system

Abstract

The system according to this embodiment aims to optimize the entire purchasing process by making proposals that meet the buyer's wishes, providing negotiation support in real time, and offering suggestions that meet the buyer's needs. [Solution] The system according to the embodiment comprises a reception unit, a proposal unit, a negotiation support unit, and an optimization unit. The reception unit receives the buyer's requests. The proposal unit makes proposals based on the requests received by the reception unit. The negotiation support unit provides real-time negotiation support based on the content proposed by the proposal unit. The optimization unit optimizes the entire purchase process based on the negotiation results conducted by the negotiation support unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, in the used car purchase process, proposals and negotiation support according to the purchaser's wishes are not sufficiently provided, and there is room for improvement in optimizing the entire process.

[0005] The system according to the embodiment aims to make proposals according to the purchaser's wishes, provide real-time negotiation support, and optimize the entire purchase process.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a proposal unit, a negotiation support unit, and an optimization unit. The reception unit receives the buyer's requests. The proposal unit makes proposals based on the requests received by the reception unit. The negotiation support unit provides real-time negotiation support based on the content proposed by the proposal unit. The optimization unit optimizes the entire purchase process based on the negotiation results conducted by the negotiation support unit. [Effects of the Invention]

[0007] The system according to this embodiment can make proposals that meet the buyer's wishes, provide negotiation support in real time, and optimize the entire purchasing process. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The used car purchase support system according to an embodiment of the present invention is a system that provides suggestions tailored to the buyer's wishes, real-time negotiation support, and optimization of the entire used car purchase process. This system receives the buyer's wishes, makes suggestions, provides real-time negotiation support, and optimizes the entire purchase process. For example, when a buyer inputs their wishes in natural language, the system recommends the most suitable vehicle from a used car database. Furthermore, it automatically analyzes historical data and repair history to compare prices and quality. The system provides real-time discount negotiation support and contract checks, and offers FAQs and risk education regarding purchases. Technically, it collects data through API connection from a used car information platform, understands requests using natural language processing, and performs price prediction and quality evaluation using machine learning. The interface is provided through integration with a dedicated application. The advantages of this system include time savings, provision of objective and reliable information, reduction of purchase risks, and reduction of stress. Feasibility and challenges include access to necessary data and costs, legal regulations and ethics (protection of personal information, data transparency), user education, and ensuring reliability. As a prototype, examples of conversations in which the AI ​​presents a list of candidate vehicles when the user inputs their budget and desired conditions, and examples of a web-operable interface are shown. This allows the used car purchase support system to provide suggestions tailored to the buyer's wishes, offer real-time negotiation support, and optimize the entire used car purchase process.

[0029] The used car purchase support system according to this embodiment comprises a reception unit, a proposal unit, a negotiation support unit, and an optimization unit. The reception unit receives the buyer's preferences. The buyer's preferences include, but are not limited to, price, make, model, year, and mileage. The reception unit accepts, for example, the buyer inputting their preferences in natural language. The reception unit can also store the buyer's preferences in a database for later reference. The proposal unit makes proposals based on the preferences received by the reception unit. The proposal unit recommends, for example, the most suitable vehicle from the used car database. The proposal unit can also compare multiple vehicles based on the buyer's preferences and present the best option. The proposal unit recommends vehicles that meet conditions such as price, make, model, year, and mileage based on the buyer's preferences. The negotiation support unit provides real-time negotiation support based on the content proposed by the proposal unit. The negotiation support unit assists with price negotiations, for example. The negotiation support unit can also check contracts. The negotiation support unit assists with negotiations with sellers based on the price desired by the buyer. The optimization unit optimizes the entire purchase process based on the negotiation results conducted by the negotiation support unit. For example, the optimization unit streamlines each step of the purchase process. The optimization unit can also propose an optimal purchase process based on the buyer's preferences. For example, the optimization unit proposes an optimal purchase process based on the buyer's desired delivery date and payment method. As a result, the used car purchase support system according to this embodiment can provide proposals that meet the buyer's preferences, real-time negotiation support, and optimization of the entire used car purchase process.

[0030] The reception department receives buyer preferences. These preferences include, but are not limited to, price, vehicle type, year of manufacture, and mileage. The reception department accepts buyer input of preferences in natural language. Specifically, buyers can input their desired conditions through web forms or mobile apps. For example, they can input specific requests such as, "I'm looking for an SUV with a budget of under 2 million yen. I prefer a vehicle from 2015 or later with less than 50,000 kilometers on the odometer." The reception department analyzes these inputs using natural language processing technology to accurately extract the buyer's preferences. Furthermore, the reception department can save the buyer's preferences in a database for later reference. The saved data is used to allow buyers to refer to and update their past preferences when they use the system again. This allows the reception department to accurately understand the buyer's preferences and provides a foundation for the subsequent proposal and negotiation support departments to function efficiently.

[0031] The Proposal Department makes suggestions based on the requests received by the Reception Department. For example, the Proposal Department recommends the most suitable vehicle from a used car database. Specifically, the Proposal Department searches for vehicles that meet the buyer's desired conditions, such as price, make, model year, and mileage. For example, if a buyer enters, "I'm looking for an SUV with a budget of under 2 million yen. I'd prefer a vehicle from 2015 or later with less than 50,000 km on the odometer," the Proposal Department will extract vehicles that match these conditions from the used car database. The Proposal Department can also compare multiple vehicles based on the buyer's preferences and present the best option. For example, it can compare conditions such as price, mileage, and model year and present the most attractive vehicles to the buyer in a ranking format. Furthermore, the Proposal Department can use AI to analyze the buyer's past selection history and other buyers' evaluations to provide more personalized suggestions. This allows the Proposal Department to quickly and accurately propose the most suitable vehicle that meets the buyer's needs.

[0032] The Negotiation Support Department provides real-time negotiation support based on proposals made by the Proposal Department. For example, the Negotiation Support Department assists with price negotiations. Specifically, it supports negotiations with sellers based on the buyer's desired price. For example, if a buyer wants to purchase a vehicle for 1.8 million yen, the Negotiation Support Department will begin negotiations with the seller based on that desired price. The Negotiation Support Department uses AI to analyze past negotiation data and market trends to formulate the optimal negotiation strategy. The Negotiation Support Department can also check contracts. Specifically, it automatically analyzes the contents of contracts to check whether they contain any unfavorable conditions for the buyer. Furthermore, the Negotiation Support Department also provides support to facilitate communication between buyers and sellers. For example, it uses a chatbot to answer buyer questions in real time and support interactions with sellers. In this way, the Negotiation Support Department helps buyers proceed with negotiations with peace of mind and achieve purchases under the best possible conditions.

[0033] The Optimization Department optimizes the entire purchase process based on the negotiation results conducted by the Negotiation Support Department. For example, the Optimization Department streamlines each step of the purchase process. Specifically, it can propose the optimal purchase process based on the buyer's desired delivery date and payment method. For example, if a buyer requests delivery by next week, the Optimization Department will adjust the delivery date and expedite the necessary procedures based on that request. The Optimization Department can also propose the optimal payment method based on the buyer's preferences. For example, it will compare payment methods such as lump-sum payment, installment payments, and loans and propose the most suitable method for the buyer. Furthermore, the Optimization Department monitors the progress of the entire purchase process in real time and makes adjustments as needed. For example, it checks the status of document submission and payment progress, and responds quickly if any problems arise. In this way, the Optimization Department can support buyers in smoothly purchasing used cars and improve the efficiency of the entire purchase process.

[0034] The analysis unit performs automated analysis of historical data and repair history. For example, the analysis unit analyzes past transaction history and maintenance history. For example, the analysis unit evaluates the vehicle's condition based on past transaction history. The analysis unit can also analyze the type and frequency of vehicle repairs based on repair history. For example, the analysis unit evaluates the details of vehicle repairs based on repair history. This allows for an accurate understanding of the vehicle's condition through automated analysis of historical data and repair history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input historical data and repair history into AI, which can then perform the analysis automatically.

[0035] The checking unit assists with price negotiations and checks contracts. For example, the checking unit assists with the timing and content of price negotiations. For example, the checking unit assists in negotiations with the seller based on the buyer's desired price. The checking unit can also check contracts. For example, the checking unit reviews the contents of the contract and provides advice to the buyer. This allows the buyer to proceed with the transaction with peace of mind through price negotiation assistance and contract checks. Some or all of the above processes in the checking unit may be performed using AI, for example, or not using AI. For example, the checking unit can input the contents of the contract into AI, and the AI ​​can perform the check automatically.

[0036] The Ministry of Education provides FAQs and risk education regarding purchases. For example, the Ministry of Education provides a list of common types and content of frequently asked questions. For example, the Ministry of Education provides detailed answers to questions that buyers often have. The Ministry of Education can also provide risk education. For example, the Ministry of Education educates buyers about the risks associated with purchases. This allows buyers to proceed with transactions with confidence through FAQs and risk education regarding purchases. Some or all of the above processes by the Ministry of Education may be performed using AI, or not. For example, the Ministry of Education can input the content of the FAQs into an AI, which can then automatically generate answers.

[0037] The data collection unit collects data through API connections from a used car information platform. The data collection unit collects data such as vehicle information, price information, and transaction information. For example, the data collection unit obtains the latest vehicle information from the used car information platform via API. The data collection unit can also collect price information and transaction information. For example, the data collection unit obtains the latest price information and transaction information via API. This allows for the acquisition of the latest information through data collection from the used car information platform. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the data obtained via API into an AI, which can then automatically analyze the data.

[0038] The understanding unit understands requests using natural language processing. The understanding unit understands the buyer's requests using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, the understanding unit analyzes the wishes entered by the buyer in natural language and understands their content. The understanding unit can also make optimal suggestions based on the buyer's requests. For example, the understanding unit analyzes the buyer's requests and recommends the most suitable vehicle based on that content. In this way, the buyer's requests can be accurately understood through natural language processing. Some or all of the above processing in the understanding unit may be performed using, for example, generative AI, or without generative AI. For example, the understanding unit can input the buyer's requests into a generative AI, and the generative AI can automatically analyze the requests.

[0039] The evaluation unit performs price prediction and quality assessment using machine learning. The evaluation unit uses algorithms such as supervised learning, unsupervised learning, and reinforcement learning to perform price prediction and quality assessment. For example, the evaluation unit predicts the price of a vehicle based on past transaction data. The evaluation unit can also assess the quality of a vehicle. For example, the evaluation unit assesses quality based on the vehicle's condition and repair history. This improves the accuracy of price prediction and quality assessment through machine learning. Some or all of the above processing in the evaluation unit may be performed using, for example, generative AI, or without generative AI. For example, the evaluation unit can input transaction data into a generative AI, which can then automatically perform price prediction and quality assessment.

[0040] The interface unit interacts with a dedicated application. For example, the interface unit exchanges information between the buyer and the system through the dedicated application. For example, the interface unit accepts the buyer's input of preferences through the dedicated application. The interface unit can also notify the buyer of the results of proposals and negotiation support from the system through the dedicated application. For example, the interface unit notifies the buyer of their preferences in real time after they input them through the dedicated application. This improves usability through integration with the dedicated application. Some or all of the above-described processes in the interface unit may be performed using AI, or not using AI. For example, the interface unit can input data acquired through the dedicated application into the AI, which can then automatically analyze the data.

[0041] The reception desk analyzes the buyer's past preference history and selects the most suitable reception method. For example, the reception desk automatically displays preferred conditions that the buyer has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the buyer has used in the past. Furthermore, the reception desk can predict and suggest preferred conditions to be used during specific time periods based on the buyer's past preference history. This allows the reception desk to select the most suitable reception method through analysis of past preference history. Some or all of the above processes in the reception desk may be performed using AI, or not. For example, the reception desk can input past preference history data into an AI, which can then automatically analyze the data and select the most suitable reception method based on the results.

[0042] The reception desk filters the buyer's current lifestyle and areas of interest when they make a request. For example, if the buyer enters their family structure, the reception desk will prioritize suggesting family-friendly vehicles. It can also suggest vehicles related to the buyer's hobbies and areas of interest if they enter those. Furthermore, the reception desk can suggest the most suitable vehicle based on the buyer's current lifestyle (commute distance, frequency of use, etc.). This allows for appropriate suggestions through filtering based on the buyer's lifestyle and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input data on the buyer's lifestyle and areas of interest into an AI, which can then automatically perform the filtering.

[0043] The reception desk prioritizes requests based on the buyer's geographical location, taking this information into consideration when a request is received. For example, if a buyer lives in a specific region, the reception desk will prioritize suggesting vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the reception desk can suggest vehicles suitable for that region. In addition, the reception desk can suggest the most suitable vehicle based on the buyer's geographical location. This allows for appropriate suggestions through reception that considers geographical location. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the buyer's geographical location into the AI, which can then automatically prioritize requests based on their relevance.

