the user to compare car taxes with other products. This allows the user to increase their tax awareness by comparing with other tax-related products.

[0053] The tax comparison unit can use the generation AI to collect tax data for different car models and display it in a ranking format. The tax comparison unit, for example, uses the generation AI to collect tax data for different car models and display it in a ranking format. For example, it displays car models with low taxes in a ranking format. The tax comparison unit also analyzes the tax data for different car models to enable the user to easily compare car models with low taxes. For example, it provides a function to display car models with low taxes in a ranking format. The tax comparison unit also suggests the most suitable car model for the user based on the tax data. For example, it displays car models with low taxes in a ranking format to make it easier for the user to make a selection. This makes it possible to collect tax data for different car models and display it in a ranking format.

[0054] The insurance comparison unit uses the generation AI to add a function for comparing insurance with other insurance-related products, thereby increasing the user's awareness of insurance. For example, the insurance comparison unit uses the generation AI to collect and compare insurance information for other insurance-related products in addition to car insurance. For example, it collects insurance information for life insurance and home contents insurance and compares it with car insurance. The insurance comparison unit also analyzes insurance information for other insurance-related products to enable the user to compare car insurance with other insurance. For example, it provides a function for comparing life insurance and home contents insurance with car insurance. The insurance comparison unit also increases the user's awareness of insurance based on insurance information for other insurance-related products. For example, it provides insurance information for life insurance and home contents insurance to enable the user to compare car insurance with other insurance. This allows the user to increase their awareness of insurance by comparing with other insurance-related products.

[0055] The insurance comparison unit can use the generation AI to collect insurance premium data for different car models and display it in a ranking format. The insurance comparison unit, for example, uses the generation AI to collect insurance premium data for different car models and display it in a ranking format. For example, it displays car models with low insurance premiums in a ranking format. The insurance comparison unit also analyzes insurance premium data for different car models to enable the user to easily compare car models with low insurance premiums. For example, it provides a function to display car models with low insurance premiums in a ranking format. The insurance comparison unit also suggests the most suitable car model for the user based on the insurance premium data. For example, it displays car models with low insurance premiums in a ranking format to make it easier for the user to make a selection. This makes it possible to collect insurance premium data for different car models and display it in a ranking format.

[0056] The mileage fare comparison unit uses generation AI to add a function for comparing mileage fare with other transportation-related products, thereby increasing the user's awareness of transportation. For example, the mileage fare comparison unit uses generation AI to collect and compare mileage fare information from other transportation-related products in addition to car mileage fare. For example, it collects mileage fare information for public transportation and bicycles and compares it with car mileage fare. The mileage fare comparison unit also analyzes mileage fare information from other transportation-related products to allow the user to compare car mileage fare with other means of transportation. For example, it provides a function to compare public transportation and bicycle mileage fare with car mileage fare. The mileage fare comparison unit also increases the user's awareness of transportation based on the mileage fare information from other transportation-related products. For example, it provides mileage fare information for public transportation and bicycles, allowing the user to compare car mileage fare with other means of transportation. This allows the user to increase their awareness of transportation by comparing with other transportation-related products.

[0057] The mileage fee comparison unit can use the generation AI to collect mileage fee data for different vehicle types and display it in ranking format. The mileage fee comparison unit, for example, uses the generation AI to collect mileage fee data for different vehicle types and display it in ranking format. For example, it displays vehicle types with low mileage fees in ranking format. The mileage fee comparison unit also analyzes mileage fee data for different vehicle types and makes it easy for users to compare vehicle types with low mileage fees. For example, it provides a function to display vehicle types with low mileage fees in ranking format. The mileage fee comparison unit also suggests the most suitable vehicle type for the user based on the mileage fee data. For example, it displays vehicle types with low mileage fees in ranking format to make it easier for the user to make a selection. This makes it possible to collect mileage fee data for different vehicle types and display it in ranking format.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The vehicle comparison system can also be equipped with a function to suggest vehicles based on the user's lifestyle. For example, if a user enjoys outdoor activities, it can suggest vehicles with excellent off-road performance. For users living in urban areas, it can suggest compact cars that are easy to park. It can also suggest family-friendly minivans and SUVs depending on the family structure. This allows it to suggest vehicles that are best suited to the user's lifestyle.

[0060] The car model comparison system can also be equipped with a function to suggest car models based on the user's health condition. For example, a car model with excellent seat support can be suggested to a user with lower back pain. Also, a car model with a highly visible display can be suggested to a user with poor eyesight. Furthermore, it is possible to suggest a car model with a powerful air purification function to a user with allergies. In this way, it is possible to suggest the car model that is best suited to the user's health condition.

[0061] The vehicle comparison system can also have a function to suggest vehicle models based on the user's hobbies and preferences. For example, a vehicle equipped with a high-quality audio system can be suggested to a user who enjoys music. A vehicle equipped with a sporty design and a high-performance engine can be suggested to a user who enjoys sports. Furthermore, a vehicle equipped with a wide range of pet accessories can be suggested to a user who keeps pets. This makes it possible to suggest a vehicle that best suits the user's hobbies and preferences.

[0062] The vehicle comparison system can also be equipped with a function to suggest vehicle models based on the user's environmental consciousness. For example, electric vehicles and hybrid vehicles can be suggested to environmentally conscious users. Also, fuel-efficient vehicles can be suggested to users who prioritize fuel efficiency. Furthermore, it is possible to suggest vehicles made from recycled materials or vehicles equipped with eco-driving functions. This allows the system to suggest vehicles that are best suited to the user's environmental consciousness.

