KR102303862B1 - Online livestock auction device and method using artificial intelligence - Google Patents

Abstract

The present invention relates to an artificial intelligence-based online livestock auction device which excludes subjective decisions of people. The artificial intelligence-based online livestock auction device comprises: a data collection module collecting information on livestock, and receiving a photographing image of livestock for which an auction is requested from a seller terminal device; an entity identification and appraisal module identifying an entity by analyzing the photographing image of the livestock received by the data collection module, and appraising the identified entity; and an auction performing module providing bidding information including an explanation for the identified entity and an auction start price for a terminal device of a bidding candidate, and determining a successful bidder by referring to a bidding amount registered by a bidder terminal device. The entity identification and appraisal module uses the photographing image and an artificial intelligence-based image analysis model to calculate the weight of the identified entity, uses the photographing image and the artificial intelligence-based image analysis model to evaluate the appearance of the identified entity, and refers to the calculated weight and appearance evaluation results to appraise the identified entity.

Description

AI-based online livestock auction device and method {ONLINE LIVESTOCK AUCTION DEVICE AND METHOD USING ARTIFICIAL INTELLIGENCE}

The present invention relates to an on-line livestock auction apparatus and method using artificial intelligence.

In general, an online auction refers to an auction method or a communication service in which an auction procedure is conducted online using a communication resource such as the Internet, and the offline auction market is gradually moving to an electronic auction market.

As the number of epidemics caused by highly contagious viruses increases, it is time to change the way livestock auctions have been conducted only offline. Therefore, the livestock auction market such as Korean beef is also adopting an electronic auction method, and an online livestock auction platform that can be easily used by auction participants is required.

On the other hand, in the case of livestock auction, since a person performs livestock appraisal for auction, there is a disadvantage in that a somewhat subjective opinion is inevitably involved even if the livestock appraisal is performed according to the set examination conditions. Therefore, it is required to develop a system for objectively appraising livestock according to the examination conditions.

SUMMARY OF THE INVENTION It is an object of the present invention devised to solve the above problems to provide an artificial intelligence-based online livestock auction apparatus and method in which subjective judgment of a person is excluded.

Another object of the present invention is to provide an artificial intelligence-based online livestock auction apparatus and method for recognizing the face of livestock to identify an object.

Another object of the present invention is to provide an artificial intelligence-based online livestock auction apparatus and method in which health status information of an auction target is disclosed to auction participants to form a transparent auction market.

An artificial intelligence-based online livestock auction apparatus according to an embodiment of the present invention includes: a data collection module for collecting information on livestock and receiving a photographed image of a livestock subject to an auction request from a seller terminal device; an object identification and emotion module for analyzing the captured image of the livestock received by the data collection module to identify an object and appraise the identified object; and an auction performing module that provides bid information including a description of the identified entity and an auction start price to a terminal device of a bid candidate, and determines a successful bidder with reference to the bid amount registered by the bidder terminal device; and , the entity identification and emotion module calculates the weight of the identified entity using the captured image and an artificial intelligence-based image analysis model, and uses the captured image and the artificial function-based image analysis model to determine the identified entity examining the appearance, and the identified individual may be evaluated with reference to the calculated weight and the appearance examination result.

In addition, the entity identification and emotion module identifies the entity by analyzing the face of the entity identified in the captured image using an AI-based facial recognition model, and the AI-based facial recognition model uses a convolutional neural network It may be generated using at least one of a neural network (CNN), a deep neural network (DNN), and a recurrent neural network (RNN).

In addition, the entity identification and emotion module identifies the entity by analyzing the face of the entity identified in the captured image using an AI-based fingerprint recognition model, and the AI-based fingerprint recognition model uses a convolutional neural network (Convolutional Neural Network). It may be generated using at least one of a neural network (CNN), a deep neural network (DNN), and a recurrent neural network (RNN).

In addition, the entity identification and emotion module may evaluate the identified entity with further reference to pedigree information of the identified entity.

Also, the entity identification and emotion module may evaluate the identified entity with further reference to the health state information of the identified entity, and the health state information may be body information obtained through a blood test.

