WO2020196945A1

WO2020196945A1 - Artificial intelligence appraisal system, artificial intelligence appraisal method, and recording medium

Info

Publication number: WO2020196945A1
Application number: PCT/KR2019/003518
Authority: WO
Inventors: 김의선
Original assignee: 김의선
Priority date: 2019-03-26
Filing date: 2019-03-26
Publication date: 2020-10-01

Abstract

Disclosed is an artificial intelligence appraisal system comprising a customer terminal and an appraisal server for appraising an item on the basis of image data transmitted online from the customer terminal through a network, wherein the appraisal server comprises an artificial intelligence-based appraisal engine trained by deep learning so that a model of the item can be distinguished, and the appraisal engine distinguishes whether the item corresponds to a genuine product of the model by performing image signal processing on one or more point parts of the item.

Description

Artificial intelligence emotion system, artificial intelligence emotion method and recording medium

The present disclosure relates to an artificial intelligence emotion system, an artificial intelligence emotion method, and a recording medium.

Luxury items such as precious metals, watches, clothing, bags, shoes, wallets, and high-priced items such as artworks such as antiques, ceramics, calligraphy and crafts are often traded at high prices even if they are used items due to their rarity. . These high-value items can be exchanged for a lot of cash if you leave them as collateral at a pawn shop. For this reason, these high-value products are often circulated in the market for counterfeits or counterfeits.

Conventionally, the appraisal of corporate movables including such high-value items has been assessed by a professional appraiser, who has been engaged in the appraisal business for a long time, while residing in a pawnshop or the like to appraise its authenticity or price. In recent years, even if you do not visit the pawnshop in person, if you transmit a picture of an item taken by the owner at a remote location through a wired or wireless network using a terminal such as a computer or smartphone, you will be able to determine whether the item is genuine based on the transmitted picture. A remote appraisal service that provides information on market prices and the like is being studied.

However, according to the research of the present inventors, since most of the existing methods depend on the personal experience of the appraiser, there is a problem that the emotion cannot be consistently performed according to a scientific and standardized method. In addition, there is a problem in that the accuracy of the emotion is greatly degraded in the existing emotion method based on a photograph of an article. Therefore, there is a need to develop a remote appraisal system capable of consistently performing appraisal in a scientific and standardized manner, performing more accurate appraisal, and presenting more accurate and objective appraiser based on appraisal results. .

The present disclosure provides an artificial intelligence emotion system, an artificial intelligence emotion method, and a recording medium capable of greatly improving the problems of the prior art, including the above problems.

An embodiment of the present disclosure includes a customer terminal and an emotion server that performs an assessment of an article based on image data transmitted from the customer terminal through a network, wherein the appraisal server determines a model of the article by deep learning. It is an artificial intelligence emotion system that includes an artificial intelligence-based emotion engine that has been learned so as to be able to perform, and the emotion engine determines whether the product corresponds to the authenticity of the model by performing image signal processing on one or more point portions of the product. I can.

An embodiment of the present disclosure includes an appraisal server for appraising an article based on image data of an article transmitted online through a network, wherein the appraisal server determines a model of the article based on the image data transmitted online. A model evaluation to determine, a genuine evaluation of determining whether the product corresponds to the genuineness of the model by performing image signal processing on one or more point portions of the product, and replacement of one or more point parts of the product, State evaluation for determining at least one factor among deformation, contamination, and discoloration, and condition evaluation for determining the condition index of the article based on this, and evaluation value determination for determining the evaluated value of the article based on the condition index It may be an artificial intelligence emotion method that executes.

An embodiment of the present disclosure may be a computer-readable recording medium in which a computer program for executing the artificial intelligence method is recorded.

According to the present disclosure, it is possible to provide an artificial intelligence emotion system, an artificial intelligence emotion method, and a recording medium capable of greatly improving the problems of the prior art, including the above problems.

In addition, various embodiments according to the present disclosure and their objects, configurations, actions, effects, advantages, and the like will be described in detail in the following description of the invention with reference to the accompanying drawings.

1 is a block diagram showing a schematic configuration of an artificial intelligence emotion system 1 according to an embodiment of the present disclosure.

2A to 2G are diagrams schematically showing an example of an operation screen of an emotion application executed in the customer terminal 30.

3 is a flow chart showing an emotion procedure executed in the emotion server 10.

4A and 4B are diagrams showing an example of a procedure for displaying model information of an article through the customer terminal 30.

5A to 5F are diagrams for explaining examples of authenticity emotions performed by the emotion engine installed in the emotion server 10.

6 is a diagram illustrating an example of a big data-based price database DB for calculating an appraised price.