[0044] The reception desk analyzes the buyer's social media activity when a request is received and accepts relevant requests. For example, the reception desk suggests relevant vehicles based on the interests and preferences shared by the buyer on social media. The reception desk can also analyze the buyer's social media activity and suggest specific brands or models. Furthermore, the reception desk can suggest the most suitable vehicle based on the buyer's social media activity. In this way, relevant requests can be accepted through the analysis of social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the buyer's social media activity data into an AI, which can automatically analyze it and accept requests based on the results.

[0045] The proposal unit adjusts the level of detail in its proposals based on the importance of the vehicle. For example, it provides detailed proposals for expensive vehicles, while providing concise proposals for lower-priced vehicles. Furthermore, it can provide special proposals for rare vehicles. This adjustment of proposal detail based on vehicle importance enables appropriate proposals. Some or all of the above processing in the proposal unit may be performed using AI, or not. For example, the proposal unit can input vehicle importance data into the AI, which can then automatically adjust the level of detail in its proposals.

[0046] The proposal unit applies different proposal algorithms depending on the vehicle category when making a proposal. For example, in the case of a sports car, the proposal unit will make proposals that focus on performance. In the case of a family car, the proposal unit may also make proposals that focus on safety. Furthermore, in the case of an eco-car, the proposal unit may also make proposals that focus on fuel efficiency. This allows for appropriate proposals by applying proposal algorithms according to the vehicle category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input vehicle category data into the AI, and the AI ​​can automatically apply the proposal algorithm.

[0047] The proposal unit determines the priority of proposals based on the vehicle registration date. For example, the proposal unit may prioritize newly registered vehicles. It may also prioritize vehicles that have been registered for a certain period of time. Furthermore, the proposal unit may specially propose vehicles with rare registration dates. This allows for appropriate proposals by determining the priority of proposals based on the vehicle registration date. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input vehicle registration date data into AI, and the AI ​​can automatically determine the priority of proposals.

[0048] The proposal unit adjusts the order of proposals based on the relevance of the vehicles. For example, the proposal unit first proposes the vehicle that best matches the buyer's desired conditions. It can also propose a vehicle that partially matches the buyer's desired conditions next. Furthermore, it can propose a vehicle that does not perfectly match the buyer's desired conditions but is still relevant last. This allows for appropriate proposals by adjusting the order of proposals based on the relevance of the vehicles. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input vehicle relevance data into the AI, which can then automatically adjust the order of proposals.

[0049] The Negotiation Support Department selects the optimal negotiation support method by referring to past negotiation data during negotiation support. For example, the Negotiation Support Department selects the optimal negotiation support method based on past successful negotiation data. The Negotiation Support Department can also analyze past unsuccessful negotiation data and select a negotiation support method that reflects improvements. Furthermore, the Negotiation Support Department can select the optimal negotiation support method according to the attributes of the buyer based on past negotiation data. In this way, the optimal negotiation support method can be selected by referring to past negotiation data. Some or all of the above processes in the Negotiation Support Department may be performed using AI, for example, or not using AI. For example, the Negotiation Support Department can input past negotiation data into AI, and the AI ​​can automatically select the optimal negotiation support method.

[0050] The Negotiation Support Department provides negotiation support while considering the buyer's attribute information. For example, the Negotiation Support Department can provide negotiation support based on the buyer's age and gender. It can also provide negotiation support based on the buyer's occupation and income. Furthermore, the Negotiation Support Department can provide negotiation support based on the buyer's past purchase history. This enables appropriate negotiation support by considering the buyer's attribute information. Some or all of the above processing in the Negotiation Support Department may be performed using AI, or not. For example, the Negotiation Support Department can input the buyer's attribute information into AI, and the AI ​​can automatically perform negotiation support.

[0051] The Negotiation Support Department considers the geographical distribution of vehicles when providing negotiation support. For example, if a buyer lives in a specific region, the Negotiation Support Department will provide negotiation support for vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the Negotiation Support Department can provide negotiation support for vehicles suitable for that region. In addition, the Negotiation Support Department can provide optimal negotiation support based on the buyer's geographical location information. This enables appropriate negotiation support by considering the geographical distribution of vehicles. Some or all of the above processing in the Negotiation Support Department may be performed using AI, or not. For example, the Negotiation Support Department can input geographical distribution data of vehicles into an AI, which can then automatically perform negotiation support.

[0052] The Negotiation Support Department improves the accuracy of negotiation support by referring to relevant vehicle documentation during negotiations. For example, the Negotiation Support Department improves the accuracy of negotiation support by referring to the vehicle's technical specifications. It can also improve the accuracy of negotiation support by referring to past vehicle evaluation reports. Furthermore, the Negotiation Support Department can improve the accuracy of negotiation support by referring to vehicle market price data. In this way, the accuracy of negotiation support is improved by referring to relevant vehicle documentation. Some or all of the above processes in the Negotiation Support Department may be performed using AI, for example, or not using AI. For example, the Negotiation Support Department can input vehicle-related documentation data into AI, and the AI ​​can automatically improve the accuracy of negotiation support.

[0053] The optimization unit optimizes the optimization algorithm by referring to past optimization data during the optimization process. For example, the optimization unit selects the optimal optimization algorithm based on past successful optimization data. The optimization unit can also analyze past failed optimization data and select an optimization algorithm that reflects improvements. Furthermore, the optimization unit can select the optimal optimization algorithm according to the attributes of the buyer based on past optimization data. In this way, the optimal optimization algorithm can be selected by referring to past optimization data. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input past optimization data into AI, and the AI ​​can automatically select the optimal optimization algorithm.

[0054] The optimization unit performs optimization while considering the buyer's attribute information. For example, the optimization unit performs optimization based on the buyer's age and gender. It can also perform optimization based on the buyer's occupation and income. Furthermore, the optimization unit can perform optimization based on the buyer's past purchase history. This enables appropriate optimization by considering the buyer's attribute information. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the buyer's attribute information into AI, and the AI ​​can perform the optimization automatically.

[0055] The optimization unit performs optimization while considering the geographical distribution of vehicles. For example, if a buyer lives in a specific region, the optimization unit will optimize for vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the optimization unit can optimize for vehicles suitable for that region. In addition, the optimization unit can optimize for the optimal vehicle based on the buyer's geographical location information. This enables appropriate optimization by considering the geographical distribution of vehicles. Some or all of the above-described processes in the optimization unit may be performed using AI, or without AI. For example, the optimization unit can input vehicle geographical distribution data into AI, which can then automatically perform the optimization.

[0056] The optimization unit improves the accuracy of optimization by referring to relevant vehicle documentation during the optimization process. For example, the optimization unit improves the accuracy of optimization by referring to the vehicle's technical specifications. The optimization unit can also improve the accuracy of optimization by referring to past vehicle evaluation reports. Furthermore, the optimization unit can improve the accuracy of optimization by referring to the vehicle's market price data. Thus, the accuracy of optimization is improved by referring to relevant vehicle documentation. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input vehicle documentation data into AI, and the AI ​​can automatically improve the accuracy of optimization.

[0057] The analysis unit optimizes the analysis algorithm by referring to historical data during the analysis process. For example, the analysis unit selects the optimal analysis algorithm based on past successful analysis data. The analysis unit can also analyze past unsuccessful analysis data and select an analysis algorithm that reflects improvements. Furthermore, the analysis unit can select the optimal analysis algorithm based on the attributes of the purchaser, based on past analysis data. In this way, the optimal analysis algorithm can be selected by referring to historical data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input historical data into AI, and the AI ​​can automatically select the optimal analysis algorithm.

[0058] The analysis unit applies different analysis methods depending on the vehicle category during the analysis. For example, in the case of a sports car, the analysis unit focuses on performance. In the case of a family car, the analysis unit can also focus on safety. Furthermore, in the case of an eco-car, the analysis unit can also focus on fuel efficiency. This allows for appropriate analysis by applying analysis methods according to the vehicle category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input vehicle category data into the AI, and the AI ​​can automatically apply the analysis method.

[0059] The analysis unit considers the geographical distribution of vehicles during the analysis. For example, if a buyer lives in a specific region, the analysis unit will analyze vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the analysis unit can analyze vehicles suitable for that region. In addition, the analysis unit can analyze the optimal vehicle based on the buyer's geographical location information. This allows for a more accurate analysis by considering the geographical distribution of vehicles. Some or all of the above processing in the analysis unit may be performed using AI, or not. For example, the analysis unit can input vehicle geographical distribution data into an AI, which can then automatically perform the analysis.

[0060] The analysis department improves the accuracy of its analysis by referring to relevant vehicle literature during the analysis process. For example, the analysis department may refer to the vehicle's technical specifications to improve the accuracy of its analysis. It may also refer to past vehicle evaluation reports to improve the accuracy of its analysis. Furthermore, the analysis department may refer to market price data for the vehicle to improve the accuracy of its analysis. Thus, the accuracy of the analysis is improved by referring to relevant vehicle literature. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input relevant vehicle literature data into AI, and the AI ​​can automatically improve the accuracy of its analysis.

[0061] The checking unit optimizes the checking algorithm by referring to past contract data during the checking process. For example, the checking unit selects the optimal checking algorithm based on past successful contract data. The checking unit can also analyze past failed contract data and select a checking algorithm that reflects improvements. Furthermore, the checking unit can select the optimal checking algorithm based on past contract data and the attributes of the buyer. In this way, the optimal checking algorithm can be selected by referring to past contract data. Some or all of the above processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input past contract data into AI, and the AI ​​can automatically select the optimal checking algorithm.

[0062] The checking unit applies different checking methods depending on the category of the contract during the checking process. For example, in the case of a vehicle purchase contract, the checking unit focuses on the vehicle's technical specifications. It can also focus on the insurance coverage in the case of an insurance contract. Furthermore, in the case of a loan contract, the checking unit can focus on the repayment terms. This ensures appropriate checking by applying checking methods appropriate to the contract category. Some or all of the above-described processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input contract category data into the AI, which can then automatically apply the checking method.

[0063] The checking unit performs its checks while considering the geographical distribution of the contracts. For example, if the buyer lives in a specific region, the checking unit will check contracts relevant to that region. Furthermore, if the buyer wishes to use the contracts in a specific region, the checking unit can also check contracts suitable for that region. In addition, the checking unit can perform optimal contract checks based on the buyer's geographical location information. This ensures proper checking by considering the geographical distribution of the contracts. Some or all of the above processing in the checking unit may be performed using AI, or not. For example, the checking unit can input geographical distribution data of the contracts into an AI, which can then perform the checks automatically.

[0064] The checking unit improves the accuracy of its checks by referring to relevant documents in the contract during the checking process. For example, the checking unit can improve the accuracy of its checks by referring to the technical specifications in the contract. It can also improve the accuracy of its checks by referring to past evaluation reports of the contract. Furthermore, the checking unit can improve the accuracy of its checks by referring to market price data in the contract. In this way, the accuracy of the checks is improved by referring to relevant documents in the contract. Some or all of the above processes in the checking unit may be performed using AI, for example, or not using AI. For example, the checking unit can input the relevant document data of the contract into AI, and the AI ​​can automatically improve the accuracy of the checks.

[0065] The Ministry of Education optimizes educational algorithms by referring to past educational data during the teaching process. For example, the Ministry of Education selects the optimal educational algorithm based on past successful educational data. It can also analyze past unsuccessful educational data and select an algorithm that reflects improvements. Furthermore, the Ministry of Education can select an optimal educational algorithm based on the attributes of the purchaser, using past educational data. This allows for the selection of the optimal educational algorithm by referring to past educational data. Some or all of the above processes by the Ministry of Education may be performed using AI, for example, or without AI. For example, the Ministry of Education can input past educational data into an AI, which can then automatically select the optimal educational algorithm.

[0066] The Ministry of Education customizes educational content during training, taking into account the purchaser's attribute information. For example, the Ministry of Education provides educational content tailored to the purchaser's age and gender. It can also provide educational content tailored to the purchaser's occupation and income. Furthermore, the Ministry of Education can provide educational content based on the purchaser's past purchase history. This allows for appropriate education through the customization of educational content that takes into account the purchaser's attribute information. Some or all of the above processes by the Ministry of Education may be performed using AI, or not. For example, the Ministry of Education can input the purchaser's attribute information into an AI, which can then automatically customize the educational content.