[0063] The vehicle comparison system can also be equipped with a function to suggest vehicles based on the user's safety consciousness. For example, for a user who places importance on safety, it can suggest vehicles equipped with the latest safety features. It can also suggest vehicles with comprehensive driving assistance systems. It can also suggest vehicles with high crash test scores and vehicles that are compatible with child seats for the safety of children. This makes it possible to suggest vehicles that are optimal for the user's safety consciousness.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The price comparison unit uses generation AI to compare the prices of multiple car models the user is considering. For example, it receives as input a list of car models the user wants to compare, collects the prices of each car model, and creates a comparison table. Step 2: The fuel economy comparison unit uses the generation AI to compare the fuel economy of multiple vehicle models the user is considering. For example, it receives as input a list of vehicle models the user wants to compare, collects and analyzes fuel economy data for each vehicle model. Step 3: The quietness comparison unit uses the generation AI to compare the quietness of multiple vehicle models the user is considering. For example, it receives as input a list of vehicle models the user wants to compare, and collects and analyzes quietness data for each vehicle model. Step 4: The acceleration comparison unit uses the generation AI to compare the acceleration of multiple vehicle models the user is considering. For example, it receives as input a list of vehicle models the user wants to compare, and collects and analyzes acceleration data for each vehicle model. Step 5: The tax comparison unit uses the generation AI to compare the taxes of multiple car models the user is considering. For example, it receives a list of car models the user wants to compare as input, and collects and analyzes tax data for each car model. Step 6: The insurance comparison unit uses the generation AI to compare insurance for multiple car models the user is considering. For example, it receives as input a list of car models the user wants to compare, collects insurance premium data for each car model, and analyzes it. Step 7: The toll comparison unit uses the generation AI to compare the tolls of multiple vehicle types the user is considering. For example, it receives as input a list of vehicle types the user wants to compare, and collects and analyzes toll data for each vehicle type.

[0066] (Example 2) A vehicle comparison system according to an embodiment of the present invention is a system that allows users to instantly compare multiple factors, such as price, fuel economy, quietness, acceleration, taxes, insurance, and mileage fees, when considering purchasing a car. This system uses a generative AI to analyze these factors and propose the most suitable vehicle model to the user. This allows the user to instantly compare multiple vehicle models and select the most suitable one.

[0067] A vehicle comparison system according to an embodiment includes a price comparison unit, a fuel efficiency comparison unit, a quietness comparison unit, an acceleration comparison unit, a tax comparison unit, an insurance comparison unit, and a mileage fee comparison unit. The price comparison unit uses a generation AI to compare the prices of multiple vehicle models that a user is considering. For example, the price comparison unit receives as input a list of vehicle models that the user wants to compare, collects the prices of each vehicle model, and creates a comparison table. The fuel efficiency comparison unit uses a generation AI to compare the fuel efficiency of multiple vehicle models that the user is considering. For example, the fuel efficiency comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes fuel efficiency data for each vehicle model. The quietness comparison unit uses a generation AI to compare the quietness of multiple vehicle models that the user is considering. For example, the quietness comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes quietness data for each vehicle model. The acceleration comparison unit uses a generation AI to compare the acceleration feel of multiple vehicle models that the user is considering. For example, the acceleration comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes acceleration feel data for each vehicle model. The tax comparison unit uses a generation AI to compare taxes for multiple vehicle models that the user is considering. For example, the tax comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes tax data for each vehicle model. The insurance comparison unit uses a generation AI to compare insurance for multiple vehicle models that the user is considering. For example, the insurance comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes insurance premium data for each vehicle model. The mileage fee comparison unit uses a generation AI to compare mileage fees for multiple vehicle models that the user is considering. For example, the mileage fee comparison unit receives as input a list of vehicle models that the user wants to compare, and collects and analyzes mileage fee data for each vehicle model. As a result, the vehicle model comparison system according to the embodiment allows the user to instantly compare multiple vehicle models and select the most suitable one.

[0068] The price comparison unit can use the generation AI to analyze past discount information and campaign information and predict future discounts. The price comparison unit, for example, uses the generation AI to collect and analyze past discount information and campaign information. For example, future discount predictions are made based on data on discount campaigns held at specific times. The price comparison unit also analyzes past discount information and predicts the amount of discount offered by a specific car model or dealer. For example, based on past data, it predicts when a specific car model will be discounted. The price comparison unit also analyzes campaign information and predicts future discount predictions. For example, based on data on campaigns held in the past by a specific dealer, it predicts the possibility of future campaigns. This makes it possible to predict future discounts, allowing users to purchase a car at the optimal time.

[0069] The price comparison unit can use the generation AI to perform comprehensive price comparisons that include not only the price of the car, but also the costs of optional equipment and after-sales service. For example, the price comparison unit uses the generation AI to collect the prices of optional equipment and after-sales service costs in addition to the base price of the car, and perform a comprehensive price comparison. For example, it performs a comparison that includes the prices of optional equipment such as a navigation system or a sunroof. The price comparison unit also analyzes the prices of optional equipment and presents a comprehensive price that includes the optional equipment selected by the user. For example, it automatically calculates the prices of the optional equipment selected by the user and displays the comprehensive price. The price comparison unit also performs price comparisons that include the costs of after-sales service. For example, it presents a comprehensive price that includes the costs of after-sales service such as regular inspections and repair costs. This allows the user to compare comprehensive prices and select the most suitable car model.

[0070] The price comparison unit can use the emotion estimation function to analyze the user's satisfaction with price and suggest the price range that provides the highest level of satisfaction. The price comparison unit, for example, uses the emotion estimation function to analyze the user's satisfaction with price. For example, it analyzes the user's facial expressions and voice and quantifies the user's satisfaction with price. The price comparison unit also suggests the price range that provides the highest level of satisfaction based on the user's satisfaction data. For example, it identifies a price range that provides the highest level of user satisfaction and suggests a car model in that price range. The price comparison unit also uses the emotion estimation function to provide advice to alleviate the user's anxiety and concerns about price. For example, it provides information to alleviate anxiety about price. This makes it possible to suggest the optimal price range based on the user's satisfaction.

[0071] The fuel efficiency comparison unit can use the generation AI to predict actual fuel efficiency based on the user's driving style and driving environment. The fuel efficiency comparison unit, for example, uses the generation AI to predict actual fuel efficiency based on the user's driving style and driving environment. For example, it collects the user's driving data and predicts actual fuel efficiency. The fuel efficiency comparison unit also predicts actual fuel efficiency based on the user's driving environment. For example, it predicts fuel efficiency based on driving environments such as urban areas and suburban areas. The fuel efficiency comparison unit also predicts actual fuel efficiency based on the user's driving style. For example, it predicts fuel efficiency based on driving styles such as sudden acceleration and sudden braking. This makes it possible to predict actual fuel efficiency based on the user's driving style and driving environment.

