Method and apparatus for authenticating second-hand luxury goods

Abstract

The present invention relates to a method and a device for authenticating second-hand luxury goods, the device comprising: a memory for storing one or more instructions; and one or more processors which execute the stored one or more instructions so as to collect component values of metal decorations provided in a plurality of genuine second-hand luxury goods of a specific model, and which authenticate, on the basis of the collected component values, second-hand luxury goods of the same model as the plurality of genuine second-hand luxury goods.

Description

Appraisal method and device for used luxury goods

[0001] The present invention relates to an appraisal system, and more particularly, to a method and device for appraising used luxury goods.

[0002] The secondhand luxury goods market is a secondary market born from the expansion of the luxury goods market. It emerged as a result of the rise of conspicuous consumption of luxury goods, but also as consumers struggle to meet these demands. Recently, a growing number of consumers are pursuing rational consumption over price, opting instead for secondhand luxury goods shops rather than department stores or duty-free shops. Leading online platforms in the secondhand luxury goods market are either promoting free-market principles for C2C transactions, allowing them to conduct transactions independently, or employing their own appraisers and experts to assign condition grades and determine the prices of luxury goods.

[0003] At this time, a platform for selling used luxury goods was researched and developed. In relation to this, prior art Korean Patent Publication No. 2021-0120248 (published on October 7, 2021) and Korean Patent Publication No. 2019-0129366 (published on November 20, 2019) disclose a configuration in which, when receiving a used luxury goods consignment from the owner of the used luxury goods and renting or selling the used luxury goods, an operating deposit is paid to the owner, and the renter can rent or purchase the registered used luxury goods for a fee, and a configuration in which used luxury goods information and transaction types are registered and stored, VR content is created by editing a photographed image of the used luxury goods in VR, and information is provided by appraising the used luxury goods with VR content.

[0004] However, the former configuration is only a configuration that mediates the use loan and sale, and even in the latter case, appraising VR content rather than the actual item means that there will be a gap in the appraised grade equal to the gap between the actual item and the VR content, making it difficult to expect accurate appraisal results. When appraising used luxury goods on a second-hand transaction platform, it would be best to see the actual item and appraise it, but due to COVID-19, people are reluctant to make face-to-face contact, and there are people who simply want to know how much their used luxury goods can receive online, but there is no platform that can satisfy this.

[0005] [Prior Art Literature]

[0006] [Patent Document]

[0007] (Patent Document 1) Domestic Publication Patent No. 10-2021-0120248

[0008] (Patent Document 2) Domestic Publication Patent No. 10-2019-0129366

[0009] This specification was devised to solve the above-mentioned problems, and its purpose is to provide a method and device for appraising used luxury goods that can increase the accuracy of appraisal of used goods without relying solely on the appraisals of appraisers.

[0010] In order to achieve the above purpose, according to an embodiment of the present specification, a used luxury goods appraisal device according to the present specification includes a memory storing one or more instructions; and one or more processors executing the one or more stored instructions to collect component values ​​of metal decorations provided on a plurality of genuine used luxury goods of a specific model, and appraise the used luxury goods of the same model as the plurality of genuine used luxury goods based on the collected component values.

[0011] Preferably, the one or more processors collect correct answer data including component values ​​of metal decorations of the plurality of genuine used luxury goods, repeatedly input the collected correct answer data into an artificial intelligence model to train the artificial intelligence model, and then collect input data including component values ​​of metal decorations of the used luxury goods, input the collected input data into the trained artificial intelligence model, and compare an error value between the input data and output data of the trained artificial intelligence model, thereby outputting a first appraisal result of the used luxury goods.

[0012] Preferably, the one or more processors are characterized in that they receive appraisal data of the used luxury goods from at least one appraiser, collate the input appraisal data to output a second appraisal result of the used luxury goods, and compare the first appraisal result and the second appraisal result to finally appraise the used luxury goods.

[0013] Preferably, the one or more processors are characterized in that they evaluate the degree of damage to the metal decoration provided on the bottom surface of the used luxury product and determine the grade of the used luxury product based on the degree of damage.

[0014] Preferably, the one or more processors are characterized in that they evaluate a first degree of damage to a metal decoration provided on a bottom surface of the used luxury product and a second degree of damage to a metal decoration provided on a non-bottom surface of the used luxury product, and compare the first degree of damage and the second degree of damage to determine a grade of the used luxury product.

[0015] According to another embodiment of the present specification, a method for appraising used luxury goods according to the present specification includes the steps of: collecting, by one or more processors, component values ​​of metal decorations provided on a plurality of genuine used luxury goods of a specific model; and appraising, by the one or more processors, a used luxury goods of the same model as the plurality of genuine used luxury goods based on the collected component values.

