KR102621283B1 - System for providing peer to peer based used car trading platform service - Google Patents

Abstract

A P2P-based used car trading platform service provision system is provided, and a seller terminal uploads a sale request by uploading vehicle information including the vehicle price, instant transaction price, vehicle history, and photos of the used vehicle to be sold, comparative estimates provided, vehicle price, and When vehicle information is uploaded from the buyer terminal and seller terminal, which sends a purchase request for a used car after searching vehicle information including the instant transaction price, a storage unit that maps and stores the seller terminal and vehicle information, used car and seller among vehicle information A blind unit that performs de-identification after extracting at least one unique identification code that can identify the user, a delivery unit that transmits the purchase request to the seller terminal when the buyer terminal uploads a purchase request to purchase a used car of the seller terminal, and the seller When approval for the sale and purchase of a used car is completed between the terminal and the buyer terminal, it includes a platform service providing server including a brokerage department that brokers a contract between the seller terminal and the buyer terminal.

Description

Ｐ２Ｐ based used car trading platform service provision system {SYSTEM FOR PROVIDING PEER TO PEER BASED USED CAR TRADING PLATFORM SERVICE}

The present invention relates to a P2P-based used car trading platform service provision system, and provides a platform that can provide services for performance guarantee and rights transfer when brokering transactions between sellers and buyers.

In a narrow sense, the used car market can be said to be a spatial concept in which automobile dealers purchase cars owned by consumers, go through a commercialization process, display them in a specific location, and sell them to visiting consumers. In a broader sense, it is With the development of the Internet and SNS, it can be said to be a concept that is expanding to the online market area that does not presuppose spatial occupation. New cars are sold through sales agents after car manufacturers go through a process of producing cars of the same quality, and the distribution process and laws are no different from those in the general industrial product industry. In the new car distribution market and the used car distribution market, brand recognition, manufacturer reliability, and consumer preference affect sales. The traditional meaning of a used car is a car that has already been used by someone else, and the central characteristic in the used car market is said to be quality assurance. Consumers are bound to be uncertain about the quality of cars that have already been used, and if there is no quality guarantee that will allow them to have confidence in the quality, they have no choice but to hesitate to purchase. As factors for forming consumer trust, perceived benefits, buyer's trust tendency, word-of-mouth effect, buyer's perceived size, and presentation of inspection and warranty policies have a positive impact.

At this time, a method of brokering the transaction of used cars was researched and developed. In relation to this, the prior art, Korean Patent Publication No. 2013-0116838 (published on October 24, 2013) and Korean Patent Publication No. 2022-0138217 (published on October 24, 2022) (released on October 12), when a request to rent a car is received from the buyer's terminal, it is sent to the seller's terminal to receive permission, the car rental fee is calculated using the model, year, rental period, and mileage of the rental vehicle, and the buyer's When the payment of the vehicle rental fee is completed, the vehicle rental is brokered, a used car sales request including a video diagnosis report for the used car is received from the seller terminal, the video diagnosis report is analyzed to calculate the used car sales price, and the used car sales price is calculated. A configuration is disclosed for registering the used car sales information included in the used car exchange and transferring the balance excluding the brokerage fee to the account of the seller terminal when a used car registered in the used car exchange is sold.

However, in the former case, since the vehicle is rented, there is no need for mediation regarding legal liability for performance guarantee and transfer of rights, and in the latter case, it is only a valuation structure that calculates the price by analyzing the video diagnosis report and does not provide a performance guarantee. However, it is not structured to carry out legal responsibility for the transfer of rights and provide services on the platform. Even if used cars have the same model, model year, options, and overall mileage, the purchase price is different depending on the owner's driving habits, car condition, accident status, transaction agreement terms, and transaction type. Consumer preferences for used car models also occur when selling. Because it is traded differently depending on the transaction volume, it is a market characteristic in which the price is adjusted on a one-product-one-price basis, making it difficult to establish a standard transaction format due to the unlimited number of trading entities and the diversity of transaction agreements. In order for e-commerce in the used car market to develop, institutional systems to gain consumer trust in the quality of used cars, such as quality assurance, quality certification, and compensation systems, must first be established in order to grow into a model that will lead used car trading. Accordingly, research and development of a platform that can assume legal responsibility for performance guarantees and rights transfer in used car transactions between individuals is required.

In one embodiment of the present invention, in order to eliminate opacity and uncertainty in the used car market, vehicle information is received from the seller's terminal, the performance status inspection record is verified and uploaded, and at least one document for vehicle transfer registration is uploaded and the document is submitted. Confirm and verify, and when a purchase request is received from the buyer's terminal, the sell request and purchase request are delivered on the platform without disclosing the contact information of the seller and buyer. When the negotiation between the seller and buyer is completed and a contract is made, the contract is signed. By providing documents as electronic documents, storing electronic documents for a preset period, and simultaneously providing the vehicle price and immediate transaction price set by the seller, the range of transaction options can be expanded to help quick decision-making and expand the range of choices. A P2P-based used car trading platform service provision system can be provided. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means to achieve the above-described technical tasks, a P2P-based used car trading platform service provision system is provided, and a sale request is uploaded by uploading vehicle information including vehicle price, instant transaction price, vehicle history, and photos of the used car to be sold. When uploading vehicle information from the seller's terminal, the buyer's terminal that sends a purchase request for a used car after searching vehicle information including the provided comparison quote, vehicle price, and instant transaction price, the seller's terminal and vehicle information are mapped. a storage unit that stores the vehicle information, a blind unit that performs de-identification after extracting at least one unique identification code that can identify the used car and the seller from the vehicle information, and when the buyer terminal uploads a purchase request to purchase the used car of the seller terminal, It includes a platform service providing server that includes a transmission unit that delivers a purchase request to the seller terminal and a brokerage unit that brokers a contract between the seller terminal and the buyer terminal when approval for the sale and purchase of a used car is completed between the seller terminal and the buyer terminal.

