KR102184836B1 - Method and system for controlling direct trading platform of used car - Google Patents

Abstract

The present invention relates to a method for controlling a direct trading platform for a used car to promote an interindividual used car trading market. According to one embodiment of the present invention, the method comprises the following steps of: when receiving a used car sale request from a seller terminal, acquiring trading information for each car of a used car requested for sale from a public auction database and calculating an expected sale period expected in accordance with a requested sale price based on the trading information; crawling data related to the car of the used car requested for sale through an external network to acquire new model launching information, car defect information, and car recall information from the crawled data and calculating an expected sale price expected in accordance with a requested sale period based on the new model launching information, the car defect information, and the car recall information; when it is confirmed that the expected sale period is longer than the requested sale period and the expected sale price is higher than the requested sale price based on the expected sale period and price, calculating the requested sale price as a recommended sale price; and providing price information about the recommended sale price to the seller terminal.

Description

Used car direct trading platform control method and system {METHOD AND SYSTEM FOR CONTROLLING DIRECT TRADING PLATFORM OF USED CAR}

The following embodiments relate to a technology for controlling a used car direct trading platform.

In recent years, as interest in used car trading increases, the market is also expanding, but various problems arise in trading used cars.

First, due to the imbalance of information between consumers and used car companies, there is an overwhelming imbalance of information on the market price, status, and finance of the vehicle. Due to the inconvenience of the used car transaction process, individuals can provide vehicle guidance, contract, It is inconvenient to process registration, transfer, payment, consignment, and commercialization.

In addition, in the case of vehicles displayed in used car complexes, there is a problem that there is uncertainty about the condition of used cars as it is not possible to test drive, and there is a problem in that there is a structure that disadvantages to buyers as the margin of the used car increases.

Accordingly, the demand to trade used cars between individuals is increasing, but there is no platform for sellers and buyers to contact, so it is difficult for people who want to sell used cars or those who want to buy used cars to know information about used cars. to be.

Accordingly, there is a situation in which the demand for a service for a used car direct trading platform is increasing by solving the above problems.

Korean Patent Application Publication No. 10-2017-0092798 (2017.08.14.)

The present invention is to solve the above-described problems of the prior art, and when a request to sell a used car is received from a seller terminal, transaction information for each vehicle of the used car requested for sale is obtained from a public auction database, and the sale request price is calculated based on the transaction information. The estimated sales period is calculated accordingly, and the data related to the vehicle of the used car requested for sale is crawled through an external network, and new car release information, vehicle defect information and vehicle recall information are obtained from the crawled data, and new car release information, Based on the vehicle defect information and vehicle recall information, the estimated sales price is calculated according to the sales request period, and based on the expected sales period and the estimated sales price, the estimated sales period is longer than the sales request period and the estimated sales price is sold. If it is confirmed that it is higher than the requested price, the sales request price is calculated as the recommended sales price, and its purpose is to provide price information on the recommended sales price to the seller terminal.

The object of the present invention is not limited to the above-mentioned object, and other objects that are not mentioned will be clearly understood from the following description.

According to an embodiment of the present invention, in a method of controlling a platform for direct trading of used cars in a service providing server, when a request to sell a used car is received from a seller terminal, transaction information for each vehicle of the used car requested for sale is obtained from a public auction database. And calculating a predicted sales period predicted according to the sales request price based on the transaction information; By crawling data related to the vehicle of the used car requested for sale through an external network, new vehicle release information, vehicle defect information, and vehicle recall information are obtained from the crawled data, and the new vehicle release information, the vehicle defect information, and the vehicle recall Calculating a predicted sales price predicted according to the sales request period based on the information; Based on the expected sales period and the expected sales price, when the expected sales period is longer than the sales request period and the expected sales price is determined to be higher than the sales request price, the sales request price is calculated as a recommended sales price. Step to do; And providing price information on the recommended selling price to the seller terminal. A method of controlling a used car direct trading platform is provided.