In addition, when the individual identification and evaluation module calculates and evaluates the value of the identified entity as an amount, the calculated amount is the auction start price, and when the value of the identified entity is calculated and evaluated as a score, the calculated score is The corresponding amount may be the auction start price.

Also, the captured image may be captured by a two-dimensional camera.

In addition, the description of the identified individual may include at least one or more of an image of the identified entity, an entity number, weight, length, body width, and information about a livestock house in which the identified entity is bred.

The display module may further include a display module for generating a screen for proceeding with the auction, and the screen generated by the display module may be displayed on a terminal device of an auction participant including a seller, a bid candidate, and a bidder.

An artificial intelligence-based online livestock auction method according to an embodiment of the present invention includes: receiving a photographed image of a livestock subject to an auction request from a seller terminal device; analyzing the received captured image of the livestock to identify an object; calculating the weight of the identified object by using the captured image and an AI-based image analysis model; examining the appearance of the identified entity using the captured image and the artificial function-based image analysis model; determining an auction start price by appraising the identified individual with reference to the calculated weight and appearance examination results; providing bidding information including a description of the identified entity and the auction start price to a terminal device of a bidding candidate; and determining a successful bidder with reference to the bid amount registered by the bidder terminal device.

In addition, the step of identifying the entity is performed by analyzing the face of the identified entity in the captured image using an AI-based facial recognition model, and the AI-based facial recognition model includes a convolutional neural network; CNN), a deep neural network (DNN), and a recurrent neural network (RNN) may be generated using at least one.

Also, the captured image may be captured by a two-dimensional camera.

According to the present invention, it is possible to provide an artificial intelligence-based online livestock auction apparatus and method in which subjective judgment of a person is excluded in appraisal of an auction target.

In addition, according to the present invention, it is possible to solve the problem of livestock management using the existing coupon by recognizing the face of the livestock to identify the individual.

In addition, according to the present invention, it is possible to form a transparent auction market by providing the health status information of the auction target to the auction participants.

1 is a diagram showing a schematic configuration of an entire system for providing an online auction service using artificial intelligence according to an embodiment of the present invention.
2 is a diagram illustrating an internal configuration of an online livestock auction apparatus according to an embodiment of the present invention.
3 is a view for explaining the appearance examination of an object performed by the object identification and emotion module according to an embodiment of the present invention.
4 is a diagram exemplarily showing that a screen generated by a display module according to an embodiment of the present invention is displayed on a terminal device of a seller.
5 is a flowchart illustrating a livestock auction procedure of the online livestock auction apparatus according to an embodiment of the present invention.
6 is a diagram illustrating a computing device according to an embodiment of the present invention.

Hereinafter, embodiments related to the present invention are illustrated in the drawings and will be described in detail through detailed description. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and should be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. .

In describing the components of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only for distinguishing the components from other components, and the essence, order, or order of the components are not limited by the terms. In addition, in this specification, when it is described that a component is “connected”, “coupled” or “connected” to another component, the component may be directly connected or connected to the other component, but each component It should be understood that another element may be “connected”, “coupled” or “connected” between elements. In the case of "connected", "coupled" or "connected", it is understood to be physically "connected", "coupled" or "connected" as well as electrically "connected", "coupled" or "connected" as needed. can be

Terms such as "~ unit (unit)", "~ group", "~ child", "~ module", etc. described in this specification mean a unit that processes at least one function or operation, which is hardware, software, or hardware and a combination of software. In addition, terms such as "comprises", "comprises" or "have" described in the present specification, unless otherwise stated, mean that the corresponding component may be embedded, so other components are excluded. Rather, it should be construed as being able to include other components further.

In addition, it is intended to clarify that the classification of the constituent parts in the present specification is merely a classification for each main function that each constituent unit is responsible for. That is, two or more components to be described below may be combined into one component, or one component may be divided into two or more for each more subdivided function. In addition, each of the constituent units to be described below may additionally perform some or all of the functions of other constituent units in addition to the main function it is responsible for. Of course, it may be carried out by being dedicated to it.