[0072] The fuel efficiency comparison unit can use the generation AI to provide eco-driving advice in addition to fuel efficiency data and make specific suggestions for improving fuel efficiency. The fuel efficiency comparison unit, for example, uses the generation AI to provide eco-driving advice in addition to fuel efficiency data. For example, it may suggest specific driving methods for improving fuel efficiency. The fuel efficiency comparison unit also analyzes the user's driving data and provides eco-driving advice. For example, it may provide advice on avoiding sudden acceleration and sudden braking. The fuel efficiency comparison unit also makes specific suggestions for improving fuel efficiency. For example, it may suggest appropriate tire air pressure or engine maintenance methods. In this way, the user can receive eco-driving advice and obtain specific suggestions for improving fuel efficiency.

[0073] The fuel efficiency comparison unit uses the emotion estimation function to analyze the user's level of satisfaction with fuel efficiency and can suggest the fuel efficiency performance that provides the highest level of satisfaction. The fuel efficiency comparison unit, for example, uses the emotion estimation function to analyze the user's level of satisfaction with fuel efficiency. For example, it analyzes the user's facial expressions and voice to quantify the level of satisfaction with fuel efficiency. The fuel efficiency comparison unit also suggests the fuel efficiency performance that provides the highest level of satisfaction based on the user satisfaction data. For example, it identifies the fuel efficiency performance that provides the highest level of satisfaction to the user and suggests a vehicle model that has that performance. The fuel efficiency comparison unit also uses the emotion estimation function to provide advice to alleviate the user's anxieties and concerns about fuel efficiency. For example, it provides information to alleviate anxiety about fuel efficiency. This makes it possible to suggest the optimal fuel efficiency performance based on the user's level of satisfaction.

[0074] The quietness comparison unit can use the generation AI to collect and compare quietness data under different driving conditions. The quietness comparison unit, for example, uses the generation AI to collect and compare quietness data under different driving conditions. For example, it collects and compares quietness data under driving conditions such as highways, urban areas, and suburbs. The quietness comparison unit also analyzes quietness data under different driving conditions to enable the user to compare quietness under each driving condition. For example, it provides a function to compare quietness between highways and urban areas. The quietness comparison unit also suggests the most suitable vehicle model for the user based on quietness data under different driving conditions. For example, it suggests the quietest vehicle under driving conditions such as highways, urban areas, and suburbs. This makes it possible to compare quietness under different driving conditions.

[0075] The quietness comparison unit uses a generation AI to evaluate the acoustic environment inside the vehicle in addition to quietness, allowing for a comprehensive quietness evaluation. For example, the quietness comparison unit uses a generation AI to evaluate the acoustic environment, such as sound quality when playing music, in addition to quietness inside the vehicle. For example, it collects data on the acoustic environment inside the vehicle and performs a comprehensive evaluation of quietness and sound quality. The quietness comparison unit also analyzes the acoustic environment inside the vehicle and allows the user to compare both quietness and sound quality. For example, it provides a function to simultaneously evaluate sound quality and quietness when playing music. The quietness comparison unit also suggests the most suitable car model for the user based on the comprehensive evaluation of quietness and the acoustic environment. For example, it suggests a car that is both quiet and has good sound quality when playing music. This makes it possible to comprehensively evaluate quietness and the acoustic environment.

[0076] The quietness comparison unit uses the emotion estimation function to analyze the user's level of satisfaction with quietness and can suggest the level of quietness that provides the highest level of satisfaction. The quietness comparison unit, for example, uses the emotion estimation function to analyze the user's level of satisfaction with quietness. For example, it analyzes the user's facial expressions and voice and quantifies the level of satisfaction with quietness. The quietness comparison unit also suggests the level of quietness that provides the highest level of satisfaction based on the user satisfaction data. For example, it identifies the level of quietness that provides the highest level of satisfaction to the user and suggests a vehicle model that has that performance. The quietness comparison unit also uses the emotion estimation function to provide advice to alleviate the user's anxieties and concerns about quietness. For example, it provides information to alleviate anxiety about quietness. This makes it possible to suggest the optimal level of quietness based on the user's satisfaction.

[0077] The acceleration feeling comparison unit can use the generation AI to collect and compare acceleration feeling data under different driving conditions. For example, the acceleration feeling comparison unit uses the generation AI to collect and compare acceleration feeling data under different driving conditions. For example, it collects and compares acceleration feeling data under driving conditions such as highways, urban areas, and suburbs. The acceleration feeling comparison unit also analyzes the acceleration feeling data under different driving conditions to allow the user to compare the acceleration feeling for each driving condition. For example, it provides a function to compare acceleration feeling on highways and urban areas. The acceleration feeling comparison unit also suggests the most suitable vehicle model for the user based on the acceleration feeling data under different driving conditions. For example, it suggests the vehicle with the best acceleration feeling under driving conditions such as highways, urban areas, and suburbs. This makes it possible to compare acceleration feeling under different driving conditions.

[0078] The acceleration feeling comparison unit uses generation AI to evaluate braking performance and handling performance in addition to acceleration feeling, allowing for a comprehensive driving feel evaluation. The acceleration feeling comparison unit, for example, uses generation AI to evaluate braking performance and handling performance in addition to acceleration feeling. For example, it collects data on a vehicle's braking performance and handling performance to perform a comprehensive driving feel evaluation. The acceleration feeling comparison unit also analyzes braking performance and handling performance, allowing the user to compare the comprehensive driving feel along with the acceleration feeling. For example, it provides a function to simultaneously evaluate acceleration feeling, braking performance, and handling performance. The acceleration feeling comparison unit also suggests the most suitable vehicle model for the user based on a comprehensive evaluation of acceleration feeling, braking performance, and handling performance. For example, it suggests a vehicle with a good acceleration feeling and excellent braking performance and handling performance. This makes it possible to comprehensively evaluate acceleration feeling, braking performance, and handling performance.

[0079] The acceleration feeling comparison unit uses the emotion estimation function to analyze the user's level of satisfaction with the acceleration feeling and can suggest the acceleration feeling that provides the highest level of satisfaction. The acceleration feeling comparison unit, for example, uses the emotion estimation function to analyze the user's level of satisfaction with the acceleration feeling. For example, it analyzes the user's facial expressions and voice and quantifies the level of satisfaction with the acceleration feeling. The acceleration feeling comparison unit also suggests the acceleration feeling that provides the highest level of satisfaction based on the user satisfaction data. For example, it identifies the acceleration feeling that provides the highest level of satisfaction to the user and suggests a vehicle model with that performance. The acceleration feeling comparison unit also uses the emotion estimation function to provide advice to reduce the anxiety or concerns the user has about the acceleration feeling. For example, it provides information to reduce anxiety about the acceleration feeling. This makes it possible to suggest the optimal acceleration feeling based on the user's satisfaction.