The calculating of the recommended selling price may include: checking the number of sales of the same class of the used car requested for sale as used cars, and setting a first weight so that a lower value is applied as the number of sales increases; Checking the number of sales completions in which vehicles of the same class of the used car requested to be sold are traded as used cars for a predetermined period, and setting a second weight so that a higher value is applied as the number of sales completions increases; Checking the number of times of inquiries of pages registered to sell vehicles of the same class of the used cars requested for sale as used cars, and setting a third weight so that a higher value is applied as the number of inquiries increases; Checking the number of repairs in which vehicles of the same vehicle type as the used vehicle requested for sale are repaired due to a failure, and setting a fourth weight so that a lower value is applied as the number of repairs increases; And adjusting the recommended selling price by applying the first weight, the second weight, the third weight, and the fourth weight.

The used car direct trading platform control method, when a purchase request for the used car requested for sale is received from a purchaser terminal, checks the current market price and sales popularity according to the vehicle type, vehicle grade, and year of the used car requested to be purchased, and the recommended sale price Determining whether it is suitable for purchase; If it is determined that the recommended selling price is suitable for purchase, checking the mileage, repair details, and accident details of the used car requested to be purchased, and calculating a guaranteed amount required for post management of the used car; Determining a final purchase price for the used car requested to be purchased by adding the guaranteed amount to the recommended selling price; And providing price information on the final purchase price to the purchaser terminal.

The method of controlling the used car direct trading platform includes: receiving a request for confirming a matching score for the used car requested to be purchased from the purchaser terminal, and obtaining a log record of a user account logged in to the purchaser terminal; A first feature of the search vehicle type of the purchaser, based on the extracted search word and the number of searches, to check the search history of the purchaser through the log record, extract the search word and the number of searches related to the vehicle from the search history Analyzing the information; Check the SNS activity details of the buyer through the log record, and collect image and tag information of the posts in which the buyer performed any one of inquiry, registration, comment, and recommendation from the SNS activity details, and the collection Extracting image and tag information related to the vehicle from the image and tag information, and analyzing second feature information on the vehicle type of interest of the purchaser based on the extracted image and tag information; Generating preferred vehicle information of the purchaser based on the first characteristic information and the second characteristic information; And calculating a matching score by comparing the preferred vehicle information with vehicle information of the used car requested to be purchased, and providing the calculated matching score to the purchaser terminal.

The used car direct trading platform control method includes receiving image information photographing the used car requested for sale from the seller terminal in various directions, and extracting all image information of the used car requested for sale through rendering of the received image information. And checking a target area image and vehicle state information from the entire image information, and generating a determination result as to whether repair of the used car requested for sale is required based on the vehicle state information; And classifying a vehicle that can be traded by classifying the state of the used car requested for sale according to the determination result, wherein the generating the determination result includes color information and texture information in the target area image. Thus, identifying a valid vehicle boundary; Extracting appearance features of particle objects in an effective vehicle area separated by the identified effective vehicle boundary; Identifying at least one foreign material object among the particle objects based on the extracted appearance features, and removing the foreign material object from the effective vehicle area; Extracting size features of particle objects in the effective vehicle area from which the foreign object object has been removed; Classifying the particle objects into one of a vehicle body object and a glass object, respectively, based on the size characteristics; Generating a first ratio in the effective vehicle area of at least one particle object classified as the vehicle body object; Generating a second ratio in the effective vehicle area of at least one particle object classified as the glass object; Generating a third ratio of the foreign object in the effective vehicle area; Generating vehicle color information based on a color characteristic of the effective vehicle area from which the foreign object object has been removed; Generating basic vehicle information based on the first ratio, the second ratio, the third ratio, and the vehicle color information; Generating auxiliary vehicle information by inquiring about vehicle type information of a used vehicle and background information of a photographing area for the target area image; Generating a feature vector corresponding to the effective vehicle area based on the basic vehicle information and the auxiliary vehicle information; Obtaining output information by applying the feature vector to a pre-trained neural network; And generating vehicle state information corresponding to the valid vehicle area based on the output information.