Hereinafter, an artificial intelligence-based online livestock auction apparatus and method according to an embodiment of the present invention will be described with reference to drawings related to embodiments of the present invention.

1 is a diagram showing a schematic configuration of an entire system for providing an online auction service using artificial intelligence according to an embodiment of the present invention.

As shown in FIG. 1 , the entire system according to an embodiment of the present invention may include a communication network 100 , an online livestock auction device 200 , and a user terminal device 300 .

First, the communication network 100 according to an embodiment of the present invention may be a high-speed backbone network of a large-scale communication network capable of data transmission/reception service, the Internet or Wi-Fi for providing a high-speed multimedia service, and It may be a next-generation wireless network including WiGig, WiBro (Wireless Broadband Internet, Wibro), and Wimax (World Interoperability for Microwave Access, Wimax).

The Internet includes the TCP/IP protocol and various services existing in its upper layers, namely HTTP (Hyper Text Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), It may mean a worldwide open computer network structure that provides Simple Network Management Protocol (SNMP), Network File Service (NFS), Network Information Service (NIS), etc., and the user terminal device 300 is an online livestock auction device 200 ) can be provided.

Meanwhile, the Internet may be a wired or wireless Internet, or may be a core network integrated with a wired public network, a wireless mobile communication network, or a portable Internet.

If the communication network 100 is a mobile communication network, it may be a synchronous mobile communication network or an asynchronous mobile communication network. As an embodiment of the asynchronous mobile communication network, a wideband code division multiple access (WCDMA) type communication network may be used. In this case, although not shown in the drawings, the mobile communication network may include, for example, a Radio Network Controller (RNC). Meanwhile, although the WCDMA network is taken as an example, it may be a next-generation communication network such as a 3G LTE network, a 4G network, or a 5G network, or other IP-based IP networks.

Next, the online livestock auction apparatus 200 according to an embodiment of the present invention identifies an object from a photograph of livestock, evaluates the identified object for auction, and provides the information to the seller and the bidder, and at least one or more It is possible to perform a function of performing an auction procedure for the identified entity, such as receiving information on a bid amount from a bidder and determining a successful bidder based on the information. A detailed configuration and function of the online livestock auction apparatus 200 according to the present invention will be described in detail below.

On the other hand, the user terminal device 300 according to an embodiment of the present invention is a digital device including a function for communicating after accessing the online livestock auction device 200 and a display function for outputting an image or text. , a desktop computer, a notebook computer, a workstation, a PDA, a web pad, a mobile phone (smartphone), etc., any digital device equipped with a memory means and equipped with a microprocessor and equipped with computing power, the user terminal device ( 300) can be adopted.

Herein, the user may be selected from among an auction participant including a bid candidate who wants to participate in the online livestock auction, a bidder who participates in the auction to receive a successful bid for the auction object, and a seller who wants to sell the auction object, and an auction manager of the online livestock auction device 200 . It may include at least one.

The user may access the online livestock auction device 200 through the user terminal device 300 , and may participate in the livestock auction by checking information on an auction target or presenting a bid amount. To this end, the user terminal device 300 may include a browser-related program or application for receiving a user interface from the online livestock auction device 200 .

Meanwhile, in the present invention, livestock is preferably an animal that provides livestock products, and may include, for example, horses, cattle, goats, pigs, etc., and may also include poultry other than mammals. However, the present invention is not limited thereto, and may include animals that do not provide livestock products if they can be auctioned off. Hereinafter, for convenience of explanation, it will be described that mainly livestock is a calf as an example.

Hereinafter, the internal configuration of the online livestock auction apparatus 200 according to the present invention and the function of each component will be described.

2 is a diagram illustrating an internal configuration of an online livestock auction apparatus according to an embodiment of the present invention.