[0080] The tax comparison unit can use generation AI to collect and compare tax data from different regions and countries. For example, the tax comparison unit uses generation AI to collect and compare car tax data from different regions and countries. For example, it collects and compares tax data from regions such as the United States, Europe, and Asia. The tax comparison unit also analyzes tax data from different regions and countries to allow users to compare taxes by region. For example, it compares how taxes on a specific car model vary by region. The tax comparison unit also suggests the most suitable car model for the user based on a global tax comparison. For example, it suggests the most cost-effective car model based on tax data from different regions and countries. This allows taxes from different regions and countries to be compared.

[0081] The tax comparison unit can use the generation AI to perform a comprehensive cost assessment that takes into account subsidies and tax reduction systems in addition to taxes. For example, the tax comparison unit uses the generation AI to collect information on subsidies and tax reduction systems in addition to vehicle taxes and perform a comprehensive cost assessment. For example, it collects information on subsidies and tax reduction systems offered in a specific region or country and performs a comprehensive cost assessment. The tax comparison unit also analyzes information on subsidies and tax reduction systems and allows users to compare overall costs in addition to taxes. For example, it provides a function to display overall costs taking into account subsidies and tax reduction systems. The tax comparison unit also suggests the optimal vehicle model for the user based on subsidies and tax reduction systems. For example, it suggests a vehicle with high overall cost performance taking into account subsidies and tax reduction systems. This makes it possible to perform a comprehensive cost assessment that takes into account subsidies and tax reduction systems in addition to taxes.

[0082] The tax comparison unit uses the emotion estimation function to analyze the user's level of satisfaction with taxes and can propose the tax system that provides the highest level of satisfaction. The tax comparison unit, for example, uses the emotion estimation function to analyze the user's level of satisfaction with taxes. For example, it analyzes the user's facial expressions and voice to quantify the level of satisfaction with taxes. The tax comparison unit also proposes the tax system that provides the highest level of satisfaction based on the user satisfaction data. For example, it identifies a tax system that provides the highest level of satisfaction to the user and proposes a region or country that has that system. The tax comparison unit also uses the emotion estimation function to provide advice to reduce the user's anxiety and concerns about taxes. For example, it provides information to reduce anxiety about taxes. This makes it possible to propose the optimal tax system based on the user's level of satisfaction.

[0083] The insurance comparison unit can use the generation AI to collect and compare insurance premium data from different insurance companies. The insurance comparison unit, for example, uses the generation AI to collect and compare insurance premium data from different insurance companies. For example, it collects and compares insurance premium data from multiple insurance companies. The insurance comparison unit also analyzes insurance premium data from different insurance companies to enable users to compare insurance premiums. For example, it provides a function to compare insurance premiums from multiple insurance companies. The insurance comparison unit also suggests the most suitable insurance plan to the user based on the insurance premium data. For example, it suggests an insurance plan with low premiums and wide coverage. This allows insurance premiums from different insurance companies to be compared.

[0084] The insurance comparison unit can use generation AI to evaluate insurance coverage and service content in addition to insurance premiums, and perform comprehensive insurance evaluations. The insurance comparison unit, for example, uses generation AI to collect insurance coverage and service content in addition to insurance premiums, and perform comprehensive insurance evaluations. For example, it collects insurance coverage and service content and performs comprehensive insurance evaluations. The insurance comparison unit also analyzes insurance coverage and service content, allowing users to compare comprehensive insurance evaluations along with insurance premiums. For example, it provides a function to evaluate insurance coverage and service content. The insurance comparison unit also proposes the optimal insurance plan to the user based on the comprehensive evaluation of insurance coverage and service content. For example, it proposes an insurance plan with low premiums and wide coverage. This makes it possible to perform comprehensive insurance evaluations that evaluate coverage and service content in addition to insurance premiums.

[0085] The insurance comparison unit can use the emotion estimation function to analyze the user's level of satisfaction with insurance and propose the insurance plan that provides the highest level of satisfaction. The insurance comparison unit, for example, uses the emotion estimation function to analyze the user's level of satisfaction with insurance. For example, it analyzes the user's facial expressions and voice to quantify the level of satisfaction with insurance. The insurance comparison unit also proposes the insurance plan that provides the highest level of satisfaction based on the user's satisfaction data. For example, it identifies the insurance plan that provides the highest level of satisfaction to the user and proposes that plan. The insurance comparison unit also uses the emotion estimation function to provide advice to alleviate the anxiety and concerns the user has about insurance. For example, it provides information to alleviate anxiety about insurance. This makes it possible to propose the optimal insurance plan based on the user's level of satisfaction.

[0086] The mileage fare comparison unit can use generation AI to collect and compare mileage fare data under different driving conditions. For example, the mileage fare comparison unit uses generation AI to collect and compare mileage fare data under different driving conditions. For example, it collects and compares mileage fare data under driving conditions such as highways, urban areas, and suburbs. The mileage fare comparison unit also analyzes mileage fare data under different driving conditions to enable users to compare mileage fare for each driving condition. For example, it provides a function to compare mileage fare between highways and urban areas. The mileage fare comparison unit also suggests the most suitable vehicle model for the user based on mileage fare data under different driving conditions. For example, it suggests the vehicle with the lowest mileage fare under driving conditions such as highways, urban areas, and suburbs. This makes it possible to compare mileage fare under different driving conditions.