According to an embodiment of the present invention, based on the expected sales period and the expected sales price, if it is determined that the expected sales period is longer than the sales request period and the expected sales price is higher than the sales request price, the sales request price is the recommended sales price. By calculating as, there is an effect of revitalizing the used car trading market between individuals by providing appropriate information on the sale price of used cars.

On the other hand, the effects according to the embodiments are not limited to those mentioned above, and other effects that are not mentioned will be clearly understood by those of ordinary skill in the art from the following description.

1 is a diagram schematically showing the configuration of a system for controlling a direct trading platform of a used car according to an embodiment of the present invention.
2 is a flowchart illustrating a process of providing information on recommended selling prices of used cars according to an embodiment of the present invention.
3 is a flowchart illustrating a process of determining a final purchase price of a used car according to an embodiment of the present invention.
4 is a flowchart illustrating a process of calculating a matching score between a used car and a buyer according to an embodiment of the present invention.
5 is a view for explaining a method of processing an image of a used car to determine whether a used car needs repair according to an embodiment of the present invention.
6 is a view for explaining a learning method employed to process an image photographed of a used car in order to determine whether a used car needs repair according to an embodiment of the present invention.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the rights of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes to the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be changed in various forms and implemented. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical idea.

Although terms such as first or second may be used to describe various components, these terms should be interpreted only for the purpose of distinguishing one component from other components. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

When a component is referred to as being "connected" to another component, it is to be understood that it may be directly connected or connected to the other component, but other components may exist in the middle.

The terms used in the examples are used for illustrative purposes only and should not be interpreted as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present specification, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this application. Does not.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of the reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, when it is determined that a detailed description of related known technologies may unnecessarily obscure the subject matter of the embodiments, the detailed description thereof will be omitted.

1 is a diagram schematically showing the configuration of a system for controlling a direct trading platform of a used car according to an embodiment of the present invention.

Referring to FIG. 1, a system according to an embodiment of the present invention may include a plurality of seller terminals 100, a plurality of buyer terminals 200, and a service providing server 300 capable of communicating with each other through a communication network.

First, the communication network may be configured regardless of its communication mode, such as wired or wireless, and may be implemented in various forms so that communication between a server and a server and communication between a server and a terminal are performed.

Each of the plurality of seller terminals 100 and each of the plurality of buyer terminals 200 may be implemented as a computing device having a communication function, for example, a mobile phone, a desktop PC, a laptop PC, a tablet PC, a smartphone, etc. It may be implemented, but is not limited thereto, and may be implemented as various types of communication devices that can be connected to an external server.

The plurality of seller terminals 100 are terminals used by sellers who want to sell used cars, and include a first seller terminal 110 used by a first seller, a second seller terminal 120 used by a second seller, etc. The plurality of purchaser terminals 200 are terminals used by buyers who want to purchase a used car, and the first purchaser terminal 210 used by the first purchaser and the second purchaser terminal 220 used by the second purchaser ), etc.

Hereinafter, for convenience of explanation, the operation of the first seller terminal 110 and the first buyer terminal 210 will be mainly described, but the operation of the first seller terminal 110 in other seller terminals such as the second seller terminal 120 It goes without saying that the operation of the first purchaser terminal 210 can be performed in another purchaser terminal such as the second purchaser terminal 220.

Each of the plurality of seller terminals 100 and each of the plurality of purchaser terminals 200 may access the service providing server 300 through a web page or an application provided by the service providing server 300.

The service providing server 300 may provide a platform for direct trading of used cars, and may provide various services so that direct transactions are made between the plurality of seller terminals 100 and the plurality of purchaser terminals 200.

2 is a flowchart illustrating a process of providing information on recommended selling prices of used cars according to an embodiment of the present invention.

First, in step S201, the service providing server 300 may receive a request for selling a used car from the first seller terminal 110. At this time, the used car sales request may include sales request price information, sales request period information, and the like. For example, the sales request period may be set to two months later, and the sales request price may be set to 15 million won.

In step S202, the service providing server 300 may obtain the vehicle-specific transaction information of the used vehicle requested for sale from the public auction database according to the used vehicle sale request, and the prediction predicted according to the sale request price based on the vehicle-specific transaction information You can estimate the sales period.