Hereinafter, an embodiment of the present disclosure will be described in detail with reference to the accompanying drawings. In the following description, “one embodiment” means an exemplary embodiment presented to aid in understanding the present disclosure, and the present disclosure is not limited to the exemplary embodiments described below. For convenience of description, the accompanying drawings may be partially enlarged, exaggerated, or simplified or omitted.

Throughout the description of the invention, when it is described that a part is "connected" or "connected" with another part, not only is it directly connected or connected, but also indirectly connected or connected through another medium or component in the middle It can also include the case where it is. When it is described that a part "includes" a certain component, it may further include, rather than excluding, other components other than the described components, unless specifically stated otherwise, and one or more other features or components It does not exclude the possibility of the presence or addition of, parts, steps, actions, or combinations thereof.

First, the overall configuration of the artificial intelligence emotion system 1 according to an embodiment of the present disclosure will be described.

Referring to FIG. 1, the artificial intelligence emotion system 1 may include an emotion server 10, a manager terminal 20, and a customer terminal 30. The artificial intelligence emotion system 1 may further include a data crawler 40. The emotion server 10, the manager terminal 20, the customer terminal 30, and the data crawler 40 are connected to the network (N) and can communicate with each other through the network (N).

The emotion server 10 may be a device that manages and controls the overall operation of the artificial intelligence emotion system. The emotion server 10 can manage and control the transmission/reception, processing, input and output of various data (including electrical signals and/or information) as a whole according to a control command from the manager terminal 20 and/or its own operation program. I can. The emotion server 10 may include, for example, a data processing unit such as a CPU, a data memory unit such as RAM and ROM, a communication unit for transmitting and receiving data, various input/output terminals for input/output of data, and the like. The emotion server 10 may include an emotion engine for performing an emotion, software such as a computer program required for system operation, and a database for storing various data used for emotion. The emotion server 10 may communicate with the manager terminal 20 and/or the data crawler 40 as necessary to perform a task necessary for the emotion. The appraisal server 10 may receive data on an item to be appraised from the customer terminal 30, perform an appraisal based thereon, and then transmit data regarding the appraisal result to the customer terminal 30. . To this end, the emotion server 10 may include a service server for providing a remote service to the customer terminal 30.

The emotion engine mounted in the emotion server 10 may include an artificial intelligence-based image processing engine that determines the model of the product, whether it is authentic, or the like, through an image captured by the user's customer terminal 30. The appraisal engine may further include a big data-based price determination engine that determines an appraisal value according to the determined product model information. Details will be described later.

The manager terminal 20 may be a device through which the manager accesses the artificial intelligence emotion system 1 through the network N. The manager may communicate with the emotion server 10 or the data crawler 40 by accessing the network N through the manager terminal 20. The manager terminal 20 may also communicate with the customer terminal 30 through the network N as necessary. The manager terminal 20 may include various input/output means capable of communication such as transmitting a control command or the like to the emotion server 10 or the data crawler 40 or receiving a processing result of data from these devices. For example, the manager terminal 20 may include a desktop computer as well as a mobile input/output means such as a notebook computer, a tablet computer, and a smart phone. The manager terminal 20 can store and execute manager software or a database required for the operation of the artificial intelligence appraisal system 1.

The customer terminal 30 may be a device for a user who wants to appraise an article to access the artificial intelligence appraisal system 1 through a network N. The customer terminal 30 may include various input/output means capable of communicating with the emotion server 10. The customer terminal 30 may store and execute an emotion application in order to transmit and receive data necessary for the emotion. The emotion application may be downloaded by connecting directly to the emotion server 10 or by accessing an Internet website, a web store, a mobile store, etc. that provide an application for downloading. The emotion application may be provided by being stored in a recording medium such as a CD, USB, or SD.

The data crawler 40 is a device that collects, stores, processes and/or updates (hereinafter referred to as "crawling") data necessary for the operation of the artificial intelligence emotion system 1 through the network N Can be The data crawler 40 may be a server device such as the emotion server 10. The data crawler 40 may build a database necessary for the emotion engine of the emotion server 10 or an assessment value calculation engine, and store and execute software necessary for crawling data. The data crawler 40 may perform crawling or input/output of data at any time and/or periodically according to a control command from the emotion server 10 or the manager terminal 20 and/or its own operation program. The data crawler 40 may be configured to be connected only to the emotion server 10 and to be operated only by the emotion server 10 as necessary.