[0016] Preferably, the step of appraising the used luxury goods comprises: a step in which the one or more processors collect correct answer data including component values ​​of metal decorations of the plurality of genuine used luxury goods, repeatedly input the collected correct answer data into an artificial intelligence model to train the artificial intelligence model; and a step in which the one or more processors collect input data including component values ​​of metal decorations of the used luxury goods, input the collected input data into a trained artificial intelligence model, and compare an error value between the input data and output data of the trained artificial intelligence model to output a first appraisal result of the used luxury goods.

[0017] Preferably, the step of appraising the used luxury goods is characterized by including a step in which the one or more processors input appraisal data of the used luxury goods from at least one appraiser, collate the input appraisal data, and output a second appraisal result of the used luxury goods; and a step in which the one or more processors compare the first appraisal result and the second appraisal result to finally appraise the used luxury goods.

[0018] As described above, according to the present specification, a method and device for appraising used luxury goods are provided, which collect the component values ​​of metal decorations provided on a plurality of genuine used luxury goods of a specific model, and appraise a plurality of genuine used luxury goods and a used luxury goods of the same model based on the collected component values, thereby increasing the accuracy of appraisal of used goods without relying solely on the appraisals of appraisers.

[0019] FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention;

[0020] Figure 2 is a drawing for explaining a method for calculating the grade of a used luxury product based on the degree of damage to the metal decoration provided on the bottom surface of the used luxury product.

[0021] Figure 3 is a drawing for explaining a method for calculating the grade of a used luxury product based on the degree of damage to the metal decoration provided on the bottom surface of the used luxury product and the degree of damage to the metal decoration provided on the non-bottom surface of the used luxury product.

[0022] Figure 4 is a block diagram showing a schematic configuration of the inside of a server according to an embodiment of the present invention.

[0023] FIG. 5 is a block diagram showing an example of hardware that can realize the function of a used luxury goods appraisal device according to an embodiment of the present invention.

[0024] Figure 6 is a flowchart showing a model learning method in a used luxury goods appraisal method according to an embodiment of the present invention, and

[0025] Figure 7 is a flowchart illustrating a method for appraising used luxury goods according to an embodiment of the present invention.

[0026] It should be noted that the technical terms used herein are merely used to describe specific embodiments and are not intended to limit the present invention. Furthermore, unless specifically defined otherwise herein, the technical terms used herein should be interpreted as having a meaning generally understood by those skilled in the art to which the present invention pertains, and should not be interpreted in an overly comprehensive or overly narrow sense. Furthermore, if a technical term used herein is incorrect and does not accurately express the spirit of the present invention, it should be replaced with a technical term that can be correctly understood by those skilled in the art. Furthermore, general terms used herein should be interpreted according to their dictionary definitions or according to the context, and should not be interpreted in an overly narrow sense.

[0027] Additionally, the singular expressions used herein include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "consist of" or "comprises" should not be construed to necessarily include all of the various components or various steps described in the specification, and should be construed to mean that some of the components or some of the steps may not be included, or that additional components or steps may be included.

[0028] In addition, the suffixes "module" and "part" used for components in this specification are given or used interchangeably only for the convenience of writing the specification, and do not have distinct meanings or roles in themselves.

[0029] Additionally, terms including ordinal numbers, such as "first," "second," etc., used herein may be used to describe various components, but these components should not be limited by these terms. These terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a "second component," and similarly, a second component could also be referred to as a "first component."

[0030] Meanwhile, in an embodiment of the present invention, a mapping method using a transmission electron microscope (TEM) and a laser induced breakdown spectroscope (LIBS) is adopted to analyze the components of metal decoration.

[0031] In particular, in the present invention, it is preferable to measure the metal component of the surface of the metal decoration using laser-induced plasma spectroscopy (LIBS), which is capable of analyzing elements regardless of conductive and non-conductive materials.

[0032] Laser-induced plasma spectroscopy (LIBS) is based on the principle of laser ablation. Laser ablation refers to the process of removing small amounts of a sample surface by irradiating the surface with a laser beam using a high-power pulsed laser. This process instantaneously creates an ultra-high-temperature plasma on the surface of the material, and LIBS is an elemental analysis instrument that spectroscopically analyzes the light emitted from this plasma to perform qualitative and quantitative analysis. LIBS is an atomic spectroscopy method that directly obtains atomic emission lines from the target in the solid, liquid, or gaseous state, enabling rapid detection of trace elements without any preprocessing.