That is, the service providing server 300 may check the wholesale and retail price of the used car through the public auction database, and calculate the expected sales period according to the sale request price of the used car. For example, if the sales request price is 10 million won If the sales period is calculated as one month and the sales request price is 15 million won, the expected sales period is calculated as three months, and the expected sales period may be calculated differently depending on the sales request price even for vehicles of the same vehicle type.

In step S203, the service providing server 300 may crawl data related to the vehicle of the used car requested for sale through an external network according to the used car sale request, and new car release information, vehicle defect information, and vehicle recall from the crawled data. The information may be obtained, and a predicted sales price predicted according to the sales request period may be calculated based on the new vehicle release information, vehicle defect information, and vehicle recall information.

That is, the service providing server 300 may calculate the estimated selling price by adjusting the current market price of used cars according to the market changing according to the new car release, vehicle defect, vehicle recall, etc. For example, a new car release plan after 2 months If it is confirmed that there is a sales request period after one month, the estimated sales price is calculated as 15 million won, and if the sales request period is three months later, the estimated sales price is calculated as KRW 10 million. The estimated selling price may be calculated differently.

In step S204, the service providing server 300, based on the expected sales period and the expected sales price, if the expected sales period is longer than the sales request period and the expected sales price is determined to be higher than the sales request price, recommends the sales request price It can be calculated at the selling price.

For example, the service providing server 300 may receive a sale request for a used car in which the sale request period is set after two months from the first seller terminal 110 and the sale request price is set to 20 million won, and the sale request price is In the case of 20 million won, the estimated sales period is calculated as 3 months, and if the sales request period is 2 months later, the estimated sales price can be calculated as 25 million KRW, and the estimated sales period is 3 months, longer than the sales request period of 2 months, and the estimated sales Since the price is 25 million won, which is higher than the sale request price of 20 million won, it is determined that the sale request price of 20 million won is appropriate, and 20 million won can be calculated as the recommended selling price.

In step S205, the service providing server 300 may provide price information on the recommended selling price to the first seller terminal 110.

According to an embodiment, the service providing server 300 may check the number of sales of the same class of used cars requested for sale as used cars, and may set the first weight so that a lower value is applied as the number of sales increases.

The service providing server 300 may check the number of sales completions in which vehicles of the same class of the used car requested for sale are traded as used cars for a predetermined period, and set the second weight so that a higher value is applied as the number of sales completions increases.

The service providing server 300 may check the number of times of inquiries of pages registered to sell vehicles of the same class of used cars requested for sale as used cars, and set the third weight so that a higher value is applied as the number of inquiries increases.

The service providing server 300 may check the number of repairs in which vehicles of the same vehicle type as the used car requested for sale are repaired due to failure, and may set the fourth weight so that a lower value is applied as the number of repairs increases.

The service providing server 300 may adjust the recommended selling price by applying the first weight, the second weight, the third weight, and the fourth weight.

3 is a flowchart illustrating a process of determining a final purchase price of a used car according to an embodiment of the present invention.

First, in step S301, the service providing server 300 may receive a purchase request for a used car requested for sale from the first purchaser terminal 210.

In step S302, the service providing server 300 checks the current market price and sales popularity according to the vehicle type, vehicle grade, and year of the used car requested to be purchased, and determines whether the recommended selling price set for the used car requested to be purchased is suitable for purchase. I can judge.

If it is determined in step S302 that the recommended selling price is suitable for purchase, in step S303, the service providing server 300 checks the mileage, repair details, and accident details of the used car requested to be purchased, and the amount of guarantee required for post management of the used car Can be calculated.

In step S304, the service providing server 300 determines a final purchase price for the used car requested to be purchased by adding a guaranteed amount to the recommended sale price, and transfers price information on the final purchase price to the first purchaser terminal 210 Can provide.

If it is determined in step S302 that the recommended selling price is not suitable for purchase, in step S305, the service providing server 300 may provide other used car information of the used car and the same class vehicle requested to be purchased, and then return to step S301. A used car purchase request may be received again.