The network N may include various types of wired or wireless communication networks that connect the emotion server 10, the manager terminal 20, the customer terminal 30, and the data crawler 40 to each other so as to communicate with each other. The network N is an Internet network that provides server-client web services, and may include, for example, a wired or wireless Internet network such as LAN, WAN, 4G, 5G, WIFI, and the like. The network N may be configured such that at least some of the emotion server 10, the manager terminal 20, and the data crawler 40 are connected only through a closed internal communication network such as a local intranet, if necessary.

Hereinafter, an artificial intelligence emotion method according to an embodiment of the present disclosure using the artificial intelligence emotion system 1 including the above-described configuration will be described in detail with reference to the drawings.

First, the operation of the emotion application executed in the customer terminal 30 will be described.

2A to 2G illustrate a case of using a smartphone as an example of the customer terminal 30, but the customer terminal 30 is not limited thereto, and data including image information such as photos and videos of an article It goes without saying that various input/output means that can be transmitted through the network N and received and confirmed the result of the emotion can be used.

Referring to FIG. 2A, first, a user may access a mobile store that provides an application for download, or the like, and download and execute an emotion application to the customer terminal 30.

When the emotion application is executed, the home screen 32 may be displayed. The home screen 32 may include a service icon display unit 32a. The service icon display unit 32a may display, for example, a service icon on the screen that allows the user to select a desired service type. The service icon may include one or more icons representing services such as, for example, transaction, wallet, emotion, notification, and settings.

The transaction icon is an online marketplace where users can place information on a list, status, price, etc. of goods and trade with each other, or an online shopping mall where an administrator places information on the list, status, and price of goods and sells and/or rents them. Alternatively, it may be an icon for moving to a screen providing a service such as a rental shop. The wallet icon may be an icon for moving to a screen providing a service for users to input, store, and pay for information on a mobile payment method such as card, cash, coupon, and the like. The emotion icon may be an icon for moving to a screen providing an artificial intelligence emotion service according to the present disclosure with respect to an item for which the user desires emotion. The notification icon may be an icon for moving to a screen displaying contents of a received message with the user as a recipient. The setting icon may be an icon for moving to a screen for designating or changing various settings or operations of an application.

In addition to the service icon, the home screen may further include a member sign-up icon. The member sign-up icon may be an icon for entering information such as a user's name, age, gender, address, and contact information, setting an ID and password, and moving to a screen for signing up as a member. When the member sign-up process is completed by tapping or touching the member sign-up icon, an account for a member may be provided. When an account for a member is provided, the emotion server 10 may preferentially receive and/or process data input through the account for a member. Data transmitted and received through the account for members may be continuously managed while being stored and updated in the emotion server 10.

When a service icon is pressed or touched, a guide phrase describing a service provided by each icon may be displayed on the screen. For example, when the emotion icon is touched, a guide phrase such as "Try changing the item to a cache now" may be displayed on the upper part of the service icon display unit 32a.

Referring to FIG. 2A, when a user presses or touches a transaction icon or an emotion icon, for example, the home screen 32 displays a category icon indicating a category of an item handled by a transaction service or an emotion service on the screen. 32b).

The category icon may include an icon representing the name or image of an item such as a laptop, tablet, mobile, bag, watch, wallet, shoes, etc. I can. For items for which the service is not yet provided, a guide phrase such as "coming soon" may be displayed along with an icon indicating the name or image of the product. Since the product category may be automatically determined by the emotion engine, when the emotion icon is pressed or touched, the category icon screen may not be displayed and the screen may be moved directly to the next screen.

When selecting the emotion icon or when selecting any one of the category icons, the home screen 32 may move to the emotion item photographing screen 34 as shown in FIGS. 2B to 2F.

Referring to FIG. 2B, the emotional article photographing screen 34 may include a screen window of a camera for acquiring image signal data such as a photograph or a video of an article. The image signal data of the emotional article can be acquired by photographing the emotional article through the screen window of the camera.

The emotion item photographing screen 34 may include a photographing sequence guide unit 34a, an image photographing unit 34b, and a help display unit 34c.

The photographing sequence guide unit 34a may be a screen for guiding a user of a photographing sequence of an article, a photographing part, a photographing method, and the like. The photographing sequence guide unit 34a allows the user to sequentially touch numbers such as ①, ②, ③, and jjs displayed on the screen, and take pictures according to the guidance displayed on the screen, so that the data necessary for the evaluation of the article is acquired. I can guide you.

The image photographing unit 34b is a screen window of a camera for photographing an emotional article, and may include a target window T for positioning a photographing object in a correct position. The target window T may include four bracket marks located at each corner of the substantially rectangular screen window, and an approximately cross-shaped target mark positioned at the center of the screen window to position the center of the target. The target window T can move its position or change its size by touching a finger. The target window T may be configured to recognize the photographing portion of the emotion item by itself and automatically adjust the position or size of the target window T according to a predetermined format.