Referring to FIG. 2 , the online livestock auction apparatus 200 according to an embodiment of the present invention includes a data collection module 210 , an entity identification and appraisal module 220 , an auction execution module 230 , and a display module 240 . ), a database 260 , a communication module 270 and a control module 280 . Here, the data collection module 210 , the event result prediction module 220 , the user interface providing module 230 , the user information management module 230 , the database 260 , the communication module 270 and the control module 280 are Not all of them have to be physically included in one server, and some components may be located outside that interworks with the server.

Meanwhile, according to an embodiment of the present invention, the data collection module 210 , the entity identification and emotion module 220 , the auction execution module 230 , the display module 240 , the database 260 , and the communication module 270 . and the control module 280 may be a program module, at least a part of which communicates with the user terminal device 300 . Such a program module may be included in the online livestock auction apparatus 200 in the form of an operating system, an application program module, or other program modules, and may be physically stored in various known storage devices. Also, such a program module may be stored in a remote storage device capable of communicating with at least one of the user terminal devices 300 . Meanwhile, such a program module includes, but is not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types according to the present invention.

First, the data collection module 210 may perform a function of collecting information on livestock to be auctioned and storing it in the database 260 . Here, the information on livestock may include images of individual individuals, identification information for individual individuals, date of birth, ancestry, health care/status information, disease history, feed provided, immune agents provided, information about livestock, etc., and the data The information collected by the collection module 210 may be computerized information on livestock managed by the livestock house.

In addition, the data collection module 210 may collect computerized data such as medical records from a hospital server and the like to collect medical treatment or treatment information of livestock. The livestock medical treatment or treatment information may include a veterinarian visit record, telemedicine record, treatment record, etc., and may also include information related to administration of various drugs such as vaccine or antibiotic administration, such as administered vaccine, drug type, inoculation date, etc. .

Meanwhile, the information collected by the data collection module 210 may include the body temperature of the livestock measured by the capsule and the biometric information received from the laboratory. Here, the biometric information received from the laboratory may be obtained by collecting blood, feces, semen, and the like from livestock and analyzing and requesting the laboratory.

The data collection module 210 may collect livestock images, and the livestock images may be livestock images captured by a seller who wants to sell livestock through an online auction.

The information collected by the data collection module 210 is stored and managed in the database 260 , and information about the object and the corresponding object may be matched and managed. Accordingly, when the entity identification and emotion module 220, which will be described later, recognizes the face of the livestock included in the image to identify the entity, it can match the identified entity and provide stored information to the auction participants.

Next, the entity identification and emotion module 220 may analyze the image of the livestock to identify the entity and perform a function of appreciating the identified entity.

According to an embodiment of the present invention, the entity identification and emotion module 220 may identify an entity using a facial recognition model based on artificial intelligence.

Artificial intelligence is a field of computer science and information technology that studies how computers can do the thinking, learning, and self-development that human intelligence can do. can mean doing Machine learning, also called machine learning, can be a technology that enables a computer to learn from data and understand a certain object or situation like a human. Algorithms that enable computers to analyze data in a technical way that learns to find and classify patterns may be key. By making sophisticated algorithms that use data, the computer can learn and provide meaningful results to users. Deep learning, one of the technologies that implements machine learning, discovers patterns in data, predicts through classification, and is based on artificial neural networks, just like humans classify objects.

In the present specification, the face recognition model is generated using any one of a convolutional neural network (CNN), a deep neural network (DNN), and a recurrent neural network (RNN), or a convolution It may be generated by combining at least two or more of a neural network, a deep neural network, and a recurrent neural network, and an object feature may be extracted from the image collected by the data collection module 210 .

The object identification and emotion module 220 compares the features extracted by the facial recognition model with pre-registered data using a clustering model such as a K-means algorithm using Euclidean distance to identify the object of the image. can be identified. The K-means algorithm is an algorithm that groups the given data into K clusters, and can operate in a manner that minimizes the variance of each cluster and distance difference. Specifically, the K-means algorithm algorithm can take K center points, then find the location of K where the sum of the distances between each feature data vector is minimized at the center points, and cluster them based on points close to the center points.

On the other hand, when the livestock is a cow (or calf), not only the method of using an AI-based facial recognition model, but also the AI-based inscription recognition model can be used to identify an object.