4 is a flowchart illustrating a process of calculating a matching score between a used car and a buyer according to an embodiment of the present invention.

First, in step S401, the service providing server 300 may receive a request for checking the matching score for the used car requested to be purchased from the first purchaser terminal 210, and the user account logged in to the first purchaser terminal 210 You can get log records.

In step S402, the service providing server 300 may check the search history of the first purchaser through log records, and in step 404, extract the search word and the number of searches related to the vehicle from the search history, and the extracted search word and the number of searches Based on, first characteristic information on the search vehicle type of the first purchaser may be analyzed.

For example, the service providing server 300 checks search terms such as vehicle type, year, brand, etc. and the number of times each search term is searched through the search history of the first purchaser, and the first purchaser searches for a vehicle of any type. It is possible to analyze the first characteristic information indicating whether or not.

In step S403, the service providing server 300 can check the SNS activity details of the first purchaser through log recording, and in step S405, the first purchaser in the SNS activity details of any one of inquiry, registration, comment, and recommendation Collect image and tag information of posts on which the activity was performed, extract image and tag information related to the vehicle from the collected image and tag information, and based on the extracted image and tag information, the vehicle type of interest of the first buyer The second characteristic information for the can be analyzed.

For example, the service providing server 300 checks whether a post related to a type of vehicle has been inquired, registered, commented, and recommended through the SNS activity details of the first purchaser. Second characteristic information indicating whether the vehicle is of interest may be analyzed.

In step S406, the service providing server 300 may generate preferred vehicle information of the first purchaser based on the first feature information and the second feature information.

That is, the service providing server 300 may determine what type of vehicle the first purchaser has searched for and what type of vehicle is interested in, and determine which vehicle the first purchaser prefers.

In step S407, the service providing server 300 may calculate a matching score by comparing the preferred vehicle information with the vehicle information of the used car requested to be purchased, and may provide the calculated matching score to the first purchaser terminal 210. .

5 is a view for explaining a method of processing an image of a used car to determine whether a used car needs repair according to an embodiment of the present invention.

According to an embodiment, the service providing server 300 may receive image information photographed from various directions of a used car requested for sale from the first seller terminal 110, and render image information photographed from various directions. By performing a task, it is possible to extract all image information of the used car requested for sale through rendering, check the target area image and vehicle status information from the extracted total image information of the used car, and request sales based on the vehicle status information It is possible to generate a determination result as to whether or not repair of the used car is required, and according to the determination result, the condition of the used car requested for sale may be classified, and the vehicles that can be traded may be classified.

Specifically, the service providing server 300 may analyze an image of a target area of a used car, extract vehicle status information included in the target area, and manage the extracted information as a database. The service providing server 300 may obtain a target area image 501 by determining a target area of the used car.

According to an embodiment, the service providing server 300 may identify an effective vehicle boundary based on color information and texture information in the target area image 501. The service providing server 300 may determine whether the vehicle is a vehicle for each area based on a color and a texture. The service providing server 300 may determine whether a vehicle is in each area by sliding a filter of a predefined unit, and the filter may be designed to output a result according to a color and a texture.

According to an embodiment, the service providing server 300 may extract an effective vehicle area 502 separated by an effective vehicle boundary within the target area image 501. The service providing server 300 may extract appearance features of particle objects in the effective vehicle area 502.

According to an embodiment, the service providing server 300 identifies the foreign object object 503 among particle objects, and removes the foreign object object 503 from the effective vehicle area 502 based on the extracted appearance characteristics. I can. The service providing server 300 identifies an object outside a predefined range based on the appearance, color, and texture information of the vehicle body and glass distributed in the effective vehicle area 502, and converts the identified object to a foreign object object 503. I can judge.

According to an embodiment, the service providing server 300 may extract size features 505 to 507 of particle objects in the effective vehicle area 504 from which the foreign object object has been removed. The service providing server 300 may identify particle objects in the effective vehicle area 504 and extract size features 505 to 507 for each size of information describing the identified particle objects. The service providing server 300 may extract and classify the size features 505 to 507 by size according to a range used as a reference for classifying a vehicle body and glass.