The help display unit 34c may specifically describe a photographing method or present a standard photographed image to help the user accurately photograph. For example, when the help display unit 34c is touched, a guide phrase such as "Please remove the obstacles around and take a picture of the front of the product on a clean background" is displayed, or the standard of each shooting step according to the category of the emotion item Sample images can be presented.

For example, when the user selects the watch as the category of the emotion item, when the user touches the "①" icon on the photographing sequence guide 34a, the user can move to the front photographing screen of FIG. 2C. The front photographing screen displays, for example, a target window T for assisting in front photographing of the watch on the image photographing unit 34b, and displays "1. The whole from the front of the object in the lower part of the target window T" A guide phrase such as "Please take a picture" and a photograph button (B) can be displayed. In this case, if the help display unit 34c is touched, an exemplary sample image in which the front of the watch is correctly photographed may be displayed on the screen.

After the front photographing of the watch is completed, if the user touches the "②" icon on the photographing sequence guide 34a, the user can move to the rear photographing screen of FIG. 2D. On the back side of the screen, along with the target window (T) and the shooting button (B), it is possible to display a guide phrase such as "2. Take a picture of the inner side of the watch", and a sample image of the back side of the watch correctly. .

After completing photographing on the back side of the watch, if the user touches the "③" icon on the photographing sequence guide 34a, the user can move to the band photographing screen of FIG. 2E. The band shooting screen, along with the target window (T) and the shooting button (B), can display a guide phrase such as "3. Take a picture with the watch band", and a sample image of the watch band correctly. .

After completing the band photographing of the watch, if the user touches the "④" icon on the photographing sequence guide 34a, the user can move to the clip photographing screen of FIG. 2F. On the clip shooting screen, along with the target window (T) and the shooting button (B), a guide phrase such as "4. Take a clip (locked part) of the watch", and a sample video of the clip of the watch correctly shot are displayed. can do.

The emotion application selects whether or not to store the data such as photos and videos acquired by shooting in the customer terminal 30 after the user completes shooting for each shooting site according to the guidance of the shooting sequence guide 34a. You can display more screens. The emotion application may further display a screen for additionally inputting other information about the emotion item. The emotion application may further display a screen for selecting whether to transmit data for emotion after all procedures for acquiring data necessary for emotion are completed. In addition, it is of course possible to further configure various screens according to the user's convenience or providing a remote emotion service.

When the user transmits the data acquired through execution of the above-described appraisal application from the customer terminal 30 to the appraisal server 10 through the network N, the appraisal server 10 executes an appraisal procedure based on the transmitted data. And, the result can be transmitted to the customer terminal 30. More details will be described later.

The evaluation result by the emotion server 10 may be transmitted to the customer terminal 30. When the emotion result is transmitted to the customer terminal 30, the received emotion result may be displayed on a notification icon of the emotion application. When the user touches the notification icon after executing the emotion application, the user may move to the emotion result screen 35 as shown in FIG. 2G.

Referring to FIG. 2G, the emotion result screen 35 may display an emotion result by the emotion server 10 together with data such as a photo for specifying an emotion item. The evaluation result may be displayed on the screen, for example, a guide phrase such as "appraisal has been completed", whether or not the item is genuine, an exact model name or production year of the item to be judged, the state of the item to be judged, and the like. The emotion result may provide an emotion report created by the emotion server 10. For example, an appraisal icon representing an appraisal can be displayed on the appraisal result screen 35, and when the user touches the appraisal icon, the appraisal can be configured to view the appraisal created by the appraisal server 10. Such an appraisal may be created by an artificial intelligence appraisal engine to be described later. The appraisal may simply present an appraisal result such as whether the product is genuine or appraised value, or provide a method of presenting in detail the basis for the appraisal result, such as the condition of the product. The appraisal may be classified as a service item provided only to users who have subscribed as members.

On the other hand, if the data or video related to the item input by the user is not in the item list of items handled by the artificial intelligence appraisal system 1, the appraisal application itself does not transmit the video data of the item to the appraisal server 10, You can judge a result such as "not an emotion item" and display it on the screen. In addition, in the case of a result of the evaluation in the emotion server 10 or a product in which it is difficult to determine whether it is genuine or not, a result of "not appraised" may be displayed.

Next, an evaluation procedure executed in the emotion server 10 will be described in detail.

Referring to FIG. 3, the emotion server 10 may execute an emotion application installed in the customer terminal 30 by a user to execute an emotion procedure based on image data of an article photographed and transmitted. The appraisal procedure 10 may proceed in the order of model appraisal, genuine appraisal, state appraisal, appraiser determination, and result transmission.