[0067] The Ministry of Education will provide training content that takes into account the geographical distribution of vehicles. For example, if a buyer lives in a specific region, the Ministry of Education will provide training content relevant to that region. Furthermore, if a buyer wishes to use the vehicle in a specific region, the Ministry of Education can provide training content suitable for that region. In addition, the Ministry of Education can provide optimal training content based on the buyer's geographical location. This ensures appropriate training by providing training content that considers the geographical distribution of vehicles. Some or all of the above processes by the Ministry of Education may be performed using AI, or not. For example, the Ministry of Education can input vehicle geographical distribution data into an AI, which can then automatically provide training content.

[0068] The Ministry of Education improves the accuracy of training by referring to relevant vehicle documentation during training. For example, the Ministry of Education improves the accuracy of training by referring to the vehicle's technical specifications. The Ministry of Education may also improve the accuracy of training by referring to past vehicle evaluation reports. Furthermore, the Ministry of Education may also improve the accuracy of training by referring to vehicle market price data. Thus, the accuracy of training is improved by referring to relevant vehicle documentation. Some or all of the above processes by the Ministry of Education may be performed using AI, for example, or not using AI. For example, the Ministry of Education can input vehicle documentation data into AI, and the AI ​​can automatically improve the accuracy of training.

[0069] The data collection unit optimizes the data collection algorithm by referring to past data collection data during the collection process. For example, the data collection unit selects the optimal data collection algorithm based on past successful data collection. The data collection unit can also analyze past unsuccessful data collection and select a data collection algorithm that reflects improvements. Furthermore, the data collection unit can select the optimal data collection algorithm based on past data collection data and the attributes of the purchaser. In this way, the optimal data collection algorithm can be selected by referring to past data collection data. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past data collection data into AI, and the AI ​​can automatically select the optimal data collection algorithm.

[0070] The data collection unit applies different collection methods depending on the data category during collection. For example, in the case of vehicle technical data, the collection unit focuses on collecting technical specifications. It can also focus on collecting market data for vehicles, focusing on market prices. Furthermore, in the case of vehicle evaluation data, the collection unit can focus on collecting evaluation criteria. This allows for appropriate data collection by applying collection methods according to the data category. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data category information into the AI, which can then automatically apply the appropriate collection method.

[0071] The data collection unit considers the geographical distribution of the data during collection. For example, if the purchaser lives in a specific region, the collection unit will collect data relevant to that region. Furthermore, if the purchaser wishes to use the data in a specific region, the collection unit can collect data appropriate for that region. In addition, the collection unit can collect optimal data based on the purchaser's geographical location information. This ensures appropriate data collection by considering the geographical distribution of the data. Some or all of the above processing in the collection unit may be performed using AI, or without AI. For example, the collection unit can input the geographical distribution information of the data into the AI, which can then automatically perform the collection.

[0072] The data collection unit improves the accuracy of data collection by referring to relevant literature during the collection process. For example, the data collection unit may improve the accuracy of data collection by referring to the data's technical specifications. The data collection unit may also improve the accuracy of data collection by referring to past evaluation reports of the data. Furthermore, the data collection unit may also improve the accuracy of data collection by referring to market price data of the data. Thus, the accuracy of data collection is improved by referring to relevant literature of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input relevant literature information of the data into the AI, and the AI ​​can automatically improve the accuracy of data collection.

[0073] The understanding unit optimizes its understanding algorithm by referring to past request data during the understanding process. For example, the understanding unit selects the optimal understanding algorithm based on past successful request data. It can also analyze past unsuccessful request data and select an understanding algorithm that reflects improvements. Furthermore, the understanding unit can select the optimal understanding algorithm based on past request data and the attributes of the buyer. In this way, the optimal understanding algorithm can be selected by referring to past request data. Some or all of the above processes in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input past request data into AI, and the AI ​​can automatically select the optimal understanding algorithm.

[0074] The understanding unit applies different understanding methods depending on the category of the request. For example, if the request concerns vehicle performance, the understanding unit will focus its understanding on performance. It can also focus its understanding on safety if the request concerns vehicle safety. Furthermore, if the request concerns vehicle fuel efficiency, the understanding unit can focus its understanding on fuel efficiency. This allows for an appropriate understanding of the request by applying the appropriate understanding method according to the category of the request. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input the category information of the request into the AI, which can then automatically apply the appropriate understanding method.

[0075] The understanding unit considers the geographical distribution of requests when performing its understanding. For example, if a buyer lives in a specific region, the understanding unit will understand requests related to that region. Furthermore, if a buyer wishes to use the product in a specific region, the understanding unit can also understand requests appropriate for that region. In addition, the understanding unit can perform the most optimal understanding of requests based on the buyer's geographical location information. This allows for an appropriate understanding of requests by considering their geographical distribution. Some or all of the above processing in the understanding unit may be performed using AI, or without AI. For example, the understanding unit can input geographical distribution information of requests into the AI, which can then perform the understanding automatically.

[0076] The understanding unit improves the accuracy of its understanding by referring to relevant literature related to the request during the understanding process. For example, the understanding unit improves the accuracy of its understanding by referring to the technical specifications of the request. It can also improve the accuracy of its understanding by referring to past evaluation reports of the request. Furthermore, the understanding unit can improve the accuracy of its understanding by referring to market price data of the request. In this way, the accuracy of understanding is improved by referring to relevant literature related to the request. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input the relevant literature information of the request into the AI, and the AI ​​can automatically improve the accuracy of its understanding.

[0077] The evaluation unit optimizes the evaluation algorithm by referring to past evaluation data during the evaluation process. For example, the evaluation unit selects the optimal evaluation algorithm based on past successful evaluation data. The evaluation unit can also analyze past unsuccessful evaluation data and select an evaluation algorithm that reflects improvements. Furthermore, the evaluation unit can select the optimal evaluation algorithm according to the attributes of the buyer based on past evaluation data. In this way, the optimal evaluation algorithm can be selected by referring to past evaluation data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input past evaluation data into AI, and the AI ​​can automatically select the optimal evaluation algorithm.

[0078] The evaluation unit applies different evaluation methods depending on the vehicle category during the evaluation process. For example, in the case of a sports car, the evaluation unit focuses on performance. In the case of a family car, the evaluation unit may also focus on safety. Furthermore, in the case of an eco-car, the evaluation unit may also focus on fuel efficiency. This allows for appropriate evaluation by applying evaluation methods according to the vehicle category. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input vehicle category information into the AI, and the AI ​​can automatically apply the evaluation method.

[0079] The evaluation unit considers the geographical distribution of vehicles during the evaluation process. For example, if a buyer lives in a specific region, the evaluation unit evaluates vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the evaluation unit can evaluate vehicles suitable for that region. In addition, the evaluation unit can evaluate the optimal vehicle based on the buyer's geographical location information. This allows for a more accurate evaluation by considering the geographical distribution of vehicles. Some or all of the above processes in the evaluation unit may be performed using AI, or not. For example, the evaluation unit can input geographical distribution information of vehicles into an AI, which can then automatically perform the evaluation.

[0080] The evaluation unit improves the accuracy of its evaluation by referring to relevant vehicle documentation during the evaluation process. For example, the evaluation unit may refer to the vehicle's technical specifications to improve the accuracy of its evaluation. It may also refer to past evaluation reports of the vehicle to improve the accuracy of its evaluation. Furthermore, the evaluation unit may refer to market price data of the vehicle to improve the accuracy of its evaluation. Thus, the accuracy of the evaluation is improved by referring to relevant vehicle documentation. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input relevant vehicle documentation information into AI, and the AI ​​can automatically improve the accuracy of the evaluation.

[0081] The interface unit selects the optimal display method when displaying the interface by referring to the buyer's past operation history. For example, the interface unit prioritizes displaying interface designs that the buyer has frequently used in the past. The interface unit can also predict specific operation patterns from the buyer's past operation history and suggest the optimal display method. Furthermore, the interface unit can select the most efficient interface display method based on the buyer's past operation history. In this way, the optimal interface display method can be selected by referring to past operation history. Some or all of the above processing in the interface unit may be performed using AI, for example, or without AI. For example, the interface unit can input past operation history data into AI, and the AI ​​can automatically select the optimal display method.

[0082] The interface unit selects the optimal display method when displaying the interface, taking into account the purchaser's device information. For example, if the purchaser is using a smartphone, the interface unit provides a display method that matches the screen size. Furthermore, if the purchaser is using a tablet, the interface unit can provide a display method optimized for a larger screen. Additionally, if the purchaser is using a smartwatch, the interface unit can provide a concise and highly visible display method. This ensures that the appropriate interface is displayed by selecting a display method that takes device information into account. Some or all of the above processing in the interface unit may be performed using AI, or without AI. For example, the interface unit can input device information into the AI, which can then automatically select the optimal display method.

[0083] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0084] The proposal department can analyze a buyer's past purchase history to make optimal recommendations. For example, it can suggest similar vehicles based on data from vehicles the buyer has previously purchased. It can also suggest related vehicles based on data from vehicles the buyer has shown interest in in the past. Furthermore, it can analyze the buyer's interest in specific brands or models from their past purchase history and make recommendations accordingly. This allows for optimal recommendations through the analysis of past purchase history.

[0085] The analysis department can evaluate the condition of a vehicle by referring to past transaction data. For example, it can predict the price and quality of a vehicle based on past transaction data. It can also analyze past transaction data to evaluate the repair and maintenance history of a specific vehicle. Furthermore, it can predict the market value of a specific vehicle based on past transaction data. This allows for an accurate assessment of the vehicle's condition by referring to past transaction data.

[0086] The checking function can apply different checking methods depending on the category of the contract. For example, in the case of a vehicle purchase contract, the check can focus on the vehicle's technical specifications. Similarly, in the case of an insurance contract, the check can focus on the insurance coverage. Furthermore, in the case of a loan contract, the check can focus on the repayment terms. This allows for appropriate checking by applying the appropriate checking method to the category of the contract.

[0087] The Ministry of Education can customize educational content by considering the attributes of purchasers. For example, it can provide educational content tailored to the purchaser's age and gender. It can also provide educational content tailored to the purchaser's occupation and income. Furthermore, it can provide educational content based on the purchaser's past purchase history. This allows for appropriate education by customizing educational content while considering the purchaser's attributes.

[0088] The interface unit can select the optimal display method considering the purchaser's device information. For example, if the purchaser is using a smartphone, it can provide a display method adapted to the screen size. If the purchaser is using a tablet, it can provide a display method optimized for the larger screen. Furthermore, if the purchaser is using a smartwatch, it can provide a concise and highly visible display method. This ensures that the appropriate interface is displayed by selecting a display method that takes device information into account.

[0089] The following briefly describes the processing flow for example form 1.

[0090] Step 1: The reception desk receives the buyer's preferences. These preferences include, for example, price, make, model, year, and mileage. The reception desk accepts the buyer's preferences entered in natural language, stores them in a database, and makes them available for later reference. Step 2: The proposal department makes proposals based on the requests received by the reception department. The proposal department recommends the most suitable vehicles from the used car database, compares multiple vehicles based on the buyer's preferences, and presents the best option. Step 3: The Negotiation Support Department provides real-time negotiation support based on the proposals submitted by the Proposal Department. The Negotiation Support Department can assist with price negotiations and review contracts. They assist in negotiations with the seller based on the price desired by the buyer. Step 4: The Optimization Department optimizes the entire purchase process based on the negotiation results conducted by the Negotiation Support Department. The Optimization Department streamlines each step of the purchase process and proposes the optimal purchase process based on the buyer's wishes. For example, it proposes the optimal purchase process based on the buyer's desired delivery date and payment method.

[0091] (Example of form 2) The used car purchase support system according to an embodiment of the present invention is a system that provides suggestions tailored to the buyer's wishes, real-time negotiation support, and optimization of the entire used car purchase process. This system receives the buyer's wishes, makes suggestions, provides real-time negotiation support, and optimizes the entire purchase process. For example, when a buyer inputs their wishes in natural language, the system recommends the most suitable vehicle from a used car database. Furthermore, it automatically analyzes historical data and repair history to compare prices and quality. The system provides real-time discount negotiation support and contract checks, and offers FAQs and risk education regarding purchases. Technically, it collects data through API connection from a used car information platform, understands requests using natural language processing, and performs price prediction and quality evaluation using machine learning. The interface is provided through integration with a dedicated application. The advantages of this system include time savings, provision of objective and reliable information, reduction of purchase risks, and reduction of stress. Feasibility and challenges include access to necessary data and costs, legal regulations and ethics (protection of personal information, data transparency), user education, and ensuring reliability. As a prototype, examples of conversations in which the AI ​​presents a list of candidate vehicles when the user inputs their budget and desired conditions, and examples of a web-operable interface are shown. This allows the used car purchase support system to provide suggestions tailored to the buyer's wishes, offer real-time negotiation support, and optimize the entire used car purchase process.