[0033] Light elements are difficult to analyze with equipment such as X-ray fluorescence (XRF) because they are easily ionized. Since spectroscopy using LIBS is suitable for analyzing light elements such as Li and Na on the surface of a material, in the present invention, Cr on the surface of a metal decoration was analyzed using LIBS. Specifically, in order to analyze a large amount of light elements that have the characteristic of being easily ionized even with a small power, conditions for increasing the spot size and lowering the laser level can be selected during LIBS analysis. In addition, since analysis of metal components such as Ni, Co, Mn, Zr, Mg, and Ti is required along with light elements such as Cr, appropriate conditions for the spot size and laser level that can analyze both light and heavy elements can be selected.

[0034] According to one embodiment, when measuring using laser-induced bubbling plasma spectroscopy (LIBS), the spot size can be set to, for example, 10 to 200 μm, for example, 50 to 200 μm, for example, 100 to 200 μm, but is not limited thereto. As the spot size increases, the power of energy can be reduced, and as the spot size decreases, the power can be increased to enable intensive analysis. Specifically, when analyzing metals, the content of light elements such as Cr is high, so low energy is required, and therefore the spot size can be set to 100 to 200 μm. In the above-mentioned spot size range, there can be an advantage of being able to analyze light elements that are easily ionized.

[0035] Additionally, the laser level can be set to, for example, 10 to 200 mJ, for example, 10 to 50 mJ, for example, 25 to 50 mJ, and can be suitable for analyzing light elements such as Cr present in the decorative surface within the above-mentioned laser level setting range.

[0036] In addition, the mapping resolution can be set to 0.2 microns or more, for example, 0.2 to 1 micron, and precise detection and content analysis of light elements can be performed under the above conditions.

[0037] [Explanation of symbols[

[0038] 110: Multiple Appraisal Terminal 120: Used Luxury Goods Appraisal Device

[0039] 121: Appraisal Result Prediction Department 122: Appraisal Result Approval Department

[0040] 123: Appraisal result input section 124: Appraisal result understanding section

[0041] 125: Emotional Score Evaluation Department 126: Compensation Department

[0042] 130: Network

[0043] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components are given the same reference numbers and redundant descriptions thereof will be omitted.

[0044] Furthermore, when describing the present invention, detailed descriptions of related known technologies will be omitted if they are deemed to obscure the gist of the present invention. Furthermore, it should be noted that the attached drawings are intended solely to facilitate understanding of the spirit of the present invention and should not be construed as limiting the spirit of the present invention.

[0045] FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention.

[0046] The network environment of Fig. 1 illustrates an example including multiple appraisal terminals (110), servers (120), and networks (130). Fig. 1 is an example for explaining the invention, and the number of appraisal terminals or servers is not limited to that of Fig. 1.

[0047] The plurality of appraisal terminals (110) may be fixed terminals implemented as computer devices or mobile terminals. Examples of the plurality of appraisal terminals (110) include smart phones, mobile phones, navigation devices, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, etc. For example, the plurality of appraisal terminals (110) may communicate with the server (120) via a network (130) using a wireless or wired communication method.

[0048] The communication method is not limited, and may include not only a communication method that utilizes a communication network (e.g., a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network) that the network (130) may include, but also short-range wireless communication between devices. For example, the network (130) may include any one or more of a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), the Internet, and the like. In addition, the network (130) may include any one or more of a network topology including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree, or a hierarchical network.

[0049] The server (120) may be implemented as a computer device or multiple computer devices that communicate with multiple appraisal terminals (110) via a network (130) to provide commands, codes, files, content, services, etc. Here, the server (120) corresponds to a used luxury goods appraisal device according to the present invention.

[0050] For example, the server (120) may provide a file for installing an application to a plurality of appraisal terminals (110) connected via a network (130). In this case, the plurality of appraisal terminals (110) may install the application using the file provided from the server (120). In addition, each of the plurality of appraisal terminals (110) may access the server (120) under the control of an operating system (OS) and at least one program (e.g., a browser or an installed application) that it includes and receive services or content provided by the server (120). For example, the plurality of appraisal terminals (100) may access the server (120) via the network (130) under the control of an application and input appraisal results for used luxury goods. The server (120) compiles the input appraisal data and outputs a second appraisal result indicating whether the used luxury goods are genuine or counterfeit.

[0051] In addition, the server (120) can collect the component values ​​of metal decorations provided on a plurality of genuine used luxury goods of a specific model, and appraise the plurality of genuine used luxury goods and the used luxury goods of the same model based on the collected component values. In particular, the server (120) collects correct answer data including the component values ​​of metal decorations of a plurality of genuine used luxury goods, repeatedly inputs the collected correct answer data into an artificial intelligence model to train the artificial intelligence model, and then collects input data including the component values ​​of metal decorations of the used luxury goods, inputs the collected input data into the trained artificial intelligence model, and compares the error values ​​between the input data and the output data of the trained artificial intelligence model, thereby outputting a first appraisal result of the used luxury goods.