The non-print recognition model may be generated using any one of a convolutional neural network, a deep neural network, and a recurrent neural network, or may be generated by combining at least two or more of a convolutional neural network, a deep neural network, and a recurrent neural network, and a data collection module In 210 , the characteristics of the object may be extracted from the collected image.

The object identification and emotion module 220 uses a clustering model such as a K-means algorithm using Euclidean distance to compare the features extracted by the non-print recognition model with pre-registered data to identify the object of the image. can be identified.

Conventionally, an ear mark, an ear mark (tag), was used to identify an individual of a livestock that is difficult to distinguish with the naked eye, such as a hair color or a mark, and to manage the history of the livestock. However, when using the livestock management system using these coupons, there is a disadvantage in that it consumes a lot of manpower and cost to manage and maintain the coupons. It is becoming. In addition, management loopholes due to illegal use of coupons, such as reusing coupons, are being raised.

According to an embodiment of the present invention, since an entity is identified through a recognition model generated based on artificial intelligence and a facial image of a livestock included in the image, all problems of the livestock management system using this mark can be solved.

When the object identification is completed by analyzing the image of the livestock, the object identification and emotion module 220 may analyze the image to calculate the weight of the identified object.

The entity identification and emotion module 220 may estimate at least one of a body width, height, and weight of an entity by analyzing an image using an AI-based image analysis model.

An image analysis model according to an embodiment of the present invention is generated using any one of a convolutional neural network (CNN), a deep neural network (DNN), and a recurrent neural network (RNN). Or, it may be generated by combining at least two or more of a convolutional neural network, a deep neural network, and a recurrent neural network, and extracts the features of the object from the image collected by the data collection module 210 to detect the area where the object is displayed in the image can do.

The entity identification and emotion module 220 derives keypoints for a specific location using an image keypoint detection algorithm, calculates the distance between the keypoints, and calculates at least one of the body width, length, and weight of the object. can

On the other hand, the image used for facial recognition, weight measurement, etc. of the livestock may be an image captured by a two-dimensional camera. Although it is common to estimate the weight of an object in an image by using an image captured by a three-dimensional camera, the online livestock auction apparatus according to the present invention uses an image captured by a two-dimensional camera, so the device dependency is low when the technology is applied. It has the advantage of easy accessibility for users who want to use the system, can increase data processing speed, and can reduce data processing costs.

The object identification and emotion module 220 may analyze the image to examine the appearance of the object, and the appearance examination result may be used to determine an auction start price for the object.

Here, the object appearance examination items may include height, body length, body line, coat color, etc., and the examination items may be set differently for each kind of livestock. For example, if the livestock to be auctioned is cattle (or calves), the appearance evaluation items are height, length, width, body height, coat color, contour, shin thickness, chest width, shoulder attachment, rib opening, It may include the upper body line, the lower body line, the hip tilt, the hip length, the ischial width, the breast volume, the hoof angle, the hind leg hock tilt, the hind leg posture, and the like.

The individual identification and emotion module 220 may give a higher score as the height, length, width, and body height are larger, give a lower score, and give a higher score as the coat color is darker. Hereinafter, a method in which the object identification and emotion module 220 analyzes an image to examine the appearance of an object will be described in detail with reference to FIG. 3 .

3 is a view for explaining the appearance examination of an object performed by the object identification and emotion module according to an embodiment of the present invention.

When the livestock to be auctioned is a cow (or calf), the object identification and analysis module 220 takes an image of the object's hoof as shown in FIG. 3 in order to increase the hoof angle among the plurality of appearance examination items can be analyzed. The entity identification and emotion module 220 may derive the feature points from the image and calculate the angles of lines connecting the feature points in order to calculate the hoof angle of the object through the angle between the slope of the horned hoof and the ground.

The entity identification and emotion module 220 gives a higher score as the hoof angle is larger as shown in (a) of FIG. 3, and a lower score is given as the hoof angle is smaller as shown in (b). .