[0092] The used car purchase support system according to this embodiment comprises a reception unit, a proposal unit, a negotiation support unit, and an optimization unit. The reception unit receives the buyer's preferences. The buyer's preferences include, but are not limited to, price, make, model, year, and mileage. The reception unit accepts, for example, the buyer inputting their preferences in natural language. The reception unit can also store the buyer's preferences in a database for later reference. The proposal unit makes proposals based on the preferences received by the reception unit. The proposal unit recommends, for example, the most suitable vehicle from the used car database. The proposal unit can also compare multiple vehicles based on the buyer's preferences and present the best option. The proposal unit recommends vehicles that meet conditions such as price, make, model, year, and mileage based on the buyer's preferences. The negotiation support unit provides real-time negotiation support based on the content proposed by the proposal unit. The negotiation support unit assists with price negotiations, for example. The negotiation support unit can also check contracts. The negotiation support unit assists with negotiations with sellers based on the price desired by the buyer. The optimization unit optimizes the entire purchase process based on the negotiation results conducted by the negotiation support unit. For example, the optimization unit streamlines each step of the purchase process. The optimization unit can also propose an optimal purchase process based on the buyer's preferences. For example, the optimization unit proposes an optimal purchase process based on the buyer's desired delivery date and payment method. As a result, the used car purchase support system according to this embodiment can provide proposals that meet the buyer's preferences, real-time negotiation support, and optimization of the entire used car purchase process.

[0093] The reception department receives buyer preferences. These preferences include, but are not limited to, price, vehicle type, year of manufacture, and mileage. The reception department accepts buyer input of preferences in natural language. Specifically, buyers can input their desired conditions through web forms or mobile apps. For example, they can input specific requests such as, "I'm looking for an SUV with a budget of under 2 million yen. I prefer a vehicle from 2015 or later with less than 50,000 kilometers on the odometer." The reception department analyzes these inputs using natural language processing technology to accurately extract the buyer's preferences. Furthermore, the reception department can save the buyer's preferences in a database for later reference. The saved data is used to allow buyers to refer to and update their past preferences when they use the system again. This allows the reception department to accurately understand the buyer's preferences and provides a foundation for the subsequent proposal and negotiation support departments to function efficiently.

[0094] The Proposal Department makes suggestions based on the requests received by the Reception Department. For example, the Proposal Department recommends the most suitable vehicle from a used car database. Specifically, the Proposal Department searches for vehicles that meet the buyer's desired conditions, such as price, make, model year, and mileage. For example, if a buyer enters, "I'm looking for an SUV with a budget of under 2 million yen. I'd prefer a vehicle from 2015 or later with less than 50,000 km on the odometer," the Proposal Department will extract vehicles that match these conditions from the used car database. The Proposal Department can also compare multiple vehicles based on the buyer's preferences and present the best option. For example, it can compare conditions such as price, mileage, and model year and present the most attractive vehicles to the buyer in a ranking format. Furthermore, the Proposal Department can use AI to analyze the buyer's past selection history and other buyers' evaluations to provide more personalized suggestions. This allows the Proposal Department to quickly and accurately propose the most suitable vehicle that meets the buyer's needs.

[0095] The Negotiation Support Department provides real-time negotiation support based on proposals made by the Proposal Department. For example, the Negotiation Support Department assists with price negotiations. Specifically, it supports negotiations with sellers based on the buyer's desired price. For example, if a buyer wants to purchase a vehicle for 1.8 million yen, the Negotiation Support Department will begin negotiations with the seller based on that desired price. The Negotiation Support Department uses AI to analyze past negotiation data and market trends to formulate the optimal negotiation strategy. The Negotiation Support Department can also check contracts. Specifically, it automatically analyzes the contents of contracts to check whether they contain any unfavorable conditions for the buyer. Furthermore, the Negotiation Support Department also provides support to facilitate communication between buyers and sellers. For example, it uses a chatbot to answer buyer questions in real time and support interactions with sellers. In this way, the Negotiation Support Department helps buyers proceed with negotiations with peace of mind and achieve purchases under the best possible conditions.

[0096] The Optimization Department optimizes the entire purchase process based on the negotiation results conducted by the Negotiation Support Department. For example, the Optimization Department streamlines each step of the purchase process. Specifically, it can propose the optimal purchase process based on the buyer's desired delivery date and payment method. For example, if a buyer requests delivery by next week, the Optimization Department will adjust the delivery date and expedite the necessary procedures based on that request. The Optimization Department can also propose the optimal payment method based on the buyer's preferences. For example, it will compare payment methods such as lump-sum payment, installment payments, and loans and propose the most suitable method for the buyer. Furthermore, the Optimization Department monitors the progress of the entire purchase process in real time and makes adjustments as needed. For example, it checks the status of document submission and payment progress, and responds quickly if any problems arise. In this way, the Optimization Department can support buyers in smoothly purchasing used cars and improve the efficiency of the entire purchase process.

[0097] The analysis unit performs automated analysis of historical data and repair history. For example, the analysis unit analyzes past transaction history and maintenance history. For example, the analysis unit evaluates the vehicle's condition based on past transaction history. The analysis unit can also analyze the type and frequency of vehicle repairs based on repair history. For example, the analysis unit evaluates the details of vehicle repairs based on repair history. This allows for an accurate understanding of the vehicle's condition through automated analysis of historical data and repair history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input historical data and repair history into AI, which can then perform the analysis automatically.

[0098] The checking unit assists with price negotiations and checks contracts. For example, the checking unit assists with the timing and content of price negotiations. For example, the checking unit assists in negotiations with the seller based on the buyer's desired price. The checking unit can also check contracts. For example, the checking unit reviews the contents of the contract and provides advice to the buyer. This allows the buyer to proceed with the transaction with peace of mind through price negotiation assistance and contract checks. Some or all of the above processes in the checking unit may be performed using AI, for example, or not using AI. For example, the checking unit can input the contents of the contract into AI, and the AI ​​can perform the check automatically.

[0099] The Ministry of Education provides FAQs and risk education regarding purchases. For example, the Ministry of Education provides a list of common types and content of frequently asked questions. For example, the Ministry of Education provides detailed answers to questions that buyers often have. The Ministry of Education can also provide risk education. For example, the Ministry of Education educates buyers about the risks associated with purchases. This allows buyers to proceed with transactions with confidence through FAQs and risk education regarding purchases. Some or all of the above processes by the Ministry of Education may be performed using AI, or not. For example, the Ministry of Education can input the content of the FAQs into an AI, which can then automatically generate answers.

[0100] The data collection unit collects data through API connections from a used car information platform. The data collection unit collects data such as vehicle information, price information, and transaction information. For example, the data collection unit obtains the latest vehicle information from the used car information platform via API. The data collection unit can also collect price information and transaction information. For example, the data collection unit obtains the latest price information and transaction information via API. This allows for the acquisition of the latest information through data collection from the used car information platform. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input the data obtained via API into an AI, which can then automatically analyze the data.

[0101] The understanding unit understands requests using natural language processing. The understanding unit understands the buyer's requests using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, the understanding unit analyzes the wishes entered by the buyer in natural language and understands their content. The understanding unit can also make optimal suggestions based on the buyer's requests. For example, the understanding unit analyzes the buyer's requests and recommends the most suitable vehicle based on that content. In this way, the buyer's requests can be accurately understood through natural language processing. Some or all of the above processing in the understanding unit may be performed using, for example, generative AI, or without generative AI. For example, the understanding unit can input the buyer's requests into a generative AI, and the generative AI can automatically analyze the requests.

[0102] The evaluation unit performs price prediction and quality assessment using machine learning. The evaluation unit uses algorithms such as supervised learning, unsupervised learning, and reinforcement learning to perform price prediction and quality assessment. For example, the evaluation unit predicts the price of a vehicle based on past transaction data. The evaluation unit can also assess the quality of a vehicle. For example, the evaluation unit assesses quality based on the vehicle's condition and repair history. This improves the accuracy of price prediction and quality assessment through machine learning. Some or all of the above processing in the evaluation unit may be performed using, for example, generative AI, or without generative AI. For example, the evaluation unit can input transaction data into a generative AI, which can then automatically perform price prediction and quality assessment.

[0103] The interface unit interacts with a dedicated application. For example, the interface unit exchanges information between the buyer and the system through the dedicated application. For example, the interface unit accepts the buyer's input of preferences through the dedicated application. The interface unit can also notify the buyer of the results of proposals and negotiation support from the system through the dedicated application. For example, the interface unit notifies the buyer of their preferences in real time after they input them through the dedicated application. This improves usability through integration with the dedicated application. Some or all of the above-described processes in the interface unit may be performed using AI, or not using AI. For example, the interface unit can input data acquired through the dedicated application into the AI, which can then automatically analyze the data.

[0104] The reception desk estimates the customer's emotions and adjusts the reception method based on the estimated emotions. For example, if the customer is stressed, the reception desk provides a simple interface and minimizes the input steps. If the customer is relaxed, the reception desk can also provide detailed input options and suggest a customizable input method. Furthermore, if the customer is in a hurry, the reception desk can prioritize voice input to allow for quick input of their preferences. This improves usability by adjusting the reception method according to the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input customer emotion data into a generative AI, which can automatically estimate the emotions and adjust the reception method based on the result.

[0105] The reception desk analyzes the buyer's past preference history and selects the most suitable reception method. For example, the reception desk automatically displays preferred conditions that the buyer has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the buyer has used in the past. Furthermore, the reception desk can predict and suggest preferred conditions to be used during specific time periods based on the buyer's past preference history. This allows the reception desk to select the most suitable reception method through analysis of past preference history. Some or all of the above processes in the reception desk may be performed using AI, or not. For example, the reception desk can input past preference history data into an AI, which can then automatically analyze the data and select the most suitable reception method based on the results.

[0106] The reception desk filters the buyer's current lifestyle and areas of interest when they make a request. For example, if the buyer enters their family structure, the reception desk will prioritize suggesting family-friendly vehicles. It can also suggest vehicles related to the buyer's hobbies and areas of interest if they enter those. Furthermore, the reception desk can suggest the most suitable vehicle based on the buyer's current lifestyle (commute distance, frequency of use, etc.). This allows for appropriate suggestions through filtering based on the buyer's lifestyle and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input data on the buyer's lifestyle and areas of interest into an AI, which can then automatically perform the filtering.

[0107] The reception desk estimates the buyer's emotions and determines the priority of requests to be received based on the estimated emotions. For example, if the buyer is in a hurry, the reception desk will prioritize the most important requests. If the buyer is relaxed, the reception desk may also prioritize detailed requests. Furthermore, if the buyer is feeling anxious, the reception desk may prioritize requests that provide reassurance. This allows for appropriate suggestions by determining priorities according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the buyer's emotion data into a generative AI, which can automatically estimate the emotions and determine the priority of requests based on the results.

[0108] The reception desk prioritizes requests based on the buyer's geographical location, taking this information into consideration when a request is received. For example, if a buyer lives in a specific region, the reception desk will prioritize suggesting vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the reception desk can suggest vehicles suitable for that region. In addition, the reception desk can suggest the most suitable vehicle based on the buyer's geographical location. This allows for appropriate suggestions through reception that considers geographical location. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the buyer's geographical location into the AI, which can then automatically prioritize requests based on their relevance.

[0109] The reception desk analyzes the buyer's social media activity when a request is received and accepts relevant requests. For example, the reception desk suggests relevant vehicles based on the interests and preferences shared by the buyer on social media. The reception desk can also analyze the buyer's social media activity and suggest specific brands or models. Furthermore, the reception desk can suggest the most suitable vehicle based on the buyer's social media activity. In this way, relevant requests can be accepted through the analysis of social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the buyer's social media activity data into an AI, which can automatically analyze it and accept requests based on the results.

[0110] The proposal unit estimates the buyer's emotions and adjusts the presentation of the proposal based on the estimated emotions. For example, if the buyer is relaxed, the proposal unit will provide a detailed proposal. If the buyer is in a hurry, the proposal unit can provide a concise proposal. Furthermore, if the buyer is excited, the proposal unit can provide a visually appealing proposal. This allows for appropriate proposals by adjusting the presentation of the proposal according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input buyer emotion data into a generative AI, which can automatically estimate the emotions and adjust the presentation of the proposal based on the result.