According to one of the means for solving the problem of the present invention described above, in order to eliminate opacity and uncertainty in the used car market, vehicle information is received from the seller's terminal, then the performance status inspection record is verified and uploaded, and at least one for vehicle transfer registration is provided. The documents are uploaded, the documents are checked and verified, and when a purchase request is received from the buyer's terminal, the sale request and purchase request are delivered on the platform without disclosing the seller's and buyer's contact information, and the negotiation between the seller and the buyer is completed. When signing a contract, contract documents are provided as electronic documents and the electronic documents are kept for a preset period. When a purchase request is received from the buyer for the vehicle price set by the seller, conditions favorable to the seller are compared through comparative estimates. It can help with quick decision making.

1 is a diagram illustrating a P2P-based used car trading platform service providing system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a platform service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which a P2P-based used car trading platform service is implemented according to an embodiment of the present invention.
Figure 5 is an operation flowchart illustrating a method of providing a P2P-based used car trading platform service according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as:

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

1 is a diagram illustrating a P2P-based used car trading platform service providing system according to an embodiment of the present invention. Referring to Figure 1, the P2P-based used car trading platform service provision system 1 includes at least one seller terminal 100, a platform service provision server 300, at least one buyer terminal 400, and at least one information provision. It may include a server 500. However, since the P2P-based used car trading platform service providing system 1 of FIG. 1 is only an embodiment of the present invention, the present invention is not limited to FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one seller terminal 100 may be connected to the platform service providing server 300 through the network 200. In addition, the platform service providing server 300 may be connected to at least one seller terminal 100, at least one buyer terminal 400, and at least one information providing server 500 through the network 200. Additionally, at least one buyer terminal 400 may be connected to the platform service providing server 300 through the network 200. In addition, at least one information providing server 500 may be connected to at least one seller terminal 100, a platform service providing server 300, and at least one buyer terminal 400 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one seller terminal 100 may be a terminal of a seller who wishes to sell a used car using a web page, app page, program, or application related to the P2P-based used car trading platform service.

Here, at least one seller terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one seller terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one seller terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The platform service providing server 300 may be a server that provides a P2P-based used car trading platform service web page, app page, program, or application. In addition, when receiving vehicle information from the seller terminal 100, the platform service providing server 300 verifies the vehicle information, maps it to the seller terminal 100, stores it, and uniquely identifies the used car and the seller among the vehicle information. It may be a server that detects and de-identifies identification information and then uploads it. In addition, the platform service providing server 300 may be a server that provides a comparison quote when the seller terminal 100 describes the vehicle price and at least one buyer terminal 400 presents a purchase price. In addition, when a purchase request is uploaded from the buyer terminal 400, the platform service providing server 300 transmits it to the seller terminal 100, and if there is agreement between both parties, prepares the contract document as an electronic document. It may be a server that receives signatures from the seller terminal 100 and the buyer terminal 400 and distributes and stores electronic documents.

Here, the platform service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one buyer terminal 400 may be a buyer terminal that uses a web page, app page, program, or application related to the P2P-based used car trading platform service. At this time, the buyer terminal 400 can simultaneously check the comparison quote provided by the platform service providing server 300 and the vehicle price and instant transaction price set by the seller terminal 100, so which option is selected among the three options? You can consider whether it is more advantageous for you, and by avoiding the paradox of choice, you can make quick decisions. At this time, the comparative quote may be the result of comparing prices for the same vehicle type and conditions. In addition, the immediate transaction price is the price set by the seller and may be the price at which the seller is willing to sell without further discussion or adjustment.

Here, at least one buyer terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one buyer terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one buyer terminal 400 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

At least one information providing server 500 may be a server that allows information inquiry of the platform service providing server 300 with or without using a web page, app page, program, or application related to the P2P-based used car trading platform service. . For example, the information provider of the information provision server 500 may be a server of each public institution such as the Ministry of Land, Infrastructure and Transport, Korea Transportation Safety Authority, the National Automobile Civil Service Portal, and Automobile 365, but is not limited to those listed and is not excluded for reasons not listed. . Here, at least one information providing server 500 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

Figure 2 is a block diagram for explaining the platform service providing server included in the system of Figure 1, and Figures 3 and 4 show an embodiment in which a P2P-based used car trading platform service is implemented according to an embodiment of the present invention. This is a drawing for explanation.