First, when data photographing an image of an article is transmitted, the appraisal server 10 may perform a model appraisal for determining an accurate model of the article. The model evaluation may proceed in the order of a product group classification for classifying which product group (category) the emotion product belongs to, a brand classification for classifying a brand of the emotion product, and a model classification for classifying a model of the emotion product. To this end, the emotion server 10 may include an emotion engine for processing image data of an article to perform an article evaluation.

The emotion engine is an artificial intelligence (AI)-based image processing engine that learns to identify objects in an image by machine learning techniques, especially deep learning techniques, and can recognize objects by itself and distinguish them from other objects based on this. . When this emotion engine learns a large amount of image data according to product group, brand, model, status, etc., it identifies the product in the image transmitted by the user by the already learned and evolved artificial intelligence, and the product group, brand, model of the product is Of course, you can accurately determine the condition of the item. As the learning data for deep learning of the emotion engine, image data according to an item list such as a product group, a brand, and a model may be collected through the data crawler 40, and based on this, the emotion engine may be continuously learned. To this end, the emotion server 10 may perform deep learning learning of the emotion engine at any time and/or periodically through communication with the data crawler 40.

Product model evaluation based on deep learning determines whether a corresponding product is an item handled by this service through an image captured by a user, and specifically recognizes a model of a specific product group and transmits the result. The deep learning engine recognizes an object learned in an image, and can use open sources such as Google's tensorflow and yolo.

The primary product group classification as to whether it corresponds to an item handled by the product appraisal service can be determined by mounting a recognition engine in an appraisal application of the customer terminal 30. Through this, it is possible to reduce the load on the appraisal server 10 by determining within the appraisal application of the customer terminal 30 without proceeding to the appraisal server 10 for items other than the handling product group.

Thereafter, in order to classify the brand and the actual model, the captured image may be transmitted and determined by the artificial intelligence emotion engine of the emotion server 10. For example, as shown in FIG. 4A, the emotion application (mobile emotion app) stored in the customer terminal 30 performs product group classification and handling item classification, and then transmits a brand and model confirmation request to the emotion server 10 And, the brand and/or model information finally confirmed by this is returned from the appraisal server 10 and reported to the customer terminal 30, and/or transmitted to the service server 12, and then the subsequent process can be performed. have. For example, as shown in FIG. 4B, model information, such as a model name, a manufacturing year, a serial number, and a photograph, that can specify a model of an article may be displayed on the customer terminal 30.

Next, the appraisal server 10 may perform a genuine appraisal for determining whether the product in the image transmitted by the user is a genuine or a counterfeit of a corresponding model.

The emotion engine extracts a specific location or part (hereinafter referred to as a point part) that can determine the characteristics of the product from the image data transmitted by the user, and processes the image signal of the image data corresponding to the point part of the product. According to this model information, it is possible to determine whether it is a genuine product. The emotion engine may automatically extract and/or process and process a point portion of a corresponding model from image data transmitted by a user. In addition, for example, as shown in FIG. 5A, a button, buckle, and logo-marked portion of a bag corresponding to a specific model may be exemplified to the photographing user in advance so that the user can transmit an image photographed about the point portion.

For example, when the logo of the corresponding brand as shown in FIG. 5A is genuine, the ratio for each stroke and the aspect ratio of the logo size may be constant. The authenticity of such a logo can be determined by the following algorithm.

First, the Y value can be used in the YCbCr conversion equation (ITU-R BT.601) of Equation (1) below to obtain a gray image for the input image of FIG. 5A.

[Equation 1]

...(One)

The image for Y'in Equation (1) above is the same as the gray image of FIG. 5B.

Next, a bilateral filter for removing noise appearing in an image and sharpening a logo may be applied. Equations (2) and (3) below represent a bilateral filter.

[Equation 2]

...(2)

[Equation 3]

...(3)

In equation (2), I ^filtered (x) represents the resulting image, I represents the input image, and x represents the coordinates of the current pixel. Ω denotes the window size for filtering, and W _p denotes the difference in brightness and the weight for the spatial short distance.

Through this process, noise can be removed while maintaining the edge component having a large difference in brightness, and FIG. 5C shows the result.

Next, edge detection may be performed. Here, the Gaussian difference method can be used.

[Equation 4]

...(4)

It is possible to derive an edge component using the difference by varying the size of the two Gaussian filters. After that, contouring is performed on the detected edge component to find a bounding box of the logo portion as shown in FIG. 5D. For contouring, for example, a findContour of OpenCV, an image processing library, can be used. When the coordinates of the bounding box found as above are respectively p1 to p4, the length ratio of the width and height can be obtained to calculate the ratio information for the size of the logo. The length ratio θ can be calculated as follows.