[0111] The proposal unit adjusts the level of detail in its proposals based on the importance of the vehicle. For example, it provides detailed proposals for expensive vehicles, while providing concise proposals for lower-priced vehicles. Furthermore, it can provide special proposals for rare vehicles. This adjustment of proposal detail based on vehicle importance enables appropriate proposals. Some or all of the above processing in the proposal unit may be performed using AI, or not. For example, the proposal unit can input vehicle importance data into the AI, which can then automatically adjust the level of detail in its proposals.

[0112] The proposal unit applies different proposal algorithms depending on the vehicle category when making a proposal. For example, in the case of a sports car, the proposal unit will make proposals that focus on performance. In the case of a family car, the proposal unit may also make proposals that focus on safety. Furthermore, in the case of an eco-car, the proposal unit may also make proposals that focus on fuel efficiency. This allows for appropriate proposals by applying proposal algorithms according to the vehicle category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input vehicle category data into the AI, and the AI ​​can automatically apply the proposal algorithm.

[0113] The suggestion unit estimates the buyer's emotions and adjusts the length of the suggestion based on the estimated emotions. For example, if the buyer is in a hurry, the suggestion unit will make a short, to-the-point suggestion. If the buyer is relaxed, the suggestion unit may make a longer suggestion that includes detailed explanations. Furthermore, if the buyer is excited, the suggestion unit may make a visually stimulating suggestion. This allows for appropriate suggestions by adjusting the length of the suggestion according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input buyer emotion data into a generative AI, which can automatically estimate the emotions and adjust the length of the suggestion based on the result.

[0114] The proposal unit determines the priority of proposals based on the vehicle registration date. For example, the proposal unit may prioritize newly registered vehicles. It may also prioritize vehicles that have been registered for a certain period of time. Furthermore, the proposal unit may specially propose vehicles with rare registration dates. This allows for appropriate proposals by determining the priority of proposals based on the vehicle registration date. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input vehicle registration date data into AI, and the AI ​​can automatically determine the priority of proposals.

[0115] The proposal unit adjusts the order of proposals based on the relevance of the vehicles. For example, the proposal unit first proposes the vehicle that best matches the buyer's desired conditions. It can also propose a vehicle that partially matches the buyer's desired conditions next. Furthermore, it can propose a vehicle that does not perfectly match the buyer's desired conditions but is still relevant last. This allows for appropriate proposals by adjusting the order of proposals based on the relevance of the vehicles. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input vehicle relevance data into the AI, which can then automatically adjust the order of proposals.

[0116] The negotiation support unit estimates the buyer's emotions and adjusts its negotiation support methods based on the estimated emotions. For example, if the buyer is nervous, the negotiation support unit will provide negotiation support in a calm tone. Conversely, if the buyer is relaxed, the negotiation support unit can provide proactive negotiation support. Furthermore, if the buyer is in a hurry, the negotiation support unit can provide rapid negotiation support. This allows for appropriate negotiation support by adjusting the negotiation support methods according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the negotiation support unit may be performed using AI or not. For example, the negotiation support unit can input buyer emotion data into a generative AI, which can automatically estimate the emotions and adjust the negotiation support methods based on the results.

[0117] The Negotiation Support Department selects the optimal negotiation support method by referring to past negotiation data during negotiation support. For example, the Negotiation Support Department selects the optimal negotiation support method based on past successful negotiation data. The Negotiation Support Department can also analyze past unsuccessful negotiation data and select a negotiation support method that reflects improvements. Furthermore, the Negotiation Support Department can select the optimal negotiation support method according to the attributes of the buyer based on past negotiation data. In this way, the optimal negotiation support method can be selected by referring to past negotiation data. Some or all of the above processes in the Negotiation Support Department may be performed using AI, for example, or not using AI. For example, the Negotiation Support Department can input past negotiation data into AI, and the AI ​​can automatically select the optimal negotiation support method.

[0118] The Negotiation Support Department provides negotiation support while considering the buyer's attribute information. For example, the Negotiation Support Department can provide negotiation support based on the buyer's age and gender. It can also provide negotiation support based on the buyer's occupation and income. Furthermore, the Negotiation Support Department can provide negotiation support based on the buyer's past purchase history. This enables appropriate negotiation support by considering the buyer's attribute information. Some or all of the above processing in the Negotiation Support Department may be performed using AI, or not. For example, the Negotiation Support Department can input the buyer's attribute information into AI, and the AI ​​can automatically perform negotiation support.

[0119] The negotiation support unit estimates the buyer's emotions and determines the priority of negotiation support based on the estimated emotions. For example, if the buyer is in a hurry, the negotiation support unit will prioritize the most important negotiation support. If the buyer is relaxed, the negotiation support unit can also provide detailed negotiation support. Furthermore, if the buyer is feeling anxious, the negotiation support unit can prioritize negotiation support that provides reassurance. This allows for appropriate negotiation support by determining the priority of negotiation support according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the negotiation support unit may be performed using AI or not. For example, the negotiation support unit can input buyer emotion data into a generative AI, which can automatically estimate emotions and determine the priority of negotiation support based on the results.

[0120] The Negotiation Support Department considers the geographical distribution of vehicles when providing negotiation support. For example, if a buyer lives in a specific region, the Negotiation Support Department will provide negotiation support for vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the Negotiation Support Department can provide negotiation support for vehicles suitable for that region. In addition, the Negotiation Support Department can provide optimal negotiation support based on the buyer's geographical location information. This enables appropriate negotiation support by considering the geographical distribution of vehicles. Some or all of the above processing in the Negotiation Support Department may be performed using AI, or not. For example, the Negotiation Support Department can input geographical distribution data of vehicles into an AI, which can then automatically perform negotiation support.

[0121] The Negotiation Support Department improves the accuracy of negotiation support by referring to relevant vehicle documentation during negotiations. For example, the Negotiation Support Department improves the accuracy of negotiation support by referring to the vehicle's technical specifications. It can also improve the accuracy of negotiation support by referring to past vehicle evaluation reports. Furthermore, the Negotiation Support Department can improve the accuracy of negotiation support by referring to vehicle market price data. In this way, the accuracy of negotiation support is improved by referring to relevant vehicle documentation. Some or all of the above processes in the Negotiation Support Department may be performed using AI, for example, or not using AI. For example, the Negotiation Support Department can input vehicle-related documentation data into AI, and the AI ​​can automatically improve the accuracy of negotiation support.

[0122] The optimization unit estimates the buyer's emotions and adjusts the optimization method based on the estimated emotions. For example, if the buyer is relaxed, the optimization unit performs detailed optimization. It can also perform rapid optimization if the buyer is in a hurry. Furthermore, if the buyer is excited, the optimization unit can perform visually appealing optimization. This allows for appropriate optimization by adjusting the optimization method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI, or not. For example, the optimization unit can input buyer emotion data into a generative AI, which can automatically estimate emotions and adjust the optimization method based on the results.

[0123] The optimization unit optimizes the optimization algorithm by referring to past optimization data during the optimization process. For example, the optimization unit selects the optimal optimization algorithm based on past successful optimization data. The optimization unit can also analyze past failed optimization data and select an optimization algorithm that reflects improvements. Furthermore, the optimization unit can select the optimal optimization algorithm according to the attributes of the buyer based on past optimization data. In this way, the optimal optimization algorithm can be selected by referring to past optimization data. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input past optimization data into AI, and the AI ​​can automatically select the optimal optimization algorithm.

[0124] The optimization unit performs optimization while considering the buyer's attribute information. For example, the optimization unit performs optimization based on the buyer's age and gender. It can also perform optimization based on the buyer's occupation and income. Furthermore, the optimization unit can perform optimization based on the buyer's past purchase history. This enables appropriate optimization by considering the buyer's attribute information. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the buyer's attribute information into AI, and the AI ​​can perform the optimization automatically.

[0125] The optimization unit estimates the buyer's emotions and determines optimization priorities based on the estimated emotions. For example, if the buyer is in a hurry, the optimization unit prioritizes the most important optimizations. If the buyer is relaxed, the optimization unit can also perform detailed optimizations. Furthermore, if the buyer is feeling anxious, the optimization unit can prioritize optimizations that provide a sense of security. This allows for appropriate optimization by determining optimization priorities according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI or not. For example, the optimization unit can input buyer emotion data into a generative AI, which can automatically estimate emotions and determine optimization priorities based on the results.

[0126] The optimization unit performs optimization while considering the geographical distribution of vehicles. For example, if a buyer lives in a specific region, the optimization unit will optimize for vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the optimization unit can optimize for vehicles suitable for that region. In addition, the optimization unit can optimize for the optimal vehicle based on the buyer's geographical location information. This enables appropriate optimization by considering the geographical distribution of vehicles. Some or all of the above-described processes in the optimization unit may be performed using AI, or without AI. For example, the optimization unit can input vehicle geographical distribution data into AI, which can then automatically perform the optimization.

[0127] The optimization unit improves the accuracy of optimization by referring to relevant vehicle documentation during the optimization process. For example, the optimization unit improves the accuracy of optimization by referring to the vehicle's technical specifications. The optimization unit can also improve the accuracy of optimization by referring to past vehicle evaluation reports. Furthermore, the optimization unit can improve the accuracy of optimization by referring to the vehicle's market price data. Thus, the accuracy of optimization is improved by referring to relevant vehicle documentation. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input vehicle documentation data into AI, and the AI ​​can automatically improve the accuracy of optimization.

[0128] The analysis unit estimates the buyer's emotions and adjusts the analysis method of historical data and repair history based on the estimated emotions. For example, if the buyer is relaxed, the analysis unit performs a detailed analysis. The analysis unit can also perform a rapid analysis if the buyer is in a hurry. Furthermore, if the buyer is excited, the analysis unit can perform a visually appealing analysis. This allows for appropriate analysis by adjusting the analysis method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the buyer's emotion data into a generative AI, which can automatically estimate the emotions and adjust the analysis method based on the results.

[0129] The analysis unit optimizes the analysis algorithm by referring to historical data during the analysis process. For example, the analysis unit selects the optimal analysis algorithm based on past successful analysis data. The analysis unit can also analyze past unsuccessful analysis data and select an analysis algorithm that reflects improvements. Furthermore, the analysis unit can select the optimal analysis algorithm based on the attributes of the purchaser, based on past analysis data. In this way, the optimal analysis algorithm can be selected by referring to historical data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input historical data into AI, and the AI ​​can automatically select the optimal analysis algorithm.

[0130] The analysis unit applies different analysis methods depending on the vehicle category during the analysis. For example, in the case of a sports car, the analysis unit focuses on performance. In the case of a family car, the analysis unit can also focus on safety. Furthermore, in the case of an eco-car, the analysis unit can also focus on fuel efficiency. This allows for appropriate analysis by applying analysis methods according to the vehicle category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input vehicle category data into the AI, and the AI ​​can automatically apply the analysis method.

[0131] The analysis unit estimates the buyer's emotions and adjusts the display method of the analysis results based on the estimated emotions. For example, if the buyer is nervous, the analysis unit provides a simple and highly visible display method. If the buyer is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if the buyer is in a hurry, the analysis unit can provide a concise display method. This allows for the display of appropriate analysis results by adjusting the display method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input buyer emotion data into a generative AI, which can automatically estimate emotions and adjust the display method based on the results.

[0132] The analysis unit considers the geographical distribution of vehicles during the analysis. For example, if a buyer lives in a specific region, the analysis unit will analyze vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the analysis unit can analyze vehicles suitable for that region. In addition, the analysis unit can analyze the optimal vehicle based on the buyer's geographical location information. This allows for a more accurate analysis by considering the geographical distribution of vehicles. Some or all of the above processing in the analysis unit may be performed using AI, or not. For example, the analysis unit can input vehicle geographical distribution data into an AI, which can then automatically perform the analysis.

[0133] The analysis department improves the accuracy of its analysis by referring to relevant vehicle literature during the analysis process. For example, the analysis department may refer to the vehicle's technical specifications to improve the accuracy of its analysis. It may also refer to past vehicle evaluation reports to improve the accuracy of its analysis. Furthermore, the analysis department may refer to market price data for the vehicle to improve the accuracy of its analysis. Thus, the accuracy of the analysis is improved by referring to relevant vehicle literature. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input relevant vehicle literature data into AI, and the AI ​​can automatically improve the accuracy of its analysis.

[0134] The checking unit estimates the buyer's emotions and adjusts the contract checking method based on the estimated emotions. For example, if the buyer is nervous, the checking unit provides a simple and highly visible checking method. If the buyer is relaxed, the checking unit can also provide a checking method that includes detailed information. Furthermore, if the buyer is in a hurry, the checking unit can provide a concise checking method. This allows for proper contract checking by adjusting the checking method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI or not using AI. For example, the checking unit can input buyer emotion data into a generative AI, which can automatically estimate the emotions and adjust the checking method based on the result.