[0052] In addition, the server (120) can compare the first and second appraisal results to finally appraise the used luxury goods. That is, the server (120) can compare the first and second appraisal results and, if the difference between the results falls outside the critical range, determine that the appraisal is not possible.

[0053] In addition, as illustrated in FIG. 2, the server (120) can evaluate the degree of damage to the metal decoration (10) provided on the bottom surface of the used luxury product and calculate the grade of the used luxury product based on the degree of damage. That is, the server (120) can store the correlation between the degree of damage to the metal decoration (10) and the grade of the used luxury product in the form of a table and calculate the grade of the used luxury product corresponding to the degree of damage to the metal decoration (10).

[0054] In addition, as illustrated in FIGS. 2 and 3, the server (120) can evaluate the first degree of damage of the metal decoration (10) provided on the bottom surface of the used luxury product and the second degree of damage of the metal decoration (20) provided on the non-bottom surface of the used luxury product, and compare the first degree of damage and the second degree of damage to determine the grade of the used luxury product. That is, the server (120) can store the correlation between the difference between the first degree of damage of the metal decoration (10) provided on the bottom surface of the used luxury product and the second degree of damage of the metal decoration (20) provided on the non-bottom surface of the used luxury product and the grade of the used luxury product in the form of a table, and can determine the grade of the used luxury product corresponding to the difference.

[0055] In addition, the server (120) can evaluate the degree of damage when the metal decoration is in an angular shape (e.g., a hexagonal button, etc.) compared to when the metal decoration is in a round shape, and determine the grade of the used luxury product based on the degree of damage.

[0056] Figure 4 is a block diagram showing a schematic configuration of the inside of a server according to an embodiment of the present invention.

[0057] Referring to FIG. 4, the server (120) according to the present invention may include an appraisal result prediction unit (121), an appraisal qualification approval unit (122), an appraisal result input unit (123), an appraisal result identification unit (124), an appraisal score evaluation unit (125), and a compensation unit (126).

[0058] The appraisal result prediction unit (121) collects the component values ​​of metal decorations provided on multiple genuine used luxury goods of a specific model, and appraises multiple genuine used luxury goods and used luxury goods of the same model based on the collected component values.

[0059] That is, the appraisal result prediction unit (121) collects correct answer data including the component values ​​of metal decorations of multiple genuine used luxury goods, and repeatedly inputs the collected correct answer data into the artificial intelligence model to train the artificial intelligence model. Specifically, the appraisal result prediction unit (121) compresses N correct answer data (consisting of vectors and also called features) through the compressor of the artificial intelligence model, and outputs the compressed data as restored data of the same form or similar size as the correct answer data through the restorer of the artificial intelligence model. The appraisal result prediction unit (121) trains the artificial intelligence model by repeatedly performing compression and restoration while changing the parameters of the artificial intelligence model so that the restoration error values ​​of the correct answer data and the restored data are appropriately reduced. At this time, the model used for compression and restoration may be a PCA, an auto-encoder, etc.

[0060] Here, the emotion result prediction unit (121) can calculate the restoration error value through one of the methods of MAE (Mean Absolute Error), MAPE (Mean Absolute Percentage Error), sMAPE (symmetric Mean Absolute Percentage Error), MSE (Mean Squared Error), and mMAPE (maximum Mean Absolute Percentage Error).

[0061] In addition, when a large deviation occurs in the error value at each consecutive point in time of the data, the emotion result prediction unit (121) can specify a window length, calculate the average value of the error values ​​at points in time within the window length based on the point in time, and change the error value at the point in time to the average value.

[0062] Meanwhile, the appraisal result prediction unit (121) collects input data including the component values ​​of the metal decoration of the used luxury product, inputs the collected input data into a learned artificial intelligence model, and compares the error values ​​between the input data and the output data of the learned artificial intelligence model to output the first appraisal result of the used luxury product. That is, the appraisal result prediction unit (121) compares the restoration error values ​​between the input data and the output data of the learned artificial intelligence model, and if the restoration error value exceeds a preset threshold value, determines the used luxury product as a counterfeit, and if the restoration error value is lower than or equal to the preset threshold value, determines the used luxury product as a genuine product.

[0063] Here, the emotional result prediction unit (121) can determine a preset threshold value using the following mathematical expression 1.

[0064]

[0065] Here, α and β represent fixed constant values.

[0066] In addition, the emotion result prediction unit (121) can use a constant value determined in advance through an experiment as a preset threshold value.

[0067] Meanwhile, in the embodiment of the present invention, the appraisal result prediction unit (121) is described as appraising used luxury goods using an unsupervised learning method, but it is not limited thereto, and the appraisal result prediction unit (121) may appraise used luxury goods using a supervised learning method.