According to an embodiment, the service providing server 300 may classify the particle objects into one of a vehicle body object and a glass object, respectively, based on the extracted size features 505 to 507. The service providing server 300 may generate a first ratio in the effective vehicle area 504 of at least one particle object classified as a vehicle body object. The first ratio may correspond to the ratio of the vehicle body in the effective vehicle area 504. The service providing server 300 may generate vehicle state information in which the characteristics of the vehicle body are reflected by using the first ratio.

According to an embodiment, the service providing server 300 may generate a second ratio in the effective vehicle area 504 of at least one particle object classified as a glass object. The second ratio may correspond to the ratio of the glass in the effective vehicle area 504. The service providing server 300 may generate vehicle state information reflecting the characteristics of the glass using the second ratio.

According to an embodiment, the service providing server 300 may generate a third ratio in the effective vehicle area 502 of the foreign object 503. The third ratio may mean a ratio occupied by foreign substances in the effective vehicle area 502.

According to an embodiment, the service providing server 300 may extract color features in the effective vehicle area 504. The service providing server 300 may generate car color information based on color characteristics.

According to an embodiment, the service providing server 300 may generate basic vehicle information based on the first ratio, the second ratio, the third ratio, and the vehicle color information. The service providing server 300 may generate basic vehicle information based on the first ratio, the second ratio, the third ratio and vehicle color information according to image processing of the effective vehicle area 504.

According to an embodiment, the service providing server 300 may identify the target area image 501 based on the location, and store vehicle type information of the used car and environment information of the shooting area for the identified target area image 501. By inquiring, auxiliary vehicle information can be generated.

The service providing server 300 may generate a feature vector 510 corresponding to the effective vehicle area 502 based on the basic vehicle information and the auxiliary vehicle information. The service providing server 300 may obtain the output information 512 by applying the feature vector 510 to the pre-learned neural network 511.

The neural network 511 learns to estimate vehicle state information from the input according to the basic vehicle information generated based on the features extracted from the vehicle image, the type of used car, and the auxiliary vehicle information that affects the environmental state of the shooting area. Can be.

The service providing server 300 may generate vehicle state information corresponding to the effective vehicle area 502 based on the output information 512.

The output information 512 may be information including a matching degree for each scratch of the vehicle, or may be designed as variables that describe the repair state of the vehicle. In addition, the output information 512 may be discretely designed according to the classification of the vehicle. For example, the output nodes of the output layer of the neural network 511 correspond to each vehicle type, and the output nodes are each vehicle type. Probability values can be output for each classification. Hereinafter, learning contents of the neural network 511 will be described with reference to FIG. 7.

6 is a view for explaining a learning method employed to process an image photographed of a used car in order to determine whether a used car needs repair according to an embodiment of the present invention.

According to an embodiment, the learning apparatus may train a neural network 604 for estimating information required to acquire vehicle state information from an image of a target area. The learning device may be a separate subject different from the service providing server 300, but is not limited thereto.

According to an embodiment, the learning device may acquire labeled vehicle images 601. The learning apparatus may obtain pre-labeled information on each vehicle image for each vehicle type, and the vehicle image may be labeled according to the pre-classified vehicle type.

According to an embodiment, the learning device is based on at least one of color information, texture information, and appearance characteristics of the particle objects, and size characteristics of the labeled vehicle images 601, a first ratio corresponding to the vehicle body object, and a glass. The basic vehicle information 602 may be generated based on the second ratio corresponding to the object, the third ratio corresponding to the foreign object, and vehicle color information. The learning device may generate used vehicle feature vectors 603 based on the basic vehicle information 602. In generating the used vehicle feature vectors 603, auxiliary vehicle information may be employed.