[0135] The checking unit optimizes the checking algorithm by referring to past contract data during the checking process. For example, the checking unit selects the optimal checking algorithm based on past successful contract data. The checking unit can also analyze past failed contract data and select a checking algorithm that reflects improvements. Furthermore, the checking unit can select the optimal checking algorithm based on past contract data and the attributes of the buyer. In this way, the optimal checking algorithm can be selected by referring to past contract data. Some or all of the above processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input past contract data into AI, and the AI ​​can automatically select the optimal checking algorithm.

[0136] The checking unit applies different checking methods depending on the category of the contract during the checking process. For example, in the case of a vehicle purchase contract, the checking unit focuses on the vehicle's technical specifications. It can also focus on the insurance coverage in the case of an insurance contract. Furthermore, in the case of a loan contract, the checking unit can focus on the repayment terms. This ensures appropriate checking by applying checking methods appropriate to the contract category. Some or all of the above-described processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input contract category data into the AI, which can then automatically apply the checking method.

[0137] The checking unit estimates the buyer's emotions and adjusts the display method of the check results based on the estimated emotions. For example, if the buyer is nervous, the checking unit provides a simple and highly visible display method. If the buyer is relaxed, the checking unit can also provide a display method that includes detailed information. Furthermore, if the buyer is in a hurry, the checking unit can provide a display method that gets straight to the point. This allows for the display of appropriate check results by adjusting the display method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI or not using AI. For example, the checking unit can input the buyer's emotion data into the generative AI, which can automatically estimate the emotions and adjust the display method based on the result.

[0138] The checking unit performs its checks while considering the geographical distribution of the contracts. For example, if the buyer lives in a specific region, the checking unit will check contracts relevant to that region. Furthermore, if the buyer wishes to use the contracts in a specific region, the checking unit can also check contracts suitable for that region. In addition, the checking unit can perform optimal contract checks based on the buyer's geographical location information. This ensures proper checking by considering the geographical distribution of the contracts. Some or all of the above processing in the checking unit may be performed using AI, or not. For example, the checking unit can input geographical distribution data of the contracts into an AI, which can then perform the checks automatically.

[0139] The checking unit improves the accuracy of its checks by referring to relevant documents in the contract during the checking process. For example, the checking unit can improve the accuracy of its checks by referring to the technical specifications in the contract. It can also improve the accuracy of its checks by referring to past evaluation reports of the contract. Furthermore, the checking unit can improve the accuracy of its checks by referring to market price data in the contract. In this way, the accuracy of the checks is improved by referring to relevant documents in the contract. Some or all of the above processes in the checking unit may be performed using AI, for example, or not using AI. For example, the checking unit can input the relevant document data of the contract into AI, and the AI ​​can automatically improve the accuracy of the checks.

[0140] The Ministry of Education estimates the buyer's emotions and adjusts the educational content based on those emotions. For example, if the buyer is nervous, the Ministry of Education provides simple and highly visual educational content. If the buyer is relaxed, the Ministry of Education can also provide educational content that includes detailed information. Furthermore, if the buyer is in a hurry, the Ministry of Education can provide educational content that gets straight to the point. This allows for appropriate education by adjusting the educational content according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing by the Ministry of Education may be performed using AI or not. For example, the Ministry of Education can input buyer emotion data into a generative AI, which can automatically estimate emotions and adjust the educational content based on the result.

[0141] The Ministry of Education optimizes educational algorithms by referring to past educational data during the teaching process. For example, the Ministry of Education selects the optimal educational algorithm based on past successful educational data. It can also analyze past unsuccessful educational data and select an algorithm that reflects improvements. Furthermore, the Ministry of Education can select an optimal educational algorithm based on the attributes of the purchaser, using past educational data. This allows for the selection of the optimal educational algorithm by referring to past educational data. Some or all of the above processes by the Ministry of Education may be performed using AI, for example, or without AI. For example, the Ministry of Education can input past educational data into an AI, which can then automatically select the optimal educational algorithm.

[0142] The Ministry of Education customizes educational content during training, taking into account the purchaser's attribute information. For example, the Ministry of Education provides educational content tailored to the purchaser's age and gender. It can also provide educational content tailored to the purchaser's occupation and income. Furthermore, the Ministry of Education can provide educational content based on the purchaser's past purchase history. This allows for appropriate education through the customization of educational content that takes into account the purchaser's attribute information. Some or all of the above processes by the Ministry of Education may be performed using AI, or not. For example, the Ministry of Education can input the purchaser's attribute information into an AI, which can then automatically customize the educational content.

[0143] The Ministry of Education estimates the buyer's emotions and prioritizes education based on those estimated emotions. For example, if the buyer is in a hurry, the Ministry of Education will prioritize providing the most important educational content. If the buyer is relaxed, the Ministry of Education may also provide more detailed educational content. Furthermore, if the buyer is feeling anxious, the Ministry of Education may prioritize providing reassuring educational content. This allows for appropriate education by prioritizing education according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing by the Ministry of Education may be performed using AI or not. For example, the Ministry of Education can input buyer emotion data into a generative AI, which can automatically estimate emotions and determine educational priorities based on the results.

[0144] The Ministry of Education will provide training content that takes into account the geographical distribution of vehicles. For example, if a buyer lives in a specific region, the Ministry of Education will provide training content relevant to that region. Furthermore, if a buyer wishes to use the vehicle in a specific region, the Ministry of Education can provide training content suitable for that region. In addition, the Ministry of Education can provide optimal training content based on the buyer's geographical location. This ensures appropriate training by providing training content that considers the geographical distribution of vehicles. Some or all of the above processes by the Ministry of Education may be performed using AI, or not. For example, the Ministry of Education can input vehicle geographical distribution data into an AI, which can then automatically provide training content.

[0145] The Ministry of Education improves the accuracy of training by referring to relevant vehicle documentation during training. For example, the Ministry of Education improves the accuracy of training by referring to the vehicle's technical specifications. The Ministry of Education may also improve the accuracy of training by referring to past vehicle evaluation reports. Furthermore, the Ministry of Education may also improve the accuracy of training by referring to vehicle market price data. Thus, the accuracy of training is improved by referring to relevant vehicle documentation. Some or all of the above processes by the Ministry of Education may be performed using AI, for example, or not using AI. For example, the Ministry of Education can input vehicle documentation data into AI, and the AI ​​can automatically improve the accuracy of training.

[0146] The data collection unit estimates the buyer's emotions and adjusts the data collection method based on the estimated emotions. For example, if the buyer is relaxed, the data collection unit can perform detailed data collection. If the buyer is in a hurry, the data collection unit can perform rapid data collection. Furthermore, if the buyer is excited, the data collection unit can perform visually appealing data collection. This allows for appropriate data collection by adjusting the data collection method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input the buyer's emotion data into a generative AI, which can automatically estimate the emotions and adjust the data collection method based on the results.

[0147] The data collection unit optimizes the data collection algorithm by referring to past data collection data during the collection process. For example, the data collection unit selects the optimal data collection algorithm based on past successful data collection. The data collection unit can also analyze past unsuccessful data collection and select a data collection algorithm that reflects improvements. Furthermore, the data collection unit can select the optimal data collection algorithm based on past data collection data and the attributes of the purchaser. In this way, the optimal data collection algorithm can be selected by referring to past data collection data. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past data collection data into AI, and the AI ​​can automatically select the optimal data collection algorithm.

[0148] The data collection unit applies different collection methods depending on the data category during collection. For example, in the case of vehicle technical data, the collection unit focuses on collecting technical specifications. It can also focus on collecting market data for vehicles, focusing on market prices. Furthermore, in the case of vehicle evaluation data, the collection unit can focus on collecting evaluation criteria. This allows for appropriate data collection by applying collection methods according to the data category. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data category information into the AI, which can then automatically apply the appropriate collection method.

[0149] The data collection unit estimates the buyer's emotions and adjusts the display method of the collected data based on the estimated emotions. For example, if the buyer is nervous, the data collection unit provides a simple and highly visible display method. If the buyer is relaxed, the data collection unit can also provide a display method that includes detailed information. Furthermore, if the buyer is in a hurry, the data collection unit can provide a concise display method. This allows for the display of appropriate collected data by adjusting the display method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input the buyer's emotion data into a generative AI, which can automatically estimate the emotions and adjust the display method based on the result.

[0150] The data collection unit considers the geographical distribution of the data during collection. For example, if the purchaser lives in a specific region, the collection unit will collect data relevant to that region. Furthermore, if the purchaser wishes to use the data in a specific region, the collection unit can collect data appropriate for that region. In addition, the collection unit can collect optimal data based on the purchaser's geographical location information. This ensures appropriate data collection by considering the geographical distribution of the data. Some or all of the above processing in the collection unit may be performed using AI, or without AI. For example, the collection unit can input the geographical distribution information of the data into the AI, which can then automatically perform the collection.

[0151] The data collection unit improves the accuracy of data collection by referring to relevant literature during the collection process. For example, the data collection unit may improve the accuracy of data collection by referring to the data's technical specifications. The data collection unit may also improve the accuracy of data collection by referring to past evaluation reports of the data. Furthermore, the data collection unit may also improve the accuracy of data collection by referring to market price data of the data. Thus, the accuracy of data collection is improved by referring to relevant literature of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input relevant literature information of the data into the AI, and the AI ​​can automatically improve the accuracy of data collection.

[0152] The understanding unit estimates the buyer's emotions and adjusts how it understands their requests based on the estimated emotions. For example, if the buyer is relaxed, the understanding unit can understand detailed requests. It can also quickly understand requests if the buyer is in a hurry. Furthermore, if the buyer is excited, the understanding unit can understand requests that are visually appealing. This allows for appropriate understanding of requests by adjusting how the request understanding method is adapted to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the understanding unit may be performed using AI or not using AI. For example, the understanding unit can input buyer emotion data into a generative AI, which can automatically estimate emotions and adjust how it understands requests based on the results.

[0153] The understanding unit optimizes its understanding algorithm by referring to past request data during the understanding process. For example, the understanding unit selects the optimal understanding algorithm based on past successful request data. It can also analyze past unsuccessful request data and select an understanding algorithm that reflects improvements. Furthermore, the understanding unit can select the optimal understanding algorithm based on past request data and the attributes of the buyer. In this way, the optimal understanding algorithm can be selected by referring to past request data. Some or all of the above processes in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input past request data into AI, and the AI ​​can automatically select the optimal understanding algorithm.

[0154] The understanding unit applies different understanding methods depending on the category of the request. For example, if the request concerns vehicle performance, the understanding unit will focus its understanding on performance. It can also focus its understanding on safety if the request concerns vehicle safety. Furthermore, if the request concerns vehicle fuel efficiency, the understanding unit can focus its understanding on fuel efficiency. This allows for an appropriate understanding of the request by applying the appropriate understanding method according to the category of the request. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input the category information of the request into the AI, which can then automatically apply the appropriate understanding method.

[0155] The understanding unit estimates the buyer's emotions and adjusts the display method of the understanding results based on the estimated emotions. For example, if the buyer is nervous, the understanding unit provides a simple and highly visible display method. If the buyer is relaxed, the understanding unit can also provide a display method that includes detailed information. Furthermore, if the buyer is in a hurry, the understanding unit can provide a concise display method. This allows for the display of appropriate understanding results by adjusting the display method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the understanding unit may be performed using AI or not using AI. For example, the understanding unit can input the buyer's emotion data into the generative AI, which can automatically estimate the emotions and adjust the display method based on the results.

[0156] The understanding unit considers the geographical distribution of requests when performing its understanding. For example, if a buyer lives in a specific region, the understanding unit will understand requests related to that region. Furthermore, if a buyer wishes to use the product in a specific region, the understanding unit can also understand requests appropriate for that region. In addition, the understanding unit can perform the most optimal understanding of requests based on the buyer's geographical location information. This allows for an appropriate understanding of requests by considering their geographical distribution. Some or all of the above processing in the understanding unit may be performed using AI, or without AI. For example, the understanding unit can input geographical distribution information of requests into the AI, which can then perform the understanding automatically.

[0157] The understanding unit improves the accuracy of its understanding by referring to relevant literature related to the request during the understanding process. For example, the understanding unit improves the accuracy of its understanding by referring to the technical specifications of the request. It can also improve the accuracy of its understanding by referring to past evaluation reports of the request. Furthermore, the understanding unit can improve the accuracy of its understanding by referring to market price data of the request. In this way, the accuracy of understanding is improved by referring to relevant literature related to the request. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input the relevant literature information of the request into the AI, and the AI ​​can automatically improve the accuracy of its understanding.