[0087] The mileage fee comparison unit uses generation AI to evaluate maintenance costs and consumable costs in addition to mileage fees, allowing for a comprehensive cost evaluation. The mileage fee comparison unit, for example, uses generation AI to collect maintenance costs and consumable costs in addition to mileage fees, and performs a comprehensive cost evaluation. For example, it collects regular inspection and repair costs, and consumable costs such as tires and oil, and performs a comprehensive cost evaluation. The mileage fee comparison unit also analyzes maintenance costs and consumable costs, allowing users to compare overall costs in addition to mileage fees. For example, it provides a function to evaluate maintenance costs and consumable costs. The mileage fee comparison unit also suggests the most suitable vehicle model for the user based on a comprehensive evaluation of maintenance costs and consumable costs. For example, it suggests a vehicle with low mileage fees, low maintenance costs, and consumable costs. This makes it possible to perform a comprehensive cost evaluation that evaluates maintenance costs and consumable costs in addition to mileage fees.

[0088] The mileage fare comparison unit uses the emotion estimation function to analyze the user's level of satisfaction with the mileage fare and can propose the mileage fare that provides the highest level of satisfaction. The mileage fare comparison unit, for example, uses the emotion estimation function to analyze the user's level of satisfaction with the mileage fare. For example, it analyzes the user's facial expressions and voice to quantify the user's level of satisfaction with the mileage fare. The mileage fare comparison unit also proposes the mileage fare that provides the highest level of satisfaction based on the user's satisfaction data. For example, it identifies the mileage fare that provides the highest level of satisfaction to the user and proposes a vehicle model that has that fare. The mileage fare comparison unit also uses the emotion estimation function to provide advice to alleviate the user's anxieties and concerns about the mileage fare. For example, it provides information to alleviate anxiety about the mileage fare. This makes it possible to propose the optimal mileage fare based on the user's level of satisfaction.

[0089] The price comparison unit uses the generation AI to add a price comparison function with other high-priced items, thereby assisting the user in making a purchasing decision. For example, the price comparison unit uses the generation AI to collect and compare price information for other high-priced items in addition to the price of a car. For example, it collects price information for home appliances and real estate and compares it with the price of a car. The price comparison unit also analyzes price information for other high-priced items, allowing the user to compare the price of a car with other items. For example, it provides a function to compare the prices of home appliances and real estate with the price of a car. The price comparison unit also supports the user's purchasing decision based on price information for other high-priced items. For example, it provides price information for home appliances and real estate, allowing the user to compare the price of a car with other items. This allows the user to make a purchasing decision by comparing it with other high-priced items.

[0090] The price comparison unit can use generation AI to collect price information from different regions and countries and perform global price comparisons. For example, the price comparison unit uses generation AI to collect and compare car price information from different regions and countries. For example, it collects and compares price information from regions such as the United States, Europe, and Asia. The price comparison unit also analyzes price information from different regions and countries and performs global price comparisons. For example, it compares how the price of a specific car model varies from region to region. The price comparison unit also suggests the most suitable car model to the user based on the global price comparison. For example, it suggests the car model with the best cost performance based on price information from different regions and countries. This makes it possible to collect price information from different regions and countries and perform global price comparisons.

[0091] The price comparison unit can use the emotion estimation function to provide advice to reduce the anxiety or concern the user has about price. The price comparison unit, for example, uses the emotion estimation function to analyze the anxiety or concern the user has about price. For example, it analyzes the user's facial expression or voice to identify the anxiety or concern about price. The price comparison unit also provides advice to reduce the user's anxiety or concern. For example, it provides information or advice to reduce the anxiety about price. The price comparison unit also uses the emotion estimation function to make specific suggestions to reduce the anxiety or concern the user has about price. For example, it suggests specific actions to reduce the anxiety about price. This makes it possible to provide advice to reduce the anxiety or concern the user has about price.

[0092] The fuel efficiency comparison unit uses the generation AI to add a function for comparing fuel efficiency with other energy-consuming products, thereby increasing the user's eco-consciousness. For example, the fuel efficiency comparison unit uses the generation AI to collect and compare fuel efficiency information of other energy-consuming products in addition to the vehicle's fuel efficiency. For example, it collects fuel efficiency information of home appliances and heating appliances and compares it with the vehicle's fuel efficiency. The fuel efficiency comparison unit also analyzes the fuel efficiency information of other energy-consuming products, allowing the user to compare the vehicle's fuel efficiency with other products. For example, it provides a function for comparing the fuel efficiency of home appliances and heating appliances with the vehicle's fuel efficiency. The fuel efficiency comparison unit also increases the user's eco-consciousness based on the fuel efficiency information of other energy-consuming products. For example, it provides fuel efficiency information of home appliances and heating appliances, allowing the user to compare the vehicle's fuel efficiency with other products. This allows the user to increase their eco-consciousness by comparing with other energy-consuming products.

[0093] The fuel efficiency comparison unit can use the generation AI to compare the fuel efficiency of different fuel types. For example, the fuel efficiency comparison unit uses the generation AI to collect and compare fuel efficiency information for vehicles with different fuel types. For example, it collects and compares fuel efficiency information for gasoline vehicles, diesel vehicles, and electric vehicles. The fuel efficiency comparison unit also analyzes the fuel efficiency information for different fuel types to enable the user to compare the fuel efficiency of each fuel type. For example, it provides a function to compare the fuel efficiency of gasoline vehicles and electric vehicles. The fuel efficiency comparison unit also suggests the vehicle with the most optimal fuel type to the user based on the fuel efficiency information for different fuel types. For example, it suggests the vehicle with the best fuel efficiency from among gasoline vehicles, diesel vehicles, and electric vehicles. This makes it possible to compare the fuel efficiency of different fuel types.

[0094] The fuel efficiency comparison unit can use the emotion estimation function to provide advice to reduce the anxiety and concerns the user has about fuel efficiency. The fuel efficiency comparison unit, for example, uses the emotion estimation function to analyze the anxiety and concerns the user has about fuel efficiency. For example, it analyzes the user's facial expression or voice to identify the anxiety and concerns about fuel efficiency. The fuel efficiency comparison unit also provides advice to reduce the user's anxiety and concerns. For example, it provides information or advice to reduce anxiety about fuel efficiency. The fuel efficiency comparison unit also uses the emotion estimation function to make specific suggestions to reduce the anxiety and concerns the user has about fuel efficiency. For example, it suggests specific actions to reduce anxiety about fuel efficiency. This makes it possible to provide advice to reduce the anxiety and concerns the user has about fuel efficiency.