[Equation 5]

...(5)

As shown in Equation (5), the width and height of the bounding box are calculated, and the ratio between them is calculated, and the authenticity can be determined by comparing the reference value for the authenticity and the ratio value calculated from the input image.

In addition to the above-described parts, the authenticity assessment may be performed by extracting various point parts that can be identified by an image, such as, for example, the shape or material of a specific part of the article, gloss or color, printed or engraved letters or numbers, and stitching status. Such a point portion may learn various image data through deep learning, and the emotion engine itself may automatically extract a specific portion of a specific item as a point portion.

On the other hand, even if the article is genuine, there is a risk that a judgment error may occur if the point portion extracted for authenticity determination is deformed due to damage, discoloration, etc. and affects emotion. For this reason, the emotion engine can collect a large amount of data for not only the genuine model but also the fake model and learn in advance through deep learning.

For example, since the manufacture of a fake product is often performed by a specific fake product manufacturer, models determined as a fake product may include a specific part in which the characteristics of the fake product manufacturer appear. By learning the image data including the shape or feature of a specific part of the fake product through deep learning, the emotion engine can determine whether it is a fake product by extracting a point part for determining whether it is a fake product model.

In addition, in some cases, fake parts are included in the genuine model due to replacement or repair of some parts. Accordingly, the appraisal engine performs both genuine and fake discrimination for the appraised item, and determines the result, for example, a genuine index indicating a degree of proximity to a genuine model and/or a degree of proximity to a counterfeit model. It can be displayed in the form of a displayed fake index. Such a genuine index and/or a fake index may be displayed in a form such as numbers, letters, percentages, etc. that the user can easily understand at a time. For example, the authenticity index may be displayed so that a score from 0 to 100 is assigned to the evaluation result, and a value closer to 100 indicates a real product, and a value closer to 0 indicates a false product. The same is true of the false goods index. Genuine or fake index can be displayed in the range of 0-10, and genuine 1 and fake are displayed in various forms, such as 0.

In addition, it goes without saying that a discrimination algorithm may be added and updated based on image signal processing and deep learning technology for various methods of distinguishing authentic products for each product.

After the genuine appraisal is completed, the appraisal server 10 may transmit the result of the genuine appraisal to the customer terminal 30 in advance. The appraisal server 10 may immediately perform a state appraisal of the appraised article without reporting the result of the appraisal of the authenticity.

The state emotion may be an emotion for determining at what level the storage state of the emotional article is. The storage condition of an article can be determined by a condition factor. Status factors include, for example, a replacement state indicating whether a specific part or part of an article has been replaced, a deformed state indicating whether it is deformed due to damage or damage, a contaminated state indicating contamination due to adhesion of foreign substances, etc., and discoloration or discoloration due to use. It may include a discoloration state indicating whether or not. Each article may include areas that are easily replaced, deformed, contaminated or discolored depending on the type of article or its model. The preservation state can be determined by extracting such a region as a point region for state evaluation.

State emotion can be executed by the emotion engine described above. As in genuine appraisal, the appraisal engine learns a large amount of video data according to the preservation status of the item and the point where it can be determined, by deep learning, and based on this, the preservation status of the item from the video data transmitted by the user. Can be identified. The learning data on the storage state of such articles may be data crawled from time to time and/or regularly through the data crawler 40, and based on this, continuous learning and evolution of the emotion engine may be performed.

The emotion engine may determine the state of the article through image signal processing by extracting and/or processing a point portion capable of determining the state of the article from the image data transmitted by the user. The emotion engine determines status factors such as replacement, deformation, contamination, and/or discoloration, based on the same algorithm as the image processing algorithm for determining authenticity, for each point part for status determination. Can be judged.

For example, like the brand logo of FIG. 5A, a specific part that frequently undergoes deformation may be extracted as a point part for determining whether or not it is deformed. The emotion engine may learn in advance a large amount of data on the deformation of the point portion and determine whether or not the emotion item is deformed based on this. For replacement, contamination, discoloration, etc., the corresponding point parts can be learned in advance by the emotion engine to determine the presence or absence. It goes without saying that various other image processing algorithms can be employed to determine the state.

The emotion engine may display the result in the form of a condition index indicating the storage state of the article after performing all state determination on the emotion article. This status index can be displayed in a form such as numbers, letters, percentages, etc. that the user can easily understand at a time. For example, if there is replacement, deformation, contamination, or discoloration in the point area, it may be marked as 1, and if not, it may be marked as 0.