Referring to Figure 2, the platform service providing server 300 includes a storage unit 310, a blind unit 320, a delivery unit 330, a mediation unit 340, a performance status verification unit 350, and a confirmation unit ( 360), medical storage department (370), transfer registration department (380), agency preparation department (390), settlement department (391), information department (393), consignment department (395), and history inquiry department (397). Includes.

The platform service providing server 300 or another server (not shown) operating in conjunction with an embodiment of the present invention provides at least one seller terminal 100, at least one buyer terminal 400, and at least one information. When transmitting a P2P-based used car trading platform service application, program, app page, web page, etc. to the server 500, at least one seller terminal 100, at least one buyer terminal 400, and at least one information providing server (500) can install or open a P2P-based used car trading platform service application, program, app page, web page, etc. Additionally, the service program may be run on at least one seller terminal 100, at least one buyer terminal 400, and at least one information provision server 500 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, when the seller terminal 100 uploads vehicle information, the storage unit 310 may map and store the seller terminal 100 and vehicle information. The seller terminal 100 may upload a sale request by uploading vehicle information including the vehicle price, vehicle history, and photos of the used car to be sold. At this time, if it is difficult to set the vehicle price, the used car price provided by at least one information provision server 500 can be provided as a guideline. However, the information provided by at least one information provision server 500, that is, a public institution, is premised on the same model, year, options, and mileage. As described above, used cars have the same model, year, options, and mileage. Even so, the purchase price is traded differently depending on the owner's driving habits, condition of the car, presence of an accident, transaction agreement terms, and transaction type, and at the time of sale, it is traded differently depending on the transaction volume of consumer preferences for used car models, so one product, one price. It is a characteristic of a market in which prices are adjusted by price, which makes it difficult to establish a standard transaction format due to the unlimited number of trading entities and the diversity of transaction agreements. Accordingly, in one embodiment of the present invention, it is possible to further provide guidelines for price based on options, accident status, insurance history, current status, etc.

<Residual value prediction>

Since it may initially take time to collect data from the platform of the present invention, a dataset for learning and verifying the artificial intelligence algorithm can be imported and used from outside. In addition, data preprocessing is performed to generate learning data for use in residual value prediction, and in the process, attributes with low correlation to used car prices can be filtered out. Since car options affect the price of used cars, parsing strings for N representative options (leather seats, heated seats, sunroof, parking sensors, rear camera, blind spot monitoring system, adaptive cruise control, etc.) So, it can be encoded in numeric form. Through the above process, the purified learning data is stored in the database.

In addition, machine learning algorithms (random forest, multi-layer perceptron, support vector machine, XGBoost, etc.) are trained to predict used car prices. To improve the accuracy of each machine learning algorithm, hyperparameter optimization can be performed and ensemble methods can be applied to the machine learning algorithm results. And, in order to predict the future value of a used car, the vehicle properties at a future point in time can be estimated. At this time, vehicle attributes that need to be estimated in the future are operation year and mileage. The operation period can be added as much as the forecast period, such as 1 year, 2 years, or 3 years from the current point, and can be divided according to the expected sales time. Driving distance can be estimated by reflecting the average driving distance to date, reflecting the period until the future point. Accordingly, the future residual value derived from estimates of the operation period and mileage that change over time can be predicted and the suitability of each model can be analyzed based on the depreciation rate. It is also possible to predict the current and future value of used cars according to driving habits by analyzing and extracting driving habits to maximize the residual value of owned vehicles by reflecting OBD-based vehicle driving records.

<Depreciation factor>

The price evaluation elements of used cars are divided into basic information research, basic market price evaluation, accident history evaluation, vehicle condition evaluation, and special factor evaluation. The basic market price is evaluated by correcting the registration date, equipment, and mileage from the average price of market information, and the assessed price is derived by correcting accident information, vehicle condition, and special factors from the basic market price. The average market price is the price that serves as the standard for calculating automobile prices and is the average transaction price calculated through market price research. The average price is calculated by researching and calculating according to vehicle type, grade, and model year, and the basic price is evaluated by correcting price fluctuation factors such as the cumulative mileage of each individual vehicle, additional options, and registration date from the average price. Cumulative mileage correction can be evaluated when the average mileage is exceeded. Considering the depreciation characteristics of each vehicle type, depreciation is calculated at a rate of 03% for every 1,000 km for general passenger cars and 05% for every 1,000 km for large passenger cars and imported cars. Correction on the registration date is evaluated considering the average market price fluctuation for the relevant model year and the number of months of correction based on the registration date, and additional options installed on the vehicle are evaluated taking into account installation cost, quality status, and depreciation according to the period of use. The number of corrected months refers to the number of months that are below or exceeded compared to the standard number of months for the model year.

Depreciation evaluation based on accident history is evaluated by considering the average market price of the vehicle and the depreciation rate according to damage and repair status. Based on the results of a survey on the transaction status of the accident car, the depreciation due to the accident history can be limited to not exceed 30% of the average market price. The average depreciation rate classified according to the extent of damage and repair can be applied based on market research results. The depreciation rate application table is applied separately to the front, side center, and rear of the vehicle, and the highest depreciation rate item is applied to the same accident area. If there are two or more accident areas, a proportional evaluation is applied so that the composite reduction rate does not exceed a maximum of 30%.