[0158] The evaluation unit estimates the buyer's emotions and adjusts the price prediction and quality evaluation methods based on the estimated emotions. For example, if the buyer is relaxed, the evaluation unit performs a detailed price prediction and quality evaluation. If the buyer is in a hurry, the evaluation unit can also perform a rapid price prediction and quality evaluation. Furthermore, if the buyer is excited, the evaluation unit can perform a visually appealing price prediction and quality evaluation. This allows for appropriate price prediction and quality evaluation by adjusting the price prediction and quality evaluation methods according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI or not using AI. For example, the evaluation unit can input buyer emotion data into a generative AI, which can automatically estimate emotions and adjust the price prediction and quality evaluation methods based on the results.

[0159] The evaluation unit optimizes the evaluation algorithm by referring to past evaluation data during the evaluation process. For example, the evaluation unit selects the optimal evaluation algorithm based on past successful evaluation data. The evaluation unit can also analyze past unsuccessful evaluation data and select an evaluation algorithm that reflects improvements. Furthermore, the evaluation unit can select the optimal evaluation algorithm according to the attributes of the buyer based on past evaluation data. In this way, the optimal evaluation algorithm can be selected by referring to past evaluation data. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input past evaluation data into AI, and the AI ​​can automatically select the optimal evaluation algorithm.

[0160] The evaluation unit applies different evaluation methods depending on the vehicle category during the evaluation process. For example, in the case of a sports car, the evaluation unit focuses on performance. In the case of a family car, the evaluation unit may also focus on safety. Furthermore, in the case of an eco-car, the evaluation unit may also focus on fuel efficiency. This allows for appropriate evaluation by applying evaluation methods according to the vehicle category. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input vehicle category information into the AI, and the AI ​​can automatically apply the evaluation method.

[0161] The evaluation unit estimates the buyer's emotions and adjusts the display method of the evaluation results based on the estimated emotions. For example, if the buyer is nervous, the evaluation unit provides a simple and highly visible display method. If the buyer is relaxed, the evaluation unit can also provide a display method that includes detailed information. Furthermore, if the buyer is in a hurry, the evaluation unit can provide a concise display method. This allows for the display of appropriate evaluation results by adjusting the display method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI or not using AI. For example, the evaluation unit can input buyer emotion data into a generative AI, which can automatically estimate the emotions and adjust the display method based on the results.

[0162] The evaluation unit considers the geographical distribution of vehicles during the evaluation process. For example, if a buyer lives in a specific region, the evaluation unit evaluates vehicles relevant to that region. Furthermore, if a buyer wishes to use a vehicle in a specific region, the evaluation unit can evaluate vehicles suitable for that region. In addition, the evaluation unit can evaluate the optimal vehicle based on the buyer's geographical location information. This allows for a more accurate evaluation by considering the geographical distribution of vehicles. Some or all of the above processes in the evaluation unit may be performed using AI, or not. For example, the evaluation unit can input geographical distribution information of vehicles into an AI, which can then automatically perform the evaluation.

[0163] The evaluation unit improves the accuracy of its evaluation by referring to relevant vehicle documentation during the evaluation process. For example, the evaluation unit may refer to the vehicle's technical specifications to improve the accuracy of its evaluation. It may also refer to past evaluation reports of the vehicle to improve the accuracy of its evaluation. Furthermore, the evaluation unit may refer to market price data of the vehicle to improve the accuracy of its evaluation. Thus, the accuracy of the evaluation is improved by referring to relevant vehicle documentation. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input relevant vehicle documentation information into AI, and the AI ​​can automatically improve the accuracy of the evaluation.

[0164] The interface unit estimates the buyer's emotions and adjusts the interface display method based on the estimated emotions. For example, if the buyer is tense, the interface unit provides an interface with calming colors to reduce visual stress. If the buyer is enjoying themselves, the interface unit provides an interface with bright colors to make the input process more enjoyable. Furthermore, if the buyer is tired, the interface unit provides a simple and highly visible interface to facilitate the input process. This allows for the display of an appropriate interface by adjusting the interface display method according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interface unit may be performed using AI, or not. For example, the interface unit can input buyer emotion data into a generative AI, which can automatically estimate the emotions and adjust the interface display method based on the result.

[0165] The interface unit selects the optimal display method when displaying the interface by referring to the buyer's past operation history. For example, the interface unit prioritizes displaying interface designs that the buyer has frequently used in the past. The interface unit can also predict specific operation patterns from the buyer's past operation history and suggest the optimal display method. Furthermore, the interface unit can select the most efficient interface display method based on the buyer's past operation history. In this way, the optimal interface display method can be selected by referring to past operation history. Some or all of the above processing in the interface unit may be performed using AI, for example, or without AI. For example, the interface unit can input past operation history data into AI, and the AI ​​can automatically select the optimal display method.

[0166] The interface unit estimates the buyer's emotions and adjusts the interface's operating procedures based on the estimated emotions. For example, if the buyer is nervous, the interface unit provides simple and easily understandable operating procedures. If the buyer is relaxed, the interface unit can also provide detailed operating procedures. Furthermore, if the buyer is in a hurry, the interface unit can provide concise operating procedures. This allows for appropriate interface operation by adjusting the operating procedures according to the buyer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interface unit may be performed using AI, or not using AI. For example, the interface unit can input buyer emotion data into a generative AI, which can automatically estimate the emotions and adjust the operating procedures based on the result.

[0167] The interface unit selects the optimal display method when displaying the interface, taking into account the purchaser's device information. For example, if the purchaser is using a smartphone, the interface unit provides a display method that matches the screen size. Furthermore, if the purchaser is using a tablet, the interface unit can provide a display method optimized for a larger screen. Additionally, if the purchaser is using a smartwatch, the interface unit can provide a concise and highly visible display method. This ensures that the appropriate interface is displayed by selecting a display method that takes device information into account. Some or all of the above processing in the interface unit may be performed using AI, or without AI. For example, the interface unit can input device information into the AI, which can then automatically select the optimal display method.

[0168] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0169] The proposal department can estimate the buyer's emotions and adjust the content of the proposal based on those emotions. For example, if the buyer is excited, the proposal department can make a visually appealing proposal. If the buyer is feeling anxious, the proposal department can provide detailed information and make a reassuring proposal. Furthermore, if the buyer is in a hurry, the proposal department can make a concise and to-the-point proposal. In this way, by adjusting the content of the proposal according to the buyer's emotions, it becomes possible to make appropriate proposals.

[0170] The analysis unit can estimate the buyer's emotions and adjust the display method of the analysis results based on those estimated emotions. For example, if the buyer is nervous, the analysis unit can provide a simple and highly visible display method. If the buyer is relaxed, it can provide a display method that includes detailed information. Furthermore, if the buyer is in a hurry, it can provide a display method that gets straight to the point. This allows for the provision of appropriate information by adjusting the display method of the analysis results according to the buyer's emotions.

[0171] The checking function can estimate the buyer's emotions and adjust the contract checking method based on those emotions. For example, if the buyer is nervous, the checking function can provide a simple and easy-to-understand checking method. If the buyer is relaxed, it can provide a checking method that includes detailed information. Furthermore, if the buyer is in a hurry, it can provide a checking method that gets straight to the point. This allows for proper checking by adjusting the contract checking method according to the buyer's emotions.

[0172] The Ministry of Education can estimate the buyer's emotions and adjust the educational content based on those estimates. For example, if the buyer is nervous, the Ministry of Education can provide simple and easy-to-understand educational content. If the buyer is relaxed, it can provide educational content that includes detailed information. Furthermore, if the buyer is in a hurry, it can provide educational content that gets straight to the point. In this way, appropriate education can be provided by adjusting the educational content according to the buyer's emotions.

[0173] The interface unit can estimate the buyer's emotions and adjust the interface display method based on those emotions. For example, if the buyer is stressed, it can provide an interface with calming colors to reduce visual stress. If the buyer is enjoying themselves, it can provide an interface with bright colors to make the input process more enjoyable. Furthermore, if the buyer is tired, it can provide a simple and highly visible interface to make the input process easier. In this way, by adjusting the interface display method according to the buyer's emotions, an appropriate interface display can be achieved.

[0174] The proposal department can analyze a buyer's past purchase history to make optimal recommendations. For example, it can suggest similar vehicles based on data from vehicles the buyer has previously purchased. It can also suggest related vehicles based on data from vehicles the buyer has shown interest in in the past. Furthermore, it can analyze the buyer's interest in specific brands or models from their past purchase history and make recommendations accordingly. This allows for optimal recommendations through the analysis of past purchase history.

[0175] The analysis department can evaluate the condition of a vehicle by referring to past transaction data. For example, it can predict the price and quality of a vehicle based on past transaction data. It can also analyze past transaction data to evaluate the repair and maintenance history of a specific vehicle. Furthermore, it can predict the market value of a specific vehicle based on past transaction data. This allows for an accurate assessment of the vehicle's condition by referring to past transaction data.

[0176] The checking function can apply different checking methods depending on the category of the contract. For example, in the case of a vehicle purchase contract, the check can focus on the vehicle's technical specifications. Similarly, in the case of an insurance contract, the check can focus on the insurance coverage. Furthermore, in the case of a loan contract, the check can focus on the repayment terms. This allows for appropriate checking by applying the appropriate checking method to the category of the contract.

[0177] The Ministry of Education can customize educational content by considering the attributes of purchasers. For example, it can provide educational content tailored to the purchaser's age and gender. It can also provide educational content tailored to the purchaser's occupation and income. Furthermore, it can provide educational content based on the purchaser's past purchase history. This allows for appropriate education by customizing educational content while considering the purchaser's attributes.

[0178] The interface unit can select the optimal display method considering the purchaser's device information. For example, if the purchaser is using a smartphone, it can provide a display method adapted to the screen size. If the purchaser is using a tablet, it can provide a display method optimized for the larger screen. Furthermore, if the purchaser is using a smartwatch, it can provide a concise and highly visible display method. This ensures that the appropriate interface is displayed by selecting a display method that takes device information into account.

[0179] The following briefly describes the processing flow for example form 2.

[0180] Step 1: The reception desk receives the buyer's preferences. These preferences include, for example, price, make, model, year, and mileage. The reception desk accepts the buyer's preferences entered in natural language, stores them in a database, and makes them available for later reference. Step 2: The proposal department makes proposals based on the requests received by the reception department. The proposal department recommends the most suitable vehicles from the used car database, compares multiple vehicles based on the buyer's preferences, and presents the best option. Step 3: The Negotiation Support Department provides real-time negotiation support based on the proposals submitted by the Proposal Department. The Negotiation Support Department can assist with price negotiations and review contracts. They assist in negotiations with the seller based on the price desired by the buyer. Step 4: The Optimization Department optimizes the entire purchase process based on the negotiation results conducted by the Negotiation Support Department. The Optimization Department streamlines each step of the purchase process and proposes the optimal purchase process based on the buyer's wishes. For example, it proposes the optimal purchase process based on the buyer's desired delivery date and payment method.

[0181] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0182] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0183] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0184] Each of the multiple elements described above, including the reception unit, proposal unit, negotiation support unit, optimization unit, analysis unit, checking unit, education unit, collection unit, understanding unit, evaluation unit, and interface unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives the buyer's wishes. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and recommends the most suitable vehicle based on the buyer's wishes. The negotiation support unit is implemented by, for example, the control unit 46A of the smart device 14 and supports price negotiation in real time. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and optimizes the entire purchase process. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs automatic analysis of historical data and repair history. The checking unit is implemented by, for example, the control unit 46A of the smart device 14 and checks the contract. The education unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides FAQs and risk education regarding purchases. The data collection unit is implemented, for example, by the control unit 46A of the smart device 14, and collects data from the used car information platform. The understanding unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and understands requests using natural language processing. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs price prediction and quality evaluation using machine learning. The interface unit is implemented, for example, by the control unit 46A of the smart device 14, and interacts with a dedicated application. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0185] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0186] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0187] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0188] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0189] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0191] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0192] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0193] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0194] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0195] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0196] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0197] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0198] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0199] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0200] Each of the multiple elements mentioned above, including the reception unit, proposal unit, negotiation support unit, optimization unit, analysis unit, checking unit, education unit, collection unit, understanding unit, evaluation unit, and interface unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives the buyer's wishes. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and recommends the most suitable vehicle based on the buyer's wishes. The negotiation support unit is implemented by, for example, the control unit 46A of the smart glasses 214 and supports price negotiation in real time. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and optimizes the entire purchase process. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs automatic analysis of historical data and repair history. The checking unit is implemented by, for example, the control unit 46A of the smart glasses 214 and checks the contract. The education unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides FAQs and risk education regarding purchases. The data collection unit is implemented, for example, by the control unit 46A of the smart glasses 214, and collects data from the used car information platform. The understanding unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and understands requests using natural language processing. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs price prediction and quality evaluation using machine learning. The interface unit is implemented, for example, by the control unit 46A of the smart glasses 214, and interacts with a dedicated application. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0201] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0202] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0203] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0204] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0205] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0206] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0207] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0208] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0209] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0210] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0211] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0212] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0213] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0214] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0215] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0216] Each of the multiple elements described above, including the reception unit, proposal unit, negotiation support unit, optimization unit, analysis unit, checking unit, education unit, collection unit, understanding unit, evaluation unit, and interface unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives the buyer's wishes. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and recommends the most suitable vehicle based on the buyer's wishes. The negotiation support unit is implemented by, for example, the control unit 46A of the headset terminal 314 and supports price negotiation in real time. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and optimizes the entire purchase process. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs automatic analysis of historical data and repair history. The checking unit is implemented by, for example, the control unit 46A of the headset terminal 314 and checks the contract. The education unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides FAQs and risk education regarding purchases. The data collection unit is implemented, for example, by the control unit 46A of the headset terminal 314, and collects data from the used car information platform. The understanding unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and understands requests using natural language processing. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs price prediction and quality evaluation using machine learning. The interface unit is implemented, for example, by the control unit 46A of the headset terminal 314, and interacts with a dedicated application. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0217] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0218] As shown in Figure 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.