[0095] The quietness comparison unit uses the generation AI to add a quietness comparison function with other quiet products, thereby increasing the user's awareness of quietness. The quietness comparison unit, for example, uses the generation AI to collect and compare quietness information of other quiet products in addition to the quietness of the car. For example, it collects quietness information of home appliances and office equipment and compares it with the quietness of the car. The quietness comparison unit also analyzes the quietness information of other quiet products, allowing the user to compare the quietness of the car with other products. For example, it provides a function to compare the quietness of home appliances and office equipment with the quietness of the car. The quietness comparison unit also increases the user's awareness of quietness based on the quietness information of other quiet products. For example, it provides quietness information of home appliances and office equipment, allowing the user to compare the quietness of the car with other products. This allows the user to increase their awareness of quietness by comparing with other quiet products.

[0096] The quietness comparison unit can use the generation AI to collect quietness data for different vehicle models and display it in a ranking format. The quietness comparison unit, for example, uses the generation AI to collect quietness data for different vehicle models and display it in a ranking format. For example, it displays the quietest vehicle models in a ranking format. The quietness comparison unit also analyzes the quietness data for different vehicle models and allows the user to easily compare the quietest vehicle models. For example, it provides a function to display the quietest vehicle models in a ranking format. The quietness comparison unit also suggests the most suitable vehicle model for the user based on the quietness data. For example, it displays the quietest vehicle models in a ranking format, making it easier for the user to make a selection. This makes it possible to collect quietness data for different vehicle models and display it in a ranking format.

[0097] The quietness comparison unit can use the emotion estimation function to provide advice to reduce the anxiety or concern the user feels about quietness. The quietness comparison unit, for example, uses the emotion estimation function to analyze the anxiety or concern the user feels about quietness. For example, it analyzes the user's facial expression or voice to identify the anxiety or concern about quietness. The quietness comparison unit also provides advice to reduce the user's anxiety or concern. For example, it provides information or advice to reduce anxiety about quietness. The quietness comparison unit also uses the emotion estimation function to make specific suggestions to reduce the anxiety or concern the user feels about quietness. For example, it suggests specific actions to reduce anxiety about quietness. This makes it possible to provide advice to reduce the anxiety or concern the user feels about quietness.

[0098] The acceleration feeling comparison unit uses a generation AI to add a performance comparison function with other high-performance products, thereby increasing the user's awareness of performance. The acceleration feeling comparison unit, for example, uses a generation AI to collect and compare performance information of other high-performance products in addition to the acceleration feeling of the car. For example, it collects performance information of sporting goods and home appliances and compares it with the acceleration feeling of the car. The acceleration feeling comparison unit also analyzes the performance information of other high-performance products to allow the user to compare the acceleration feeling of the car with other products. For example, it provides a function to compare the performance of sporting goods and home appliances with the acceleration feeling of the car. The acceleration feeling comparison unit also increases the user's awareness of performance based on the performance information of other high-performance products. For example, it provides performance information of sporting goods and home appliances to allow the user to compare the acceleration feeling of the car with other products. This allows the user to increase their awareness of performance by comparing with other high-performance products.

[0099] The acceleration feeling comparison unit can use the generation AI to collect acceleration feeling data of different vehicle models and display it in a ranking format. The acceleration feeling comparison unit, for example, uses the generation AI to collect acceleration feeling data of different vehicle models and display it in a ranking format. For example, it displays vehicle models with good acceleration feeling in a ranking format. The acceleration feeling comparison unit also analyzes the acceleration feeling data of different vehicle models and allows the user to easily compare vehicle models with good acceleration feeling. For example, it provides a function to display vehicle models with good acceleration feeling in a ranking format. The acceleration feeling comparison unit also suggests the vehicle model that is best suited to the user based on the acceleration feeling data. For example, it displays vehicle models with good acceleration feeling in a ranking format to make it easier for the user to select. This allows acceleration feeling data of different vehicle models to be collected and displayed in a ranking format.

[0100] The acceleration feeling comparison unit can use the emotion estimation function to provide advice to reduce the anxiety or concern the user feels about the acceleration feeling. The acceleration feeling comparison unit, for example, uses the emotion estimation function to analyze the anxiety or concern the user feels about the acceleration feeling. For example, it analyzes the user's facial expression or voice to identify the anxiety or concern about the acceleration feeling. The acceleration feeling comparison unit also provides advice to reduce the user's anxiety or concern. For example, it provides information or advice to reduce anxiety about the acceleration feeling. The acceleration feeling comparison unit also uses the emotion estimation function to make specific suggestions to reduce the anxiety or concern the user feels about the acceleration feeling. For example, it suggests specific actions to reduce anxiety about the acceleration feeling. This makes it possible to provide advice to reduce the anxiety or concern the user feels about the acceleration feeling.

[0101] The tax comparison unit uses the generation AI to add a tax comparison function with other tax-related products, thereby increasing the user's tax awareness. For example, the tax comparison unit uses the generation AI to collect and compare tax information for other tax-related products in addition to car taxes. For example, it collects tax information for real estate and high-value items and compares it with car taxes. The tax comparison unit also analyzes the tax information for other tax-related products to allow the user to compare car taxes with other products. For example, it provides a function to compare the taxes for real estate and high-value items with car taxes. The tax comparison unit also increases the user's tax awareness based on the tax information for other tax-related products. For example, it provides tax information for real estate and high-value items to allow the user to compare car taxes with other products. This allows the user to increase their tax awareness by comparing with other tax-related products.

[0102] The tax comparison unit can use the generation AI to collect tax data for different car models and display it in a ranking format. The tax comparison unit, for example, uses the generation AI to collect tax data for different car models and display it in a ranking format. For example, it displays car models with low taxes in a ranking format. The tax comparison unit also analyzes the tax data for different car models to enable the user to easily compare car models with low taxes. For example, it provides a function to display car models with low taxes in a ranking format. The tax comparison unit also suggests the most suitable car model for the user based on the tax data. For example, it displays car models with low taxes in a ranking format to make it easier for the user to make a selection. This makes it possible to collect tax data for different car models and display it in a ranking format.