The entity identification and emotion module 220 calculates the length, angle, etc. corresponding to each item using the above-described AI-based image analysis model and image feature point detection algorithm, and examines the appearance of the entity using the calculated values. have.

The entity identification and evaluation module 220 may evaluate the identified entity in order to determine the economic value of the identified entity, and may evaluate the identified entity with reference to the calculated weight information and the appearance evaluation result. When the entity identification and evaluation module 220 calculates and evaluates the value of the identified entity as an amount, the calculated amount (appraisal value) may be the auction start price, and the entity identification and evaluation module 220 determines the value of the identified entity. In the case of appraisal by calculating the value as a score, the price corresponding to the calculated score may be the starting price of the auction.

Alternatively, the entity identification and emotion module 220 may evaluate the identified entity in consideration of not only the weight and appearance examination results of the identified entity, but also pedigree information of the identified entity.

Alternatively, the entity identification and evaluation module 220 may evaluate the identified entity by further considering not only the weight and appearance examination results of the identified entity, but also health status information of the identified entity, for example, internal data obtained through a blood test. may be Health state information of the identified entity may be obtained from the database 260 .

Meanwhile, when the entity identification and evaluation module 220 does not consider health state information in appraising the identified entity, health state information matched to the identified entity may be provided to the auction participant at the start of the auction.

In this case, since the value of the object is evaluated by considering all the specific information indicating the health status of the object to be auctioned, the accuracy and objectivity of emotion can be increased. In addition, even if health status information is not reflected in the appraisal, it is possible to form a transparent auction market by disclosing it to auction participants such as bidders. In addition, according to the embodiment of the present invention, since the auction target is evaluated by excluding the subjective judgment of a person, an honest and sound livestock auction market can be formed.

Next, the auction performing module 230 provides the bidding candidate with bidding information including the description of the identified entity and the auction start price to the bidding candidate, and determines a successful bidder with reference to the bid amount suggested by the bidders. can be performed.

The information of the auction target includes an image of the auction target, identification information (eg, individual number) of the auction target, age or month of the auction target, and external appearance information (eg, body length, width, height) of the auction target. etc.), information on the livestock to which the individual is shipped, the evaluation result calculated with reference to the weight and appearance examination results of the individual, the auction start price, and the like.

The display module 240, which will be described later, may generate a screen on which auction-related information is displayed, and the generated screen is provided to and displayed on the terminal device 300 of a user including an auction manager, a bid candidate, and a seller who sells an auction object. can be The bid candidates may register the bid amount by checking the information on the auction target displayed on the terminal device, determining whether to participate in the bid, and inputting the bid amount into the terminal device.

The auction performing module 230 may determine a bid candidate who has offered a bid amount as a bidder, and collect information about the bidder and information on the bid amount. Here, all bid amounts may be displayed on the terminal device of the seller as well as the auction manager.

The auction performing module 230 may determine a successful bidder by referring to the bid amount received from the bidder's terminal device 300 , and if there are multiple bidders, compare the bid amounts to determine the successful bidder. For example, the auction performing module 230 may determine a bidder who has registered the highest bid price as a successful bidder.

Hereinafter, specific functions of the display module 240 will be described with reference to FIG. 4 .

4 is a diagram exemplarily showing that a screen generated by a display module according to an embodiment of the present invention is displayed on a terminal device of a seller.

The display module 240 may perform a function of generating a screen for the auction proceeding, and the screen generated by the display module 240 may be provided to the user terminal device 300 by the display module 240 , Alternatively, it may be provided by the auction performing module 230 .

When a seller requests an online auction from the online livestock auction device 200 by transmitting an image of a livestock to be sold through an online auction using a terminal device to the online livestock auction device 200, the data collection module 210 This livestock photographed image is collected, the object identification and appraisal module 220 identifies the livestock requested for auction, and when the evaluation of the identified object through the above-described series of processes is finished, the online auction starts.

To this end, the display module 240 may generate a screen enabling the seller to participate in the online auction and transmit an image of the livestock to be sold to the online livestock auction device 200 .