Vehicle condition is broadly evaluated by dividing each item into 4 grades (good, average, inadequate, poor) for each item such as appearance (exterior), interior/interior, main device performance, wheels/tires, and basic equipment. The rating is calculated by assigning a basic score to each item based on the vehicle condition rating and multiplying the basic score by a weight. The overall rating is the sum of the scores for each evaluation item. Next is the special factor evaluation, where a special depreciation rate is applied to flooded vehicles, fire vehicles, total loss vehicles, vehicles with structural changes, and vehicles with a history of change in purpose or owner. The depreciation rate for each special factor is calculated taking into account market transaction characteristics. The price can be determined by conducting a comprehensive evaluation that adjusts accident information, vehicle condition, and special factors from the basic market price of each individual vehicle. Of course, in addition to estimating the residual value using the above-described method, it can help the seller set the price by providing guidelines for the price of a used car in various ways.

The blind unit 320 may perform de-identification after extracting at least one unique identification code that can identify the used car and the seller from the vehicle information. For example, among vehicle information, information such as license plate number, seller's name, contact information, and address can be removed by blurring, mosaicing, or completely deleting. In addition, when the performance status inspection record is uploaded, information that can identify the used car or the seller from the performance status inspection record, for example, the automobile registration number in item ② of Figure 4a and the vehicle identification number in item ⑥ are removed and After detecting, identifying, and extracting items and information that can identify an individual, such as the vehicle identification number of the vehicle history information of Car 365, blur processing, mosaic processing, or deletion processing can be performed. At this time, if the vehicle information is provided in a scanned PDF, etc., each item in the PDF is identified using OCR (Optical Character Recognition), and an item identifier corresponding to the unique identification information among each item, for example, It can detect, identify and blur names, social security numbers, addresses, phone numbers, vehicle identification numbers, car registration numbers, etc. As shown in Figures 4a to 4d, the format of the performance status inspection record is set as [Appendix Form No. 82] in accordance with the Enforcement Rules of the Automobile Management Act. Accordingly, when the number, location, and content of each item are stored, the location, or area, of the information to be searched by OCR has already been secured, so extracting it is relatively simple. In addition, since the site format provided by Car 365 for vehicle history has already been determined, you can relatively easily find the location containing personal information by specifying a search term for each location, coordinates, or item. The problem at this time is a document whose format is not set. In this case, entity name recognition can be performed according to an artificial intelligence algorithm as follows.

<Entity name recognition>

Text in the standard format provided by the above-mentioned countries is recognized by OCR, but not all text recognized by OCR is personal information or unique identification information, and although the location is specified, it is not scanned properly or is not scanned properly or is not a photo. In this case, the location may vary depending on the shooting angle, and if it is not a standard format, the location or area for each item is not even known, so only the text corresponding to the unique identification information must be selected after recognizing the entity name using an artificial intelligence algorithm. At this time, if the document formats are all different and the terms used are different for each company, collecting and constructing this as big data and then mapping it according to standard codes may need to be done first. You can hire a labeler, or you can use data mapped by each employee. For example, it may have a format such as [standard code]-[term], but is not limited to this. Once the data set is constructed in this way, the [terms] read by OCR are entered as a query into the artificial intelligence algorithm, the artificial intelligence algorithm is learned and verified to output a [standard code], and then the algorithm with the highest accuracy is selected as the work of the present invention. It can be set using an algorithm according to the embodiment. After this process is completed, only the items necessary for customs declaration are extracted through [OCR]-[AI], and each unique identification information is de-identified (anonymized, pseudonymized) because it is output as a standard code regardless of the differences in terms. , ready for mosaic processing or blur processing.

<Deep learning object detection>

Object detection is a deep learning technology widely used in computer vision, and is a technology that both locates objects in images or videos (object localization) and classifies objects. Representative deep learning object detection algorithms include R-CNN, Fast R-CNN, and YOLO. Among them, YOLO (You Only Look Once) utilizes the entire feature information of the image to detect the bounding box of the object in the image in a single neural network. It is a one-stage detector that outputs the class probability of the box and object at once, and the neural network configuration is simpler than the two-stage detector. However, since both object detection and class must be detected in a single step, the accuracy is lower than that of the two-step detector. Therefore, in order to de-identify, for example, mosaic or delete a license plate displaying a used car's license plate number, accurate detection is more important than quick detection, so a two-stage detector is used to increase accuracy.

<License plate detection>

Since most photos provided by sellers are not taken by professionals, they may go through the processes of license plate detection, direction normalization, character segmentation, and character recognition. This is because not all license plates in photos are horizontal to the ground, and depending on the camera angle, the license plate may be photographed trapezoidal or inverted trapezoidal. In the case of license plate detection, license plates in a specified image are detected and then classified by type. The input is a color or grayscale image, which can have different lighting conditions and different backgrounds. To this end, Mask R-CNN, a deep learning algorithm of the CNN (Convolutional Neural Network) series, can be used to reduce environmental dependence and increase accuracy. The Mask R-CNN algorithm is a successor to the R-CNN family of R-CNN, Fast R-CNN, and Faster R-CNN. It is the most recently developed object detection and instance segmentation framework and has the highest learning accuracy compared to previous algorithms. high. Mask R-CNN is a structure in which a small FCN (Fully Connected Network) mask branch that predicts a segmentation mask is added to each RoI (Region of Interest) obtained from Faster R-CNN. The backbone structure of the Mask R-CNN model used for license plate detection may be ResNet.