[0219] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0220] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0221] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0223] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0224] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0225] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0227] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0228] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0229] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0230] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0231] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0232] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0233] Each of the multiple elements mentioned above, including the reception unit, proposal unit, negotiation support unit, optimization unit, analysis unit, checking unit, education unit, collection unit, understanding unit, evaluation unit, and interface unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives the buyer's wishes. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and recommends the most suitable vehicle based on the buyer's wishes. The negotiation support unit is implemented by, for example, the control unit 46A of the robot 414 and assists in real-time price negotiations. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and optimizes the entire purchase process. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs automatic analysis of historical data and repair history. The checking unit is implemented by, for example, the control unit 46A of the robot 414 and checks the contract. The education unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides FAQs and risk education regarding purchases. The data collection unit is implemented, for example, by the control unit 46A of the robot 414, and collects data from the used car information platform. The understanding unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and understands requests using natural language processing. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs price prediction and quality evaluation using machine learning. The interface unit is implemented, for example, by the control unit 46A of the robot 414, and coordinates with a dedicated application. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0234] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0235] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0236] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0237] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0238] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0239] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0240] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0241] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0242] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0243] 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.

[0244] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0245] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0246] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0247] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0248] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0249] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0250] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0251] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0252] (Note 1) A reception desk that takes orders from buyers, A proposal department that makes proposals based on requests received by the aforementioned reception department, A negotiation support department provides real-time negotiation support based on the content proposed by the aforementioned proposal department, The system includes an optimization unit that optimizes the entire purchasing process based on the negotiation results performed by the negotiation support unit. A system characterized by the following features. (Note 2) It is equipped with an analysis unit that performs automated analysis of historical data and repair history. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a checking department that provides support for price negotiations and checks contracts. The system described in Appendix 1, characterized by the features described herein. (Note 4) The department has an education section that provides FAQs and risk education regarding purchases. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a data collection unit that collects data via API connection from a used car information platform. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes an understanding unit that compresponds to requests using natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 7) It features an evaluation unit that uses machine learning to predict prices and assess quality. The system described in Appendix 1, characterized by the features described herein. (Note 8) It features an interface section for connecting with a dedicated app. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is The system estimates the buyer's emotions and adjusts the preferred order processing method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is We analyze the buyer's past request history and select the most suitable method of acceptance. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving a request, filtering will be performed based on the buyer's current living situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is The system estimates the buyer's emotions and determines the priority of requests to accept based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When receiving requests, we will prioritize requests that are highly relevant to the buyer, taking into account their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is When receiving a request, the system analyzes the buyer's social media activity and accepts relevant requests. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned proposal section is, We estimate the buyer's emotions and adjust the way the proposal is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, When making a proposal, adjust the level of detail based on the importance of the vehicle. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, When making a proposal, different proposal algorithms are applied depending on the vehicle category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, Estimate the emotions of the purchaser and adjust the length of the proposal based on the estimated emotions of the purchaser The system according to Appendix 1, characterized by the above. (Appendix 19) The proposal department At the time of proposal, determine the priority of the proposal based on the registration time of the vehicle The system according to Appendix 1, characterized by the above. (Appendix 20) The proposal department At the time of proposal, adjust the order of the proposal based on the relevance of the vehicle The system according to Appendix 1, characterized by the above. (Appendix 21) The negotiation support department Estimate the emotions of the purchaser and adjust the negotiation support method based on the estimated emotions of the purchaser The system according to Appendix 1, characterized by the above. (Appendix 22) The negotiation support department At the time of negotiation support, select the optimal negotiation support method by referring to past negotiation data The system according to Appendix 1, characterized by the above. (Appendix 23) The negotiation support department At the time of negotiation support, conduct negotiation support considering the attribute information of the purchaser The system according to Appendix 1, characterized by the above. (Appendix 24) The negotiation support department Estimate the emotions of the purchaser and determine the priority of negotiation support based on the estimated emotions of the purchaser The system according to Appendix 1, characterized by the above. (Appendix 25) The negotiation support department At the time of negotiation support, conduct negotiation support considering the geographical distribution of the vehicle The system according to Appendix 1, characterized by the above. (Appendix 26) The negotiation support department At the time of negotiation support, refer to the relevant literature of the vehicle to improve the accuracy of negotiation support The system described in Appendix 1, characterized by the features described herein. (Note 27) The optimization unit, We estimate the buyer's emotions and adjust the optimization method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The optimization unit, During optimization, the optimization algorithm is optimized by referring to past optimization data. The system described in Appendix 1, characterized by the features described herein. (Note 29) The optimization unit, During optimization, the buyer's attribute information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The optimization unit, It estimates the buyer's emotions and determines optimization priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The optimization unit, During optimization, the geographical distribution of vehicles is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 32) The optimization unit, During optimization, we improve the accuracy of the optimization by referring to relevant vehicle literature. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned analysis unit is We estimate the buyer's emotions and adjust the analysis methods for historical data and repair history based on the estimated buyer's emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned analysis unit is During analysis, the analysis algorithm is optimized by referring to historical data. The system described in Appendix 2, characterized by the features described herein. (Note 35) The analysis unit applies different analysis methods according to the category of the vehicle during analysis for the system according to Supplementary Note 2. (Supplementary Note 36) The analysis unit estimates the emotions of the purchaser and adjusts the display method of the analysis results based on the estimated emotions of the purchaser for the system according to Supplementary Note 2. (Supplementary Note 37) The analysis unit performs analysis considering the geographical distribution of the vehicles during analysis for the system according to Supplementary Note 2. (Supplementary Note 38) The analysis unit refers to relevant literature of the vehicle to improve the accuracy of analysis during analysis for the system according to Supplementary Note 2. [[ID=​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​During the review process, the geographical distribution of the contracts will be taken into consideration. The system described in Appendix 3, characterized by the features described herein. (Note 44) The aforementioned checking unit is During the review process, we refer to relevant documents in the contract to improve the accuracy of the review. The system described in Appendix 3, characterized by the features described herein. (Note 45) The aforementioned Ministry of Education, The system estimates the buyer's emotions and adjusts the educational content based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned Ministry of Education, During education, the educational algorithm is optimized by referring to past educational data. The system described in Appendix 4, characterized by the features described herein. (Note 47) The aforementioned Ministry of Education, During training, the content of the training will be customized by taking into account the attribute information of the purchasers. The system described in Appendix 4, characterized by the features described herein. (Note 48) The aforementioned Ministry of Education, Estimate the buyer's emotions and determine educational priorities based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 49) The aforementioned Ministry of Education, When providing training, the content should be tailored to the geographical distribution of vehicles. The system described in Appendix 4, characterized by the features described herein. (Note 50) The aforementioned Ministry of Education, During training, refer to relevant vehicle-related literature to improve the accuracy of the training. The system described in Appendix 4, characterized by the features described herein. (Note 51) The aforementioned collection unit is We estimate the buyer's emotions and adjust the data collection method based on the estimated buyer's emotions. The system described in Appendix 5, characterized by the features described herein. (Note 52) The aforementioned collection unit is During data collection, the collection algorithm is optimized by referring to past collected data. The system described in Appendix 5, characterized by the features described herein. (Note 53) The aforementioned collection unit is When collecting data, different collection methods are applied depending on the data category. The system described in Appendix 5, characterized by the features described herein. (Note 54) The aforementioned collection unit is We estimate the buyer's sentiment and adjust how the collected data is displayed based on that estimated sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 55) The aforementioned collection unit is When collecting data, consider its geographical distribution. The system described in Appendix 5, characterized by the features described herein. (Note 56) The aforementioned collection unit is During data collection, we refer to relevant literature to improve the accuracy of the collection. The system described in Appendix 5, characterized by the features described herein. (Note 57) The aforementioned understanding unit is, We estimate the buyer's emotions and adjust how we understand their needs based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 58) The aforementioned understanding unit is, During the understanding process, the understanding algorithm is optimized by referring to past request data. The system described in Appendix 6, characterized by the features described herein. (Note 59) The aforementioned understanding unit is, When understanding a request, different understanding methods are applied depending on the category of the request. The system described in Appendix 6, characterized by the features described herein. (Note 60) The aforementioned understanding unit is, It estimates the buyer's emotions and adjusts how the understanding results are displayed based on the estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 61) The aforementioned understanding unit is, When understanding the situation, take into account the geographical distribution of the requests. The system described in Appendix 6, characterized by the features described herein. (Note 62) The aforementioned understanding unit is, To improve the accuracy of understanding, refer to relevant literature related to the request. The system described in Appendix 6, characterized by the features described herein. (Note 63) The evaluation unit, We estimate buyer sentiment and adjust price forecasting and quality evaluation methods based on that estimated sentiment. The system described in Appendix 7, characterized by the features described herein. (Note 64) The evaluation unit, During the evaluation process, the evaluation algorithm is optimized by referring to past evaluation data. The system described in Appendix 7, characterized by the features described herein. (Note 65) The evaluation unit, During evaluation, different evaluation methods are applied depending on the vehicle category. The system described in Appendix 7, characterized by the features described herein. (Note 66) The evaluation unit, We estimate the buyer's sentiment and adjust how the evaluation results are displayed based on that estimated sentiment. The system described in Appendix 7, characterized by the features described herein. (Note 67) The evaluation unit, During the evaluation, the geographical distribution of the vehicles will be taken into consideration. The system described in Appendix 7, characterized by the features described herein. (Note 68) The evaluation unit, During evaluation, we improve the accuracy of the evaluation by referring to relevant vehicle literature. The system described in Appendix 7, characterized by the features described herein. (Note 69) The interface unit is It estimates the buyer's emotions and adjusts the interface display based on those estimated emotions. The system described in Appendix 8, characterized by the features described herein. (Note 70) The interface unit is When displaying the interface, the system selects the optimal display method by referring to the purchaser's past operation history. The system described in Appendix 8, characterized by the features described herein. (Note 71) The interface unit is It estimates the buyer's emotions and adjusts the interface's operation procedures based on those estimated emotions. The system described in Appendix 8, characterized by the features described herein. (Note 72) The interface unit is When displaying the interface, the optimal display method is selected considering the purchaser's device information. The system described in Appendix 8, characterized by the features described herein. [Explanation of Symbols]

[0253] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that takes orders from buyers, A proposal department that makes proposals based on requests received by the aforementioned reception department, A negotiation support department provides real-time negotiation support based on the content proposed by the aforementioned proposal department, The system includes an optimization unit that optimizes the entire purchasing process based on the negotiation results performed by the negotiation support unit. A system characterized by the following features.

2. It is equipped with an analysis unit that performs automated analysis of historical data and repair history. The system according to feature 1.

3. It includes a checking department that provides support for price negotiations and checks contracts. The system according to feature 1.

4. The department has an education section that provides FAQs and risk education regarding purchases. The system according to feature 1.

5. It includes a data collection unit that collects data via API connection from a used car information platform. The system according to feature 1.

6. It includes an understanding unit that compresponds to requests using natural language processing. The system according to feature 1.

7. It features an evaluation unit that uses machine learning to predict prices and assess quality. The system according to feature 1.

8. It features an interface section for connecting with a dedicated app. The system according to feature 1.

Images