According to an embodiment, the learning apparatus may obtain the output information 605 by applying the used vehicle feature vectors 603 to the neural network 604. The learning device may train the neural network 604 based on the output information 605 and the labels 606. The learning apparatus may train the neural network 604 by calculating errors corresponding to the output information 605 and optimizing a connection relationship between nodes in the neural network 604 in order to minimize the errors. The service providing server 300 may acquire vehicle status information from the target area image using the neural network 604 on which the learning has been completed.

The embodiments described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices, methods, and components described in the embodiments include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, such as one or more general purpose computers or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of the program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to behave as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

As described above, although the embodiments have been described by the limited drawings, a person of ordinary skill in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order from the described method, and/or components such as a system, structure, device, circuit, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Therefore, other implementations, other embodiments and claims and equivalents fall within the scope of the following claims.

100: multiple seller terminals
110: first seller terminal
120: second seller terminal
200: multiple purchaser terminals
210: first purchaser terminal
220: second purchaser terminal
300: service providing server

Claims (3)

In the method of controlling the direct trading platform of used cars in the service providing server,
When a request to sell a used car is received from a seller terminal, acquiring transaction information for each vehicle of the used car requested for sale from a public auction database, and calculating a predicted sales period predicted according to the sale request price based on the transaction information;
By crawling data related to the vehicle of the used car requested for sale through an external network, new vehicle release information, vehicle defect information, and vehicle recall information are obtained from the crawled data, and the new vehicle release information, the vehicle defect information, and the vehicle recall Calculating a predicted sales price predicted according to the sales request period based on the information;
Based on the expected sales period and the expected sales price, when the expected sales period is longer than the sales request period and the expected sales price is determined to be higher than the sales request price, the sales request price is calculated as a recommended sales price. Step to do;
Providing price information on the recommended selling price to the seller terminal;
When the purchase request for the used car requested for sale is received from the purchaser terminal, the current market price and sales popularity are checked according to the vehicle type, vehicle grade, and year of the used car requested to be purchased, and it is determined whether the recommended selling price is suitable for purchase. Step to do;
If it is determined that the recommended selling price is suitable for purchase, checking the mileage, repair details, and accident details of the used car requested to be purchased, and calculating a guaranteed amount required for post management of the used car;
Determining a final purchase price for the used car requested to be purchased by adding the guaranteed amount to the recommended selling price;
Providing price information on the final purchase price to the purchaser terminal;
Receiving a request for checking a matching score for the used car requested to be purchased from the purchaser terminal, and obtaining a log record of a user account logged in to the purchaser terminal;
A first feature of the search vehicle type of the purchaser, based on the extracted search word and the number of searches, to check the search history of the purchaser through the log record, extract the search word and the number of searches related to the vehicle from the search history Analyzing the information;
Check the SNS activity details of the buyer through the log record, and collect image and tag information of the posts in which the buyer performed any one of inquiry, registration, comment, and recommendation from the SNS activity details, and the collection Extracting image and tag information related to the vehicle from the image and tag information, and analyzing second feature information on the vehicle type of interest of the purchaser based on the extracted image and tag information;
Generating preferred vehicle information of the purchaser based on the first characteristic information and the second characteristic information; And
Computing a matching score by comparing the preferred vehicle information and vehicle information of the used car requested to be purchased, and providing the calculated matching score to the purchaser terminal,
Used car direct trading platform control method. The method of claim 1,
The step of calculating the recommended selling price,
Checking the number of sales of the same class of used cars that are requested to be sold as used cars, and setting a first weight so that a lower value is applied as the number of sales increases;
Checking the number of sales completions in which vehicles of the same class of the used car requested to be sold are traded as used cars during a preset period, and setting a second weight to apply a higher value as the number of sales completions increases;
Checking the number of times of inquiries of pages registered to sell vehicles of the same class of the used cars requested for sale as used cars, and setting a third weight so that a higher value is applied as the number of inquiries increases;
Checking the number of repairs in which vehicles of the same vehicle type as the used vehicle requested for sale are repaired due to a failure, and setting a fourth weight so that a lower value is applied as the number of repairs increases; And
And adjusting the recommended selling price by applying the first weight, the second weight, the third weight, and the fourth weight,
Used car direct trading platform control method. delete

Images