<Direction normalization>

After detecting a car license plate in an image, a process is added to normalize the direction of the license plate in the detected area. In the case of tilted license plates, there is a possibility of errors occurring when classifying characters, so character segmentation and character recognition can be performed in the license plate area where the direction is normalized. To apply direction normalization, the Perspective Transformation image processing technique can be used. Perspective Transformation is a transformation that gives a sense of perspective by making the same object appear smaller depending on the perspective, but objects that are far away appear small and objects that are close appear large. After detecting a license plate through the license plate detection module, if you know the coordinates of each vertex of the license plate, you can normalize the direction by converting the coordinates through a transformation matrix. If the vertex at the top left of the license plate is (x1,y1), the vertex at the bottom left is (x2,y2), the vertex at the top right is (y3,y3), and the vertex at the bottom right is (x4,y4), the transformation matrix is The following is the same as Equation 1. At this time, matrices a, b, c, d, e, f, g, and h are further included on the right side of the right hand side of this transformation matrix, but they were not included due to space constraints. If you arbitrarily set the coordinate values after transformation of this transformation matrix, you can obtain the inverse matrix of the 8×8 matrix and know the values of eight variables: a, b, c, d, e, f, g, and h.

<Character Splitting>

The Mask R-CNN model can be used for character segmentation. In this module, the Mask R-CNN model first detects each letter and number and then calculates the location coordinates. Next, we use a simple sorting algorithm and take into account the license plate type to sort the letters and numbers in the order they appear on the license plate. Some Korean license plates have one line of letters and numbers, like the personal version, and some have two lines of letters and numbers, like the American-sized business version. The backbone structure of this model can also use ResNet and be trained on a dataset containing 300 images of license plates of various types.

<Text recognition>

For character recognition, letters and numbers in character segmentation are identified. In this module, you can also use Mask R-CNN and ResNet as the backbone structure. The CNN model used can be trained with images of 10 numbers (0-9) and 46 Korean characters. Of course, various methods other than the above-described methods can be used, and when uploading, check whether the vehicle number of the license plate extracted in this way, the vehicle number provided by the seller terminal 100, or the vehicle number collected from various public institutions are correct. The area containing the vehicle number can be deleted.

When the buyer terminal 400 uploads a purchase request to purchase a used car of the seller terminal 100, the transmission unit 330 may transmit the purchase request to the seller terminal 100. The buyer terminal 400 may search vehicle information and then transmit a purchase request for a used car. At this time, the delivery unit 330 may provide a comparative quote in response to the buyer's purchase request. The buyer who submitted the purchase request at the highest price will be selected, but if the buyer is a dealer, he or she may attempt to reduce the price. Accordingly, when listing buyers who have made purchase requests, prices can be sorted based on individuals rather than dealers. At this time, the method to check whether a dealer is a dealer is as follows. Businesses wishing to sell used cars must register with the competent Special Self-Governing City Mayor, Special Self-Governing Province Governor, Mayor, County Governor, or District Head (Main Text of Article 53 (1) of the Automobile Management Act), and employees in the used car sales business must indicate their identity. Therefore, it is possible to check whether the employee selling the car is an employee of an officially registered company (Article 59, Paragraph 2, Item 3 of the Automobile Management Act). If an employee selling used cars does not indicate his/her identity, the registration of the car sales business will be canceled or all or part of the business will be suspended for up to 6 months (Article 66 (1) 12 of the Automobile Management Act) Item H) You can check whether you are a dealer or not.

The brokerage unit 340 may broker a contract between the seller terminal 100 and the buyer terminal 400 when approval for the sale and purchase of a used car is completed between the seller terminal 100 and the buyer terminal 400. If the buyer terminal 400 has an intention to purchase, if the [YES] button is pressed, a purchase request is simultaneously transmitted to the seller terminal 100 and the buyer terminal 400, and the seller terminal 100 expresses its intention to accept this, e.g. For example, if you press the [YES] button, the contract can proceed with the agreement of both parties. At this time, as shown in Figure 4p, the contract can use the attached list of automobile registration rules, Ministry of Land, Infrastructure and Transport Ordinance No. 1161 [Form 15] Automobile Transfer Certificate (for direct transactions between the transferor and transferee), and this contract is an electronic contract that contains public certificates, financial certificates, etc. After verifying the identity verification method, it can be written and stored as an electronic signature.