When the online auction for the identified entity starts, the display module 240, as shown in FIG. 4, includes a livestock image display area 410, an information display area 420, and a bid information display area 430. You can create a screen.

The livestock image display area 410 may display an image of the object to be auctioned as taken by the seller, and information on the object to be auctioned in the information display area 420 , for example, object number, height, length, body width, etc. Appearance information of the same individual, the weight of the individual, the result of appearance examination, the age or age of the individual, information about the individual shipment and livestock may be displayed. In the bid information display area 430 , information on a bidder and a bid amount registered by the bidder may be displayed.

Although not shown in FIG. 4 , the display module 240 may generate a screen to be provided to a bid candidate or a bidder's terminal device, and the screen includes a livestock image display area 410 and an information display area 420 and In the same area, an area allowing a bidding candidate to participate in an auction and register a bid amount may be further included.

In addition, the display module 240 may generate a screen to be provided to the terminal device of the auction manager, and may include an area for displaying all information displayed on the terminal device of the seller, the bid candidate, and the bidder.

Next, the database 260 according to an embodiment of the present invention includes a plurality of livestock and identification information corresponding to each of the livestock, face recognition information for each livestock, inscription information for each cattle when the livestock is a cattle, each livestock It is possible to store and manage information necessary for online livestock auction, such as appearance information and health information.

Although the database 260 is illustrated as one in FIG. 2 , the database 260 may be divided into a plurality of databases according to the needs of those skilled in the art for implementing the present invention.

Meanwhile, the database 260 in the present invention is a concept including a computer-readable recording medium, and may be a database in a broad sense including not only a narrow database but also a file system-based data record, and a simple log Even a set can be the database 260 in the present invention if data can be extracted by searching for it.

Next, the communication module 270 according to an embodiment of the present invention includes the data collection module 210 , the entity identification and emotion module 220 , the auction execution module 230 , the display module 240 , and the database 260 . and data transmission/reception to/from the control module 280 or a function of enabling communication between the user terminal device 300 and the online livestock auction device 200 .

Finally, the control module 280 according to an embodiment of the present invention includes a data collection module 210 , an entity identification and emotion module 220 , an auction execution module 230 , a display module 240 , and a database 260 . and controlling the flow of data between the communication modules 270 . That is, the control module 280 according to the present invention controls the data flow to/from the outside of the online livestock auction device 200 or the data flow between each component of the online livestock auction device 200 , so that the data collection module ( 210 ), the entity identification and emotion module 220 , the auction execution module 230 , the display module 240 , the database 260 , and the communication module 270 may control each to perform a unique function.

5 is a flowchart illustrating a livestock auction procedure of the online livestock auction apparatus according to an embodiment of the present invention.

First, when the seller terminal device requests an auction of the livestock while transmitting the photographed image of the livestock to be sold, the data collection module 210 may collect the transmitted livestock image ( S510 ).

Next, the object identification and emotion module 220 may identify the object by recognizing the face of the livestock that is the target of the auction request or by recognizing the inscription ( S520 ). The object identification and emotion module 220 extracts features of an object using an artificial intelligence-based facial recognition model or a non-print recognition model, and identifies the object by comparing the extracted features and pre-registered data using a clustering model. can

Next, the entity identification and evaluation module 220 evaluates the identified entity with reference to the weight and appearance examination result information of the identified entity ( S530 ). To this end, the entity identification and emotion module 220 may calculate a weight from the livestock image collected by the data collection module 210 and examine the appearance.

The object identification and emotion module 220 detects an area in which an object is displayed in an image using an artificial intelligence-based image analysis model, derives feature points using a feature point detection algorithm, calculates the distance, angle, etc. between the feature points to calculate the object It is possible to calculate the body weight and the numerical values necessary for the appearance examination, for example, body width and length.

Next, the auction performing module 230 may provide bidding information, that is, information on the identified object to be auctioned and the auction start price, to the terminal device of the auction participant so that the bidding candidates can participate in the auction for the identified object. There is (S540).