In addition, the emotion engine learns a large amount of data in advance by dividing the replacement, deformation, contamination or discoloration of the point portion for state determination into "upper", "middle", and "lower", and replaces, transforms, and When the contamination or discoloration state is "top", "medium", and "bottom", it can be displayed in the form of scores of "1", "2", and "3", respectively. The emotion engine can also learn by subdividing the state of an article into three or more stages. In addition, it goes without saying that the score of the state index can be displayed in various ways, such as a range of 1 to 10 and a range of 1 to 100.

In the above, a two-dimensional discrimination technique based on photographs has been mainly described, but the emotion server 10 reconstructs image data such as photographs and videos taken by the user to obtain a virtual reality or augmented reality. The same three-dimensional model can be constructed. Thereby, a standardized 3D model can be constructed, and based on this, extraction of a point portion, a genuine feeling, a state feeling, etc. can be performed more accurately and easily. In addition, the emotion result may be three-dimensionally displayed in the form of augmented reality or the like on the 3D model. As a result, it is possible to easily recognize the state of the article, the result of the evaluation, and the like in a more realistic and intuitive manner.

Next, after completing the state evaluation, the emotion server 10 may determine an assessed value. The determination of the appraisal price may be executed by a big data-based price determination engine mounted in the appraisal server 10. The appraised value may be determined by the following appraised price calculation model.

Referring to FIG. 6, the price DB may include an article definition table and a price table. The article definition table may record and store IDs such as article names and article numbers according to the product group, brand, model, etc. of the emotional article. The price table may record and store the price according to the ID of each item as a product price.

The commodity prices recorded in the price table may be collected at any time and/or periodically from a price reference site designated in advance by a price DB operation agent. Product prices recorded in the price reference site and the price table may be automatically designated or updated by data crawling by the data crawler 40.

When there is no corresponding item on the designated or collected price reference site, the appraisal server 10 may notify the manager terminal 20 of a signal requesting registration of information for price determination by designating the ID of the corresponding item. When this request is notified, the manager may additionally register price information in the price table directly through the manager terminal 20. If the item is deleted from the designated or collected price reference site, you can designate the item from another site and add the designated site and the collected item to the price DB operation agent.

The product price recorded in the price table may be the highest price of the ID item collected from the price reference site. That is, the price of the item with the best preservation status can be specified as the price of the ID item. Alternatively, the average price of an average price of the ID item collected from a plurality of price reference sites may be recorded as the price of the ID item. That is, the item in the average storage state of the model can be specified by the price of the ID item.

The pricing engine may determine the appraised price based on these commodity prices and the state index described above.

For example, a constant weighting coefficient may be assigned to each of the factors representing the state of storage of the article, that is, the state of replacement, deformation, contamination, and discoloration. The weighting factor may be a factor representing a share of the price of the appraised article. By multiplying this weighting factor by the above-described condition index, it is possible to calculate a price discount rate indicating the degree of depreciation caused by the deterioration of the storage condition of the article. Therefore, the appraised value can be determined by the following subtraction method.

Assessed value = commodity price-(commodity price x weighting factor x status index)

For example, when the commodity price of an article is 1, a weighting factor of 0.4 for replacement, 0.3 for deformation, 0.2 for contamination, and 0.1 for discoloration can be given. When there is a replacement at the point portion of the article, for example, the state index becomes 1 and the weighting factor becomes 0.3, so the depreciation may be 0.3. Therefore, the appraised value may be determined as 1-(1x0.3x1)=0.7. That is, when there is a replacement for the product, 30% of the product price may be depreciated and 70% of the product price may be determined as the appraised price.

In addition, when there are a plurality of point regions for determining each state factor such as replacement or transformation, for example, a value obtained by dividing the weighting factor of the state factor by the total number of point regions for determining the state factor is sub-weighting factor And, by summing all the products of the sub-weighting factor and the state index for each point of the state factor, the product of the weighting factor of the state factor and the state index can be obtained.

Alternatively, the appraisal engine records the lowest or average price of the ID item collected from the price reference site as a commodity price in the price table, and if there is no item corresponding to the above-described depreciation or is good, the value corresponding to the depreciation is The appraisal value can also be determined by the addition method to be added.

In addition, the appraised value may be determined by reflecting the business cost or profit rate of the manager providing the goods appraisal service in the appraised price calculation.

According to the emotion system and the emotion method according to an embodiment of the present disclosure described above, an image of an article transmitted online by a user by an emotion server 10 equipped with an artificial intelligence based emotion engine learned and evolved through deep learning. Since the authenticity assessment is performed by performing image signal processing on the product, it is possible to provide a product assessment service capable of accurately and quickly discriminating whether the product is a genuine product of the corresponding model in a more scientific and standard way.