The performance status verification unit 350 extracts and stores the text for each item in the used car performance status inspection record among the vehicle information, verifies whether the preset expiration date of the performance status inspection record has expired, and verifies whether the performance status inspection record has expired. Verify whether a signature or seal exists on the signature and seal item, check the contact information for the performance status inspector who created the performance status inspection record, and if the warranty type in the performance status inspection record is not subscribed, the entity responsible for inspecting the performance status is. and warranty type can be requested from the seller terminal (100). At this time, the preset validity period is stipulated as 120 days (Article 58 (1) No. 1 of the Automobile Management Act, Article 120 (1) of the Enforcement Rules of the Automobile Management Act and Form No. 82 attached). Accordingly, although it is based on 120, it may be changed if laws, ordinances, and rules change.

If the preset validity period has expired, the confirmation unit 360 requests the seller terminal 100 to reissue the performance status inspection record, and records the authenticity of the signature and seal in the signature and seal item of the performance status inspection record. It is verified by comparing it with the performance status checker's signature and seal in the constructed signature and seal database, and a call can be made to the contact information for the performance status checker to check whether it is the performance status checker's contact information. At this time, if the signature or seal of the company that created the performance status inspection record cannot be confirmed, confirmation of the signature or seal can be requested through the business terminal at the branch, and verification can be performed based on this.

The mandatory storage unit 370 may store the performance status inspection record for one year from the date of sale when the contract between the seller terminal 100 and the buyer terminal 400 is completed and the transfer of the used car is completed. At this time, the medical storage department 370 may need to record, manage, and preserve the contents of the performance status inspection record, and register it on the automobile complaint management business portal website (https://biz.ecar.go.kr). (Article 58, Paragraphs 9 and 10 of the Automobile Management Act and Article 116, Paragraph 1, Item 1 of the Enforcement Rules of the Automobile Management Act). The information at this time may include the basic information of the car, overall condition of the car, history of accidents, exchanges, repairs, etc., detailed condition of the car, contents of research and calculation of the car price (limited to cases where the buyer wishes to research and calculate the price), etc. However, it is not limited to this. In addition, in the case of an electronic or offline contract, various documents such as contracts can be stored. At this time, a method of determining the degree of similarity of documents can be further used to confirm the originality of the document for the contract. For example, Locality Sensitive Hashing (LSH) can be used. In general, similarity is a measure that can be used to distinguish between [similar] or [not similar] with the naked eye. At this time, the judgment of [similar] and [not similar] is a subjective indicator that may vary from person to person. If you use subjective indicators like these to determine whether a contract is original, the results are bound to be subjective. However, because the above-mentioned LSH is programmed, implemented, and processed through already mathematically established calculation formulas, it can be free from the misunderstanding or stigma of subjective similarity. LSH is one of the algorithms for comparing similarity and is used in fields such as data mining, pattern recognition, computer vision, computational geometry, and data compression. It is also used for spell checking, plagiarism detection, and measuring chemical similarity.

<Shingling>

The shingling step refers to converting a document into a collection of words. This is the same process as representing each document as a number in the vector similarity model. One document is divided according to the number of tokens, which are defined as letters, words, or other units, and is expressed as a series of words (characters). In order to compress the document expressed in this way, the string of the document is hashed into a set number of bytes, and the result of this entire hashing is expressed as a document. When hashing is done on a word or character basis in this way, intuitively similar documents will have the same hashing results in common when viewed as an entire document.

<Min-Hashing>

The Min-Hashing step is a step that goes through the MinHash algorithm. This step is the process of converting a large document set (Shingles-processed document) into a short signature while maintaining document similarity. In the shingles process, the document is expressed as a set of shingles, and this set is expressed like a matrix (column, row) and converted to a new signature array using permutation π. The definition of MinHash used at this time is as follows. It is the same as equation 2.

In the above formula, for permutation π, the value of the first column represents the number of the first (order of permutation) row. By applying this to all columns, several randomly selected permutations π are applied to create a signature for each column. The result is expressed as a matrix, and for permutation π, the columns are expressed as Sets and the rows are expressed as MinHash values. The signatrue created in this way has a fixed value regardless of the size of the original document, allowing similarity comparison with documents of different sizes.

<LSH>

The whole idea of Locality Sensitive Hashing (LSH) starts from the hash string for the matrix generated during the MinHash process. Even after going through the MinHash process, you can see that the hash column appears as many times as the number of documents. LSH is a concept that roughly calculates only rows with similar hash results and places them in the same bucket to compare for equality in order to avoid comparing all documents. Assuming that it is defined as a band consisting of each column of the matrix M, each band calculates a part of each column as a hash table with buckets. Bands that reach the same area become document pairs with a probability of similarity, and since only document pairs with this probability are compared, the similarity between large amounts of electronic information can be compared by reducing the number of comparisons of all documents. Of course, in addition to the hashing method described above, a method of converting the contract into a preset number of texts by hashing the contract itself can also be used. In this case, even if one letter is incorrect, the hash value is completely different, so it can be useful for verifying the original or authenticity.

When the used car contract between the seller terminal 100 and the buyer terminal 400 is completed, the transfer registration agency 380 can perform vehicle transfer registration for transferring rights to the used car. When the seller and buyer of the seller terminal 100 and the buyer terminal 400 request agency for vehicle transfer registration, the agency preparation unit 390 receives a seal certificate for sale, a transfer certificate, and a power of attorney from the seller terminal 100. , a seal certificate, transfer certificate, power of attorney, and insurance subscription certificate can be received from the buyer terminal 400.