[0068] To this end, the appraisal result prediction unit (121) is a model based on a convolutional neural network that has been pre-trained to be able to determine whether each used luxury product is genuine or fake based on a training set consisting of component values ​​of metal decorations of a plurality of genuine used luxury goods and component values ​​of metal decorations of a plurality of fake used luxury goods. When the component values ​​of the metal decorations of each used luxury product are input, a model for determining whether each used luxury product is genuine can be constructed by passing the component values ​​input through the convolutional neural network.

[0069] Here, a convolutional neural network is a neural network composed of multiple convolutional layers and pooling layers composed of convolutional filters, and when input data such as component values ​​of the convolutional neural network are configured as a feature map and input to the convolutional layer, convolution occurs by convolutional filters having one or more channels constituting the convolutional layer to generate an output feature map, and downsampling is performed to reduce the size of the output feature map through a pooling layer, and then the output is input again to the next convolutional layer and pooling layer, and this process is repeated, and a predetermined output is produced through repetition of this process.

[0070] In this regard, the process by which a developer builds a deep learning discrimination model for a specific used luxury product among multiple used luxury products is briefly described as follows. First, the developer can prepare the component values ​​of the metal decorations of used luxury products that are genuine and the component values ​​of the metal decorations of used luxury products that are counterfeit, and configure them as a training set. Then, the developer designates the component values ​​of genuine products as inputs to a convolutional neural network, and simultaneously designates a predetermined output value indicating 'genuine' as the output of the convolutional neural network. Furthermore, the developer designates the component values ​​of counterfeit products as inputs to the convolutional neural network, and simultaneously designates a predetermined output value indicating 'counterfeit' as the output of the convolutional neural network, and then performs supervised learning on the convolutional neural network, thereby building a deep learning discrimination model based on the convolutional neural network.

[0071] The appraisal qualification approval department (122) approves the appraisal qualifications of registered members. In one embodiment, the appraisal qualification approval department (22) receives membership applications. Some registered individual members can be converted to appraisers with appraisal qualifications, i.e., business members, through the appraisal qualification approval process.

[0072] In other words, registered members who are business owners or capable of appraising used luxury goods can be converted to business members. In this embodiment, only business members approved by the Appraisal Qualifications Approval Department (122) can participate in appraisals as appraisers.

[0073] For general members who have only registered as members, it is impossible to participate in the appraisal of used luxury goods, but they can respond to data appraised by business members through comments.

[0074] The appraisal qualification approval department (122) receives business information including company number, company name, address, and online website address to convert to a business member and approves the member's appraisal qualification.

[0075] The appraisal qualification approval department (122) may request additional information when necessary for appraisal qualification approval, and may approve appraisal qualification over several days.

[0076] In an embodiment of the present invention, the used luxury goods appraisal device (120) may provide an online used luxury goods sales platform. Registered members can sell and purchase used luxury goods on the online used luxury goods sales platform. However, to participate in used luxury goods appraisals, appraisal qualifications must be approved through the appraisal qualification approval process of the appraisal qualification approval department (122).

[0077] The appraisal result input unit (123) receives appraisal results on whether a used luxury item is genuine or counterfeit from at least one appraiser who has been approved as an appraiser. In this case, the appraiser is a business member who has been approved as an appraiser by the appraisal qualification approval unit (122).

[0078] In one embodiment, the emotion result input unit (123) provides an emotion activity related page that is not provided to general members to business members who have been approved as emotion eligibility.

[0079] Business members can review luxury goods data, including images, descriptive text, and videos, for used luxury goods for which they have requested an appraisal, and determine whether the item is genuine or counterfeit. Based on the appraisal results, business members can select one of three options: authentic, counterfeit, or request additional information, and then provide additional comments.

[0080] According to an embodiment of the present invention, business members can participate in the appraisal once for each luxury item listing, and once selected, the appraisal option (genuine or fake) cannot be changed. This is to encourage business members to participate in the appraisal more carefully and to prevent them from changing their selection after the appraisal results are released.

[0081] However, if you select "Request Additional Data" from the emotional options, you can change the selection between genuine and fake at any time. It should be noted that even if you select "genuine" or "fake" after requesting additional data, you cannot change the selection.

[0082] At this time, it is not possible to change the selection for genuine or fake, but it is possible to modify and add specific appraisal comments.

[0083] For general members, it's possible to implement a system that allows them to comment on the content appraised by business members or express their opinions with likes and dislikes. This can encourage business members to exercise caution when appraising, thereby enhancing the reliability of appraisals.

[0084] The appraisal result identification unit (124) collects appraisal data input from different appraisers for a single used luxury item and determines the appraisal result indicating whether the used luxury item is genuine or counterfeit based on the collected appraisal data.