In addition, since the emotion engine learns not only the genuine data but also the fake data through deep learning, it performs both genuine product determination and false product determination, thereby providing a product appraisal service capable of performing more accurate authenticity determination.

In addition, the appraisal engine may provide a product appraisal service capable of distinguishing prices according to the preservation status of the goods by performing state determination to determine the storage status of the goods and calculating the status index.

In addition, the pricing engine not only determines the product price by collecting a large amount of information on the price of the product based on big data, but also calculates the depreciation of the product based on the state index calculated by the appraisal engine to discriminate according to the storage status of the product. You can calculate this possible appraised value. Accordingly, the user may be provided with a specific appraised value determined by more objective and consistent criteria according to the preservation status of the item for which the appraisal is requested.

The artificial intelligence appraisal system and the artificial intelligence appraisal method according to an embodiment of the present disclosure may be employed in various commerce and financial services such as online pawn shops, second-hand transactions, and mortgage loans, as well as appraisal services using mobile.

In one embodiment of the present disclosure, the artificial intelligence emotion system and the artificial intelligence emotion method are produced as a control logic or program including instructions executable by a computer such as a program module executed by a computer and recorded in a computer-readable recording medium. It can also be implemented in a form. The computer-readable recording medium may be any available medium that can be accessed by a computer, and may include both volatile and nonvolatile media, and removable and non-removable media. Also, the computer-readable recording medium may include a computer storage medium. Computer storage media may include both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The present disclosure is not limited only to the above-described embodiments, and various modifications and changes are possible by a person skilled in the art. In addition, each component or method described in each of the above-described embodiments, each application example, or a modified example thereof may be appropriately combined with each other or separately and implemented separately as necessary. Accordingly, the scope of the rights according to the present disclosure should be interpreted broadly to include all modifications and other embodiments including the technical configurations and their equivalents described in the following claims.

Claims

With the customer terminal,

Including an appraisal server that performs appraisal of the article based on the video data transmitted from the customer terminal through the network,

The emotion server includes an artificial intelligence-based emotion engine that has been trained to determine a model of the product by deep learning,

The emotion engine is an artificial intelligence emotion system that determines whether the product corresponds to a genuine product of the model by performing image signal processing on one or more point portions of the product.
The method of claim 1,

The emotion engine is an artificial intelligence emotion system that learns an image related to the fake product of the model by deep learning, and determines whether the product corresponds to the fake product of the model by performing image signal processing on one or more point portions of the product. .
The method of claim 1,

Artificial intelligence emotion system further comprising a data crawler for performing data crawling for deep learning learning of the emotion server.
The method of claim 1,

The emotion server constructs a three-dimensional model of the article from the image data using virtual reality or augmented reality, and extracts one or more point portions of the article from the three-dimensional model,

The emotion engine is an artificial intelligence emotion system that processes the image signal on the at least one point portion extracted from the 3D model.
The method of claim 1,

The emotion engine performs image signal processing for determining one or more status factors among replacement, deformation, contamination, and discoloration of one or more point portions of the article, and based on this, a status index for indicating the storage status of the article Artificial intelligence emotion system that determines the.
The method of claim 3,

The appraisal engine assigns a weighting factor to each of the one or more status factors, calculates a depreciation of the article by product of the status index and the weighting factor, and determines the appraised value of the article based on the depreciation. Artificial intelligence emotion system.
The method of claim 6,

The appraisal server registers the ID of the article according to the model of the article, and the artificial intelligence includes a big data-based price database that records the merchandise price obtained from a price reference site that provides price information of the article corresponding to the ID. Emotion system.
Including an appraisal server for appraising the article based on the video data of the article transmitted online through the network,

The emotion server,

A model assessment for determining a model of the article based on the image data transmitted online,

A genuine appraisal for determining whether the item corresponds to the genuine item of the model by performing image signal processing on one or more point portions of the item;

A state assessment of performing image signal processing for determining one or more factors among replacement, deformation, contamination, and discoloration of one or more point portions of the article, and determining a state index of the article based thereon,

An artificial intelligence appraisal method for performing appraisal determination for determining appraisal value of the article based on the state index.
The method of claim 8,

The appraisal server registers the ID of the article according to the model of the article, and the artificial intelligence includes a big data-based price database that records the merchandise price obtained from a price reference site that provides price information of the article corresponding to the ID. Emotion method.
A computer-readable recording medium on which a computer program for executing the artificial intelligence analysis method according to claim 8 is recorded.