[0103] The tax comparison unit can use the emotion estimation function to provide advice to reduce the anxiety and concern the user has about taxes. The tax comparison unit, for example, uses the emotion estimation function to analyze the anxiety and concern the user has about taxes. For example, it analyzes the user's facial expressions and voice to identify the anxiety and concern about taxes. The tax comparison unit also provides advice to reduce the user's anxiety and concern. For example, it provides information and advice to reduce anxiety about taxes. The tax comparison unit also uses the emotion estimation function to make specific suggestions to reduce the anxiety and concern the user has about taxes. For example, it suggests specific actions to reduce anxiety about taxes. This makes it possible to provide advice to reduce the anxiety and concern the user has about taxes.

[0104] The insurance comparison unit uses the generation AI to add a function for comparing insurance with other insurance-related products, thereby increasing the user's awareness of insurance. For example, the insurance comparison unit uses the generation AI to collect and compare insurance information for other insurance-related products in addition to car insurance. For example, it collects insurance information for life insurance and home contents insurance and compares it with car insurance. The insurance comparison unit also analyzes insurance information for other insurance-related products to enable the user to compare car insurance with other insurance. For example, it provides a function for comparing life insurance and home contents insurance with car insurance. The insurance comparison unit also increases the user's awareness of insurance based on insurance information for other insurance-related products. For example, it provides insurance information for life insurance and home contents insurance to enable the user to compare car insurance with other insurance. This allows the user to increase their awareness of insurance by comparing with other insurance-related products.

[0105] The insurance comparison unit can use the generation AI to collect insurance premium data for different car models and display it in a ranking format. The insurance comparison unit, for example, uses the generation AI to collect insurance premium data for different car models and display it in a ranking format. For example, it displays car models with low insurance premiums in a ranking format. The insurance comparison unit also analyzes insurance premium data for different car models to enable the user to easily compare car models with low insurance premiums. For example, it provides a function to display car models with low insurance premiums in a ranking format. The insurance comparison unit also suggests the most suitable car model for the user based on the insurance premium data. For example, it displays car models with low insurance premiums in a ranking format to make it easier for the user to make a selection. This makes it possible to collect insurance premium data for different car models and display it in a ranking format.

[0106] The insurance comparison unit can use the emotion estimation function to provide advice to reduce the anxiety and concerns the user has about insurance. The insurance comparison unit, for example, uses the emotion estimation function to analyze the anxiety and concerns the user has about insurance. For example, it analyzes the user's facial expressions and voice to identify the anxiety and concerns about insurance. The insurance comparison unit also provides advice to reduce the user's anxiety and concerns. For example, it provides information and advice to reduce the anxiety about insurance. The insurance comparison unit also uses the emotion estimation function to make specific suggestions to reduce the anxiety and concerns the user has about insurance. For example, it suggests specific actions to reduce the anxiety about insurance. This makes it possible to provide advice to reduce the anxiety and concerns the user has about insurance.

[0107] The mileage fare comparison unit uses generation AI to add a function for comparing mileage fare with other transportation-related products, thereby increasing the user's awareness of transportation. For example, the mileage fare comparison unit uses generation AI to collect and compare mileage fare information from other transportation-related products in addition to car mileage fare. For example, it collects mileage fare information for public transportation and bicycles and compares it with car mileage fare. The mileage fare comparison unit also analyzes mileage fare information from other transportation-related products to allow the user to compare car mileage fare with other means of transportation. For example, it provides a function to compare public transportation and bicycle mileage fare with car mileage fare. The mileage fare comparison unit also increases the user's awareness of transportation based on the mileage fare information from other transportation-related products. For example, it provides mileage fare information for public transportation and bicycles, allowing the user to compare car mileage fare with other means of transportation. This allows the user to increase their awareness of transportation by comparing with other transportation-related products.

[0108] The mileage fee comparison unit can use the generation AI to collect mileage fee data for different vehicle types and display it in ranking format. The mileage fee comparison unit, for example, uses the generation AI to collect mileage fee data for different vehicle types and display it in ranking format. For example, it displays vehicle types with low mileage fees in ranking format. The mileage fee comparison unit also analyzes mileage fee data for different vehicle types and makes it easy for users to compare vehicle types with low mileage fees. For example, it provides a function to display vehicle types with low mileage fees in ranking format. The mileage fee comparison unit also suggests the most suitable vehicle type for the user based on the mileage fee data. For example, it displays vehicle types with low mileage fees in ranking format to make it easier for the user to make a selection. This makes it possible to collect mileage fee data for different vehicle types and display it in ranking format.

[0109] The mileage fare comparison unit can use the emotion estimation function to provide advice to reduce the anxiety and concerns the user has about the mileage toll. The mileage fare comparison unit, for example, uses the emotion estimation function to analyze the anxiety and concerns the user has about the mileage toll. For example, it analyzes the user's facial expressions and voice to identify the anxiety and concerns about the mileage toll. The mileage fare comparison unit also provides advice to reduce the user's anxiety and concerns. For example, it provides information or advice to reduce the anxiety about the mileage toll. The mileage fare comparison unit also uses the emotion estimation function to make specific suggestions to reduce the anxiety and concerns the user has about the mileage toll. For example, it suggests specific actions to reduce the anxiety about the mileage toll. This makes it possible to provide advice to reduce the anxiety and concerns the user has about the mileage toll.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The vehicle comparison system can also be equipped with a function to suggest vehicles based on the user's lifestyle. For example, if a user enjoys outdoor activities, it can suggest vehicles with excellent off-road performance. For users living in urban areas, it can suggest compact cars that are easy to park. It can also suggest family-friendly minivans and SUVs depending on the family structure. This allows it to suggest vehicles that are best suited to the user's lifestyle.

[0112] The car model comparison system can also be equipped with a function to suggest car models based on the user's health condition. For example, a car model with excellent seat support can be suggested to a user with lower back pain. Also, a car model with a highly visible display can be suggested to a user with poor eyesight. Furthermore, it is possible to suggest a car model with a powerful air purification function to a user with allergies. In this way, it is possible to suggest the car model that is best suited to the user's health condition.

[0113] The vehicle comparison system can also have a function to suggest vehicle models based on the user's hobbies and preferences. For example, a vehicle equipped with a high-quality audio system can be suggested to a user who enjoys music. A vehicle equipped with a sporty design and a high-performance engine can be suggested to a user who enjoys sports. Furthermore, a vehicle equipped with a wide range of pet accessories can be suggested to a user who keeps pets. This makes it possible to suggest a vehicle that best suits the user's hobbies and preferences.