[0085] That is, the appraisal result identification unit (124) collates the appraisal data entered by appraisers and determines whether a single used luxury item is genuine or counterfeit. At this time, for the appraisal result identification unit (124) to determine the final appraisal result, at least three identical appraisals for genuine or counterfeit items must be collected. Alternatively, if three or more identical appraisals (genuine / fake) are not collected 24 hours after the used luxury item is listed, the final appraisal result can be derived based on the appraisal data at the time 24 hours have passed.

[0086] At this time, it is desirable to implement a system where, until the appraisal results are available, the appraisal data (genuine / fake) from other business members cannot be viewed, except for the information provided by the business member who registered the used luxury item (for sale) and the "Additional Data Request." Furthermore, once the appraisal results are available, all appraisal data (genuine / fake) and comments from other business members can be viewed.

[0087] The final appraisal result can be one of the following: genuine, fake, or appraisal.

[0088] The emotional score evaluation unit (125) evaluates the emotional scores for the emotional results entered by each of the different emotional appraisers based on the emotional result evaluation results of the emotional result evaluation unit (124).

[0089] In the case of business members who participated in the appraisal (genuine / fake), the appraisal scores for the appraisal results entered by each appraiser (business member) are evaluated.

[0090] For example, before the final appraisal results are determined, all participating business members are awarded +5 points. Furthermore, if the appraisal results change, the appraisal scores may also change.

[0091] If a specific business member (appraiser) performs an appraisal identical to the final appraisal result, they will receive +5 points, and if they perform an appraisal different from the final appraisal result, they will receive -25 points. Furthermore, if an appraisal is performed after the appraisal result has been released, they will receive +2 points, and if an appraisal is performed differently from the final appraisal result, they will receive +5 points. In this case, the appraisal score evaluation unit (125) will change the appraisal score to +5 points if the appraisal is identical to the final appraisal result and -25 points if the appraisal is different from the final appraisal result.

[0092] That is, once the final appraisal results are derived, the appraisal scores obtained by each business member may change accordingly.

[0093] Furthermore, in one aspect, the appraisal score evaluation unit (125) is characterized by reflecting the number of appraisal participations, the accuracy of appraisal participation, and other members' evaluations of the appraisal when evaluating the appraisal score. The appraisal score evaluation unit (125) can change the appraisal score by reflecting the number of appraisal participations, the accuracy of appraisal participation, and other members' evaluations of the appraisal. In other words, the appraisal participation rate can be increased, and by calculating the appraisal score based on the accuracy of the appraisal, business members can participate in luxury goods appraisals more carefully.

[0094] In one aspect of the present invention, the compensation unit (126) evaluates the emotional activities of the appraisers based on the emotional scores of the appraisers evaluated by the emotional score evaluation unit (125), assigns an emotional level, and rewards the appraisers according to the assigned emotional level.

[0095] The compensation department (126) can offer various benefits, including discounts on sales commissions, increased exposure for products sold by business members, and other benefits based on appraisal levels. For example, it can offer discounts on sales commissions for business members who are appraisers. It can also enhance the exposure of used luxury goods sold by business members.

[0096] Additionally, the compensation department (126) divides the sales price into sections and provides commissions for each section. Each time a level is raised, the commission for one section may decrease. In other words, when a business member, who is an appraiser, sells a used luxury item using the used luxury item appraisal device (120) according to the embodiment, the business member receives commission benefits based on the member's level.

[0097] That is, the compensation unit (126) can motivate the emotional activities of the appraisers and instill prudence in the emotions by assigning emotional levels through evaluation of the emotional activities of the appraisers based on the emotional scores and rewarding the appraisers according to the assigned emotional levels.

[0098] Below, the specific configuration of the used luxury goods appraisal device according to the present invention will be described.

[0099] Referring to Fig. 5, hardware capable of realizing the functions of a used luxury goods appraisal device (120) is described. Fig. 5 is a block diagram illustrating an example of hardware capable of realizing the functions of a used luxury goods appraisal device (120) according to an embodiment of the present invention.

[0100] The functions of the used luxury goods appraisal device (120) can be realized using, for example, the hardware resources illustrated in FIG. 5. That is, the functions of the used luxury goods appraisal device (120) are realized by controlling the hardware illustrated in FIG. 5 using a computer program.

[0101] As illustrated in FIG. 5, the hardware mainly has a CPU (502), a ROM (Read Only Memory) (504), a RAM (506), a host bus (508), and a bridge (510). In addition, the hardware has an external bus (512), an interface (514), an input unit (516), an output unit (518), a memory unit (520), a drive (522), a connection port (524), and a communication unit (526).