The settlement unit 391 completes payment for the vehicle price of the used car at the buyer terminal 400, uploads the car registration certificate and seal certificate for sale for the used car at the seller terminal 100, and If the buyer completes vehicle transfer registration using the insurance subscription certificate and vehicle transfer registration application, the remainder of the vehicle price minus the preset commission can be paid to the seller terminal 100.

If a claim regarding the performance status inspection record is received at the buyer terminal 400, the information department 393 may guide the buyer terminal 400 to file a complaint with the traffic administration department or automobile management team within the district office.

The consignment unit 395 provides a private option for processing the contact information of the seller terminal 100 and the contact information of the buyer terminal 400 as private, and requests for sale and purchase between the seller terminal 100 and the buyer terminal 400. If it exists, the expression of intention can be transmitted from the platform service providing server to the seller terminal 100 and the buyer terminal 400.

When the history inquiry unit 397 wants to check the vehicle history on the buyer terminal 400, after obtaining the consent of the seller terminal 100, the history inquiry unit 397 provides basic information about the used car, inspection history information, seizure registration information, and mortgage registration information. , vehicle history including automobile tax arrears information, mandatory insurance subscription information, maintenance history information, and performance status inspection record can be searched and transmitted to the buyer terminal 400. As shown in Figures 4e to 4o, when searching through sites such as Automobile 365 and Automobile Public Portal, my data can be collected and searched with the consent of the seller terminal 100, and the results can be provided to the buyer terminal 400. You can.

Hereinafter, the operation process according to the configuration of the platform service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to Figure 3, (a) the platform service providing server 300 collects and stores used car vehicle information from the seller terminal 100, and as in (b), the authenticity of the performance status inspection record is checked by the issuer who issued it. Verification can be performed by confirming with the (business branch) and comparing it with the information received from the various information provision servers 500, and as in (c), the used car can be identified among the information provided by the seller terminal 100 or the seller. You can upload after removing all information that can identify you. The platform service providing server 300 can provide comparative quotes when there are multiple buyers, as shown in (d), and can mediate sales as shown in (a) of FIG. 4. In addition, when transferring rights, the required documents can be received from the seller's terminal (100) and the buyer's terminal (400), and then the rights can be transferred on behalf of the parties or brokered between the parties. If the contract is not conducted through an electronic contract, various documents can be submitted. Save it in the database to prevent disputes or quarrels that may arise in the future. In addition, as in (c), it can help sellers and buyers make decisions about selling and buying by predicting the price of used cars, and as in (d), a deep learning object detection model is used when detecting and blurring objects in a photo. can be used. 4A to 4P are diagrams showing legal forms or information provided by each public institution as described above, so duplicate descriptions will be omitted.

Matters that are not explained about the method of providing the P2P-based used car trading platform service in Figures 2 to 4 are the same as or can be easily explained from the content explained about the method of providing the P2P-based used car trading platform service through Figure 1. Since inference is possible, the description below will be omitted.

FIG. 5 is a diagram illustrating a process in which data is transmitted and received between each component included in the P2P-based used car trading platform service provision system of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to Figure 5, when vehicle information is uploaded from the seller's terminal, the platform service providing server maps and stores the seller's terminal and vehicle information (S5100).

Then, the platform service providing server extracts at least one unique identification code that can identify the used car and the seller from the vehicle information, performs de-identification (S5200), and uploads a purchase request to purchase the used car of the seller's terminal from the buyer's terminal. In this case, a purchase request is transmitted to the seller's terminal (S5300). In addition, the platform service providing server brokers a contract between the seller terminal and the buyer terminal when approval for the sale and purchase of a used car is completed between the seller terminal and the buyer terminal (S5400).

The sequence between the above-described steps (S5100 to S5400) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5400) may change, and some of the steps may be executed simultaneously or deleted.

Matters that are not explained about the method of providing the P2P-based used car trading platform service in Figure 5 are the same as or can be easily explained from the content explained about the method of providing the P2P-based used car trading platform service through Figures 1 to 4. Since inference is possible, the description below will be omitted.

The method of providing a P2P-based used car trading platform service according to an embodiment described in Figure 5 can also be implemented in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. there is. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing a P2P-based used car trading platform service according to an embodiment of the present invention described above is executed by an application installed by default on the terminal (this may include programs included in the platform or operating system, etc., installed by default on the terminal). It may be executed by an application (i.e., a program) that the user installs directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing a P2P-based used car trading platform service according to an embodiment of the present invention described above is implemented as an application (i.e., a program) installed by default in the terminal or directly installed by the user and readable by a computer such as in the terminal. It can be recorded on any recording medium that can be recorded.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (10)