[0114] The vehicle comparison system can also be equipped with a function to suggest vehicle models based on the user's environmental consciousness. For example, electric vehicles and hybrid vehicles can be suggested to environmentally conscious users. Also, fuel-efficient vehicles can be suggested to users who prioritize fuel efficiency. Furthermore, it is possible to suggest vehicles made from recycled materials or vehicles equipped with eco-driving functions. This allows the system to suggest vehicles that are best suited to the user's environmental consciousness.

[0115] The vehicle comparison system can also be equipped with a function to suggest vehicles based on the user's safety consciousness. For example, for a user who places importance on safety, it can suggest vehicles equipped with the latest safety features. It can also suggest vehicles with comprehensive driving assistance systems. It can also suggest vehicles with high crash test scores and vehicles that are compatible with child seats for the safety of children. This makes it possible to suggest vehicles that are optimal for the user's safety consciousness.

[0116] The car model comparison system can further estimate the user's emotions and suggest car models based on the estimated emotions. For example, if the user is excited, a sports car can be suggested. If the user is relaxed, a comfortable car model can be suggested. Furthermore, if the user is feeling stressed, a quiet and relaxing car model can be suggested. In this way, the system can suggest the most suitable car model based on the user's emotions.

[0117] The car model comparison system can further estimate the user's emotions and suggest car model customization options based on the estimated emotions. For example, if the user is excited, sporty accessories can be suggested. If the user is relaxed, options that enhance comfort can be suggested. Furthermore, if the user is stressed, options with relaxation functions can be suggested. In this way, optimal customization options can be suggested based on the user's emotions.

[0118] The vehicle comparison system can further estimate the user's emotions and suggest a test drive schedule based on the estimated emotions. For example, if the user is excited, a schedule for an immediate test drive can be suggested. If the user is relaxed, a schedule for a leisurely test drive can be suggested. Furthermore, if the user is feeling stressed, it can also suggest a test drive in a relaxing environment. In this way, the system can suggest the optimal test drive schedule based on the user's emotions.

[0119] The vehicle comparison system can further estimate the user's emotions and suggest a post-purchase support plan based on the estimated emotions. For example, if the user is excited, it can suggest a quick support plan. If the user is relaxed, it can suggest a regular maintenance plan. Furthermore, if the user is stressed, it can suggest a support plan to provide a sense of security. In this way, it is possible to suggest the optimal post-purchase support plan based on the user's emotions.

[0120] The car model comparison system can further estimate the user's emotions and suggest the best time to purchase based on the estimated emotions. For example, if the user is excited, it can suggest an immediate purchase. If the user is relaxed, it can suggest time to carefully consider the purchase. Furthermore, if the user is feeling stressed, it can provide information to reduce stress and suggest the best time to purchase. In this way, it is possible to suggest the optimal time to purchase based on the user's emotions.

[0121] The processing flow of the second embodiment will be briefly explained below.

[0122] Step 1: The price comparison unit uses generation AI to compare the prices of multiple car models the user is considering. For example, it receives as input a list of car models the user wants to compare, collects the prices of each car model, and creates a comparison table. Step 2: The fuel economy comparison unit uses the generation AI to compare the fuel economy of multiple vehicle models the user is considering. For example, it receives as input a list of vehicle models the user wants to compare, collects and analyzes fuel economy data for each vehicle model. Step 3: The quietness comparison unit uses the generation AI to compare the quietness of multiple vehicle models the user is considering. For example, it receives as input a list of vehicle models the user wants to compare, and collects and analyzes quietness data for each vehicle model. Step 4: The acceleration comparison unit uses the generation AI to compare the acceleration of multiple vehicle models the user is considering. For example, it receives as input a list of vehicle models the user wants to compare, and collects and analyzes acceleration data for each vehicle model. Step 5: The tax comparison unit uses the generation AI to compare the taxes of multiple car models the user is considering. For example, it receives a list of car models the user wants to compare as input, and collects and analyzes tax data for each car model. Step 6: The insurance comparison unit uses the generation AI to compare insurance for multiple car models the user is considering. For example, it receives as input a list of car models the user wants to compare, collects insurance premium data for each car model, and analyzes it. Step 7: The toll comparison unit uses the generation AI to compare the tolls of multiple vehicle types the user is considering. For example, it receives as input a list of vehicle types the user wants to compare, and collects and analyzes toll data for each vehicle type.

[0123] 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.

[0124] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 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.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0129] 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.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] 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.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0142] 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.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0144] 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.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0158] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0159] 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.

[0160] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0161] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0162] 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.

[0163] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0164] 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.

[0165] 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.

[0166] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0167] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0169] 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.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0171] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] 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.

[0173] 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 encompasses both emotions 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.

[0174] 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.

[0175] 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).

[0176] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0177] 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."

[0178] 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.

[0179] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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. A processor also includes 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.

[0184] The hardware resource that executes the specific process 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 process may be a single processor.

[0185] 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.

[0186] 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.

[0187] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0188] 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.

[0189] 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. [Explanation of symbols]

[0190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. Using generative AI, a price comparison unit that compares the prices of multiple car models that the user is considering; a fuel efficiency comparison unit that compares the fuel efficiency of a plurality of vehicle models that the user is considering; a quietness comparison unit that compares the quietness of a plurality of vehicle models that the user is considering; an acceleration feeling comparison unit that compares the acceleration feelings of a plurality of vehicle models that the user is considering; a tax comparison unit that compares taxes on a plurality of vehicle models that the user is considering; an insurance comparison unit that compares insurance for a plurality of vehicle types that the user is considering; a travel fee comparison unit that compares the travel fees of multiple vehicle types that the user is considering; A system characterized by:

2. The price comparison unit The generation AI is used to analyze past discount information and campaign information and predict future discounts.

2. The system of claim 1.

3. The price comparison unit Using the generative AI, a comprehensive price comparison is performed that includes not only the price of the car but also the cost of optional equipment and after-sales service.

2. The system of claim 1.

4. The price comparison unit Analyze the satisfaction level of the user regarding the price and propose the price range that provides the highest level of satisfaction 2. The system of claim 1.

5. The fuel efficiency comparison unit The generation AI is used to predict actual fuel consumption based on the user's driving style and driving environment.

2. The system of claim 1.

Images