[0102] The CPU (502) functions as, for example, an operation processing unit or a control unit, and controls the overall operation or part of the operation of each component based on various programs recorded in the ROM (504), the RAM (506), the memory (520), or the removable recording medium (528). The ROM (504) is an example of a storage device that stores programs read by the CPU (502), data used for operations, etc. In the RAM (506), for example, programs read by the CPU (502), various parameters that change when executing the program, etc. are temporarily or permanently stored.

[0103] These elements are connected to each other, for example, through a host bus (508) capable of high-speed data transmission. Meanwhile, the host bus (508) is connected to an external bus (512) with a relatively low data transmission speed, for example, through a bridge (510). In addition, as the input unit (516), for example, a mouse, a keyboard, a touch panel, a touch pad, a button, a switch, a lever, and the like are used. In addition, as the input unit (516), a remote controller capable of transmitting a control signal using infrared rays or other radio waves can be used.

[0104] As the output unit (518), a display device such as a CRT (Cathode Ray Tube), an LCD (Liquid Crystal Display), a PDP (Plasma Display Panel), or an ELD (Electro-Luminescence Display) can be used, for example. In addition, as the output unit (518), an audio output device such as a speaker or headphone, or a printer, etc. can be used.

[0105] The memory unit (520) is a device for storing various types of data. For example, a magnetic storage device such as an HDD is used as the memory unit (520). Furthermore, a semiconductor storage device such as an SSD (Solid State Drive) or a RAM disk, an optical storage device, or an optical magneto-magnetic storage device may also be used as the memory unit (520).

[0106] The drive (522) is a device that reads information recorded on a removable recording medium (528), which is a removable recording medium, or records information on the removable recording medium (528). As the removable recording medium (528), for example, a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory may be used. In addition, a program that regulates the operation of the used luxury goods appraisal device (120) may be stored on the removable recording medium (528).

[0107] The connection port (524) is a port for connecting an external connection device (530), such as a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface), an RS-232C port, or an optical audio terminal. As the external connection device (530), a printer or the like is used, for example.

[0108] The communication unit (526) is a communication device for connecting to a network (532). As the communication unit (526), ​​for example, a communication circuit for a wired or wireless LAN, a communication circuit for a WUSB (Wireless USB), a communication circuit for a mobile phone network, etc. can be used. The network (532) is, for example, a network connected by wire or wireless.

[0109] Above, the hardware of the used luxury goods appraisal device (120) has been described. Furthermore, the hardware described above is merely an example, and modifications such as omitting some elements or adding new elements are possible.

[0110] Figure 6 is a flowchart illustrating a model learning method in a used luxury goods appraisal method according to an embodiment of the present invention.

[0111] Referring to FIG. 6, the used luxury goods appraisal device (120) collects correct data including component values ​​of metal decorations of a plurality of genuine used luxury goods (S610).

[0112] The used luxury goods appraisal device (120) inputs the collected correct answer data into an artificial intelligence model (compressor) and compresses it to a specific length (S620).

[0113] The used luxury goods appraisal device (120) inputs compressed data into an artificial intelligence model (restorer) and restores it in the same form as the correct data (S630).

[0114] The used luxury goods appraisal device (120) determines whether the restoration error value between the correct data and the restored data is less than a preset threshold value (S640), and if the restoration error value is greater than the preset threshold value, it returns to step S620 and inputs the correct data into the artificial intelligence model again.

[0115] The used luxury goods appraisal device (120) terminates the learning of the artificial intelligence model when the restoration error value is less than a preset threshold value (S650).

[0116] Figure 7 is a flowchart illustrating a method for appraising used luxury goods according to an embodiment of the present invention.

[0117] Referring to FIG. 7, the used luxury goods appraisal device (120) collects input data including the component values ​​of the metal decoration of the used luxury goods (S710).

[0118] The used luxury goods appraisal device (120) inputs the collected input data into an artificial intelligence model (compressor) and compresses it to a specific length (S720).

[0119] The used luxury goods appraisal device (120) inputs compressed data into an artificial intelligence model (restorer) and restores it in the same form as the input data (S730).

[0120] The used luxury goods appraisal device (120) determines whether the restoration error value between the input data and the restoration data is below a preset threshold value (S740), and if the restoration error value is below the preset threshold value, determines the used luxury goods to be genuine (S750).

[0121] The used luxury goods appraisal device (120) determines the used luxury goods as counterfeit if the restoration error value exceeds a preset threshold value (S742).

[0122] Next, the used luxury goods appraisal device (120) receives appraisal data on used luxury goods from at least one appraiser (S760).

[0123] The used luxury goods appraisal device (120) collects the input appraisal data to determine whether the used luxury goods are genuine (S770), and if the used luxury goods are determined to be genuine, the used luxury goods are finally determined to be genuine (S780).