A seller terminal that uploads a sale request by uploading vehicle information including the vehicle price, instant transaction price, vehicle history, and photos of the used car to be sold;
A buyer terminal that sends a purchase request for the used car after checking the vehicle information including the provided comparison quote, vehicle price, and instant transaction price; and
When uploading the vehicle information from the seller's terminal, a storage unit that maps and stores the seller's terminal and vehicle information extracts at least one unique identification code that can identify the used car and the seller from the vehicle information and then de-identifies it. A blind unit that performs, when the buyer terminal uploads a purchase request to purchase a used car of the seller terminal, a transmission unit that transmits the purchase request to the seller terminal, selling and buying the used car between the seller terminal and the buyer terminal. When approval is completed, a platform service providing server including a brokerage unit that brokers a contract between the seller terminal and the buyer terminal; includes,
The platform service providing server is,
Provides price guidelines to the seller's terminal based on the options, accident status, insurance history, and current condition of the used car to be sold,
We manage car options including leather seats, heated seats, sunroof, parking sensors, rearview camera, blind spot monitoring system, and adaptive cruise control with learning data to be used in residual value prediction, and to predict the future value of used cars. Estimating vehicle properties at a future point in time, including a driving period equivalent to a preset prediction point in time from the present point in time, and a driving distance reflecting the average mileage to date and the period up to a preset future point in time, and estimating the vehicle properties at the estimated future point in time. We predict future residual value based on vehicle properties and analyze suitability based on depreciation rate.
The transmission unit,
A comparative quote is provided in response to the purchase request from the buyer's terminal, and in order to prevent attempts to reduce the price if the buyer is a dealer, when listing the buyer who made the purchase request, the buyer who made the purchase request is a registered company that intends to sell the car. A P2P-based used car trading platform service provision system that checks whether the buyer is a dealer by checking whether the buyer is an employee of and sorts prices based on individuals other than dealers.
According to claim 1,
The platform service providing server is,
Extract and store the text for each item in the used car performance status inspection record among the vehicle information, verify whether the preset expiration date of the performance status inspection record has expired, and sign and seal the signature and seal item in the performance status inspection record. Or, verify whether a seal exists, check the contact information for the performance status inspector who created the performance status inspection record, and if the warranty type of the performance status inspection record is not subscribed, determine the entity responsible for inspecting the performance status and the warranty type. A performance status verification unit making a request to the seller's terminal;
A P2P-based used car trading platform service provision system further comprising:
According to claim 2,
The platform service providing server is,
When the preset expiration date has expired, a reissue of the performance status inspection record is requested through the seller's terminal, and the authenticity of the signature and seal or seal on the signature and seal items of the performance status inspection record is checked through a previously established signature and seal database. a confirmation unit that verifies the performance status checker's signature and seal by comparing it with the performance status checker's contact information within the performance status checker, and sends a call to the contact information for the performance status checker to confirm whether the contact information is the performance status checker;
A P2P-based used car trading platform service provision system further comprising:
According to claim 2,
The platform service providing server is,
a mandatory storage unit that stores the performance status inspection record for one year from the date of sale when the contract between the seller terminal and the buyer terminal is completed and the transfer of the used car is completed;
A P2P-based used car trading platform service provision system further comprising:
According to claim 1,
The platform service providing server is,
When the used car contract between the seller's terminal and the buyer's terminal is completed, a transfer registration agency that performs vehicle transfer registration for transferring rights to the used car;
A P2P-based used car trading platform service provision system further comprising:
According to claim 5,
The platform service providing server is,
When the seller and buyer of the seller terminal and the buyer terminal request agency for vehicle transfer registration, a seal certificate, transfer certificate, and power of attorney for sale are received from the seller terminal, and a seal certificate, transfer certificate, power of attorney, and insurance are received from the buyer terminal. Agency preparation department that receives the certificate of membership;
A P2P-based used car trading platform service provision system further comprising:
According to claim 1,
The platform service providing server is,
Payment for the vehicle price of the used car is completed at the buyer terminal, the car registration certificate and seal certificate for sale for the used car are uploaded at the seller terminal, and the buyer of the buyer terminal submits an insurance subscription certificate and a car transfer registration application form. a settlement unit that pays the remainder of the vehicle price minus a preset commission to the seller's terminal when the vehicle transfer registration is completed using;
A P2P-based used car trading platform service provision system further comprising:
According to claim 2,
The platform service providing server is,
When a claim regarding the performance status inspection record is received from the buyer terminal, an information unit that guides the buyer terminal to file a complaint with the traffic administration department or automobile management team within the district office having jurisdiction over the buyer;
A P2P-based used car trading platform service provision system further comprising:
According to claim 1,
The platform service providing server is,
A private option is provided to make the contact information of the seller terminal and the contact information of the buyer terminal private, and when there is a sell request and a purchase request between the seller terminal and the buyer terminal, the platform service providing server provides the seller terminal and the buyer terminal. A consignment unit that delivers expressions of intent through a terminal;
A P2P-based used car trading platform service provision system further comprising:
According to claim 1,
The platform service providing server is,
If you want to check the vehicle history on the buyer's terminal, after obtaining the consent of the seller's terminal, basic information about the used car, inspection history information, seizure registration information, mortgage registration information, automobile tax delinquency information, and mandatory insurance subscription information , a history inquiry unit that searches vehicle history including maintenance history information and performance status inspection record and transmits it to the buyer terminal;
A P2P-based used car trading platform service provision system further comprising:

Images