[0124] If the used luxury goods appraisal device (120) determines that the used luxury goods are counterfeit, it determines that the used luxury goods are counterfeit (S772).

[0125] Meanwhile, in the embodiment of the present invention, it was described that after appraising a used luxury product based on a learned model, the used luxury product is additionally appraised by at least one appraiser. Conversely, after appraising a used luxury product by at least one appraiser, the used luxury product may be additionally appraised based on a learned model.

[0126] The aforementioned method can be implemented through various means. For example, embodiments of the present invention can be implemented through hardware, firmware, software, or a combination thereof.

[0127] In the case of hardware implementation, the method according to embodiments of the present invention may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), processors, controllers, microcontrollers, and microprocessors.

[0128] When implemented using firmware or software, the methods according to embodiments of the present invention may be implemented in the form of modules, procedures, or functions that perform the functions or operations described above. The software code may be stored in a memory unit and executed by a processor. The memory unit may be located within or outside the processor and may exchange data with the processor using various known means.

[0129] The embodiments disclosed in this specification have been described above with reference to the attached drawings. The embodiments depicted in each drawing should not be construed as limiting, and those skilled in the art, familiar with the contents of this specification, may combine them with each other. When combined, some components may be omitted.

[0130] Here, the terms or words used in this specification and claims should not be interpreted as limited to their usual or dictionary meanings, but should be interpreted as meanings and concepts consistent with the technical ideas disclosed in this specification.

[0131] Therefore, the embodiments described in this specification and the configurations illustrated in the drawings are merely embodiments disclosed in this specification and do not represent all of the technical ideas disclosed in this specification. Therefore, it should be understood that there may be various equivalents and modified examples that can replace them at the time of this application.

Claims

1. Memory that stores one or more instructions; and By executing one or more of the above stored instances, One or more processors that collect component values ​​of metal decorations provided on a plurality of genuine used luxury goods of a specific model, and appraise a used luxury goods of the same model as the plurality of genuine used luxury goods based on the collected component values; A used luxury goods appraisal device including .

2. In paragraph 1, One or more of the above processors, After collecting correct answer data including the component values ​​of the metal decorations of the above multiple genuine used luxury goods, and repeatedly inputting the collected correct answer data into an artificial intelligence model to train the artificial intelligence model, A used luxury goods appraisal device characterized in that it collects input data including the component values ​​of the metal decoration of the used luxury goods, inputs the collected input data into a learned artificial intelligence model, and outputs a first appraisal result of the used luxury goods by comparing an error value between the input data and the output data of the learned artificial intelligence model.

3. In paragraph 2, The one or more processors receive appraisal data of the used luxury goods from at least one appraiser, collate the input appraisal data, and output a second appraisal result of the used luxury goods. A used luxury goods appraisal device characterized in that the used luxury goods are finally appraised by comparing the first appraisal result and the second appraisal result.

4. In paragraph 1, A used luxury goods appraisal device characterized in that the one or more processors evaluate the degree of damage to the metal decoration provided on the bottom surface of the used luxury goods and calculate the grade of the used luxury goods based on the degree of damage.

5. In paragraph 1, A used luxury goods appraisal device characterized in that the one or more processors evaluate a first degree of damage to a metal decoration provided on a bottom surface of the used luxury goods and a second degree of damage to a metal decoration provided on a non-bottom surface of the used luxury goods, and compare the first degree of damage and the second degree of damage to determine a grade of the used luxury goods.

6. A step of collecting the component values ​​of metal decorations provided on a plurality of genuine used luxury goods of a specific model by one or more processors; and A step in which the one or more processors appraise the plurality of genuine used luxury goods and the used luxury goods of the same model based on the collected component values; A method of appraising used luxury goods, including:

7. In paragraph 6, the step of appraising the used luxury goods is: A step in which the one or more processors collect correct answer data including the component values ​​of the metal decorations of the plurality of genuine used luxury goods, and repeatedly input the collected correct answer data into an artificial intelligence model to train the artificial intelligence model; and A step in which the one or more processors collect input data including component values ​​of metal decorations of the used luxury goods, input the collected input data into a learned artificial intelligence model, and compare an error value between the input data and output data of the learned artificial intelligence model to output a first appraisal result of the used luxury goods; A method for appraising used luxury goods, characterized by including:

8. In paragraph 7, the step of appraising the used luxury goods is: A step in which the one or more processors input appraisal data of the used luxury goods from at least one appraiser, collate the input appraisal data, and output a second appraisal result of the used luxury goods; and A step in which the one or more processors compare the first appraisal result and the second appraisal result to finally appraise the used luxury product; A method for appraising used luxury goods, characterized by including:

Images