The information on the identified entity may include an image of the identified entity, an entity number, the age or age of the identified entity, weight, an appearance examination result, health status information, and the like.

Finally, the auction performing module 230 may determine a successful bidder of the auction by comparing the bid amount registered through the terminal device while the bidder participates in the bidding ( S550 ).

6 is a diagram illustrating a computing device according to an embodiment of the present invention. The computing device TN100 of FIG. 6 may be a device described herein (eg, the online livestock auction device 200 , the user terminal device 300 , etc.).

In the embodiment of FIG. 6 , the computing device TN100 may include at least one processor TN110 , a transceiver device TN120 , and a memory TN130 . Also, the computing device TN100 may further include a storage device TN140 , an input interface device TN150 , an output interface device TN160 , and the like. Components included in the computing device TN100 may be connected by a bus TN170 to communicate with each other.

The processor TN110 may execute a program command stored in at least one of the memory TN130 and the storage device TN140. The processor TN110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to an embodiment of the present invention are performed. The processor TN110 may be configured to implement procedures, functions, and methods described in connection with an embodiment of the present invention. The processor TN110 may control each component of the computing device TN100 .

Each of the memory TN130 and the storage device TN140 may store various information related to the operation of the processor TN110 . Each of the memory TN130 and the storage device TN140 may be configured as at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory TN130 may include at least one of a read only memory (ROM) and a random access memory (RAM).

The transceiver TN120 may transmit or receive a wired signal or a wireless signal. The transceiver TN120 may be connected to a network to perform communication.

Those of ordinary skill in the art to which the present invention pertains will understand that the present invention may be embodied in other specific forms without changing the technical spirit or essential features thereof. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The scope of the present invention is indicated by the claims described below rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts are included in the scope of the present invention. should be interpreted

100: communication network 200: online livestock auction device
300: user terminal device 210: data collection module
220: entity identification and appraisal module 230: auction execution module
240: display module 260: database
270: communication module 280: control module

Claims (7)

a data collection module that collects information on livestock and receives a photographed image of livestock that is an auction request target from a seller terminal device;
an object identification and emotion module for analyzing the captured image of the livestock received by the data collection module to identify an object and appraise the identified object;
an auction performing module that provides bid information including a description of the identified entity and an auction start price to a terminal device of a bid candidate, and determines a successful bidder with reference to the bid amount registered by the bidder terminal device; and
a display module for generating a screen enabling the seller to transmit the photographed image of the livestock and providing it to the seller terminal device; includes,
The entity identification and emotion module,
Calculating the weight of the identified individual using the captured image and an artificial intelligence-based image analysis model,
Using the artificial intelligence-based image analysis model and image feature point detection algorithm, a plurality of feature points are derived from the captured image of the livestock, and the distance between the feature points and the angle between lines connecting the feature points are calculated to determine the identified entity examine the appearance of
Evaluate the identified individual with reference to the calculated weight and appearance examination results,
Identifies the object by analyzing the object's face in the captured image of the livestock using an artificial intelligence-based facial recognition model,
The auction start price is determined based on the calculated weight and the evaluation result of the appearance,
An artificial intelligence-based online livestock auction device in which the photographed image of the livestock is taken with a two-dimensional camera. According to claim 1,
The artificial intelligence-based face recognition model is generated using at least one of a convolutional neural network (CNN), a deep neural network (DNN), and a recurrent neural network (RNN). An artificial intelligence-based online livestock auction device. According to claim 1,
The entity identification and emotion module,
An artificial intelligence-based online livestock auction apparatus for appraising the identified entity by further referring to the pedigree information or health status information of the identified entity. According to claim 1,
The entity identification and emotion module,
Evaluate the identified entity with further reference to the health status information of the identified entity,
The health status information is an artificial intelligence-based online livestock auction device that is body information obtained through a blood test. According to claim 1,
When the individual identification and evaluation module calculates and evaluates the value of the identified entity as an amount, the calculated amount is the auction start price, and when the value of the identified entity is calculated and evaluated as a score, corresponding to the calculated score An artificial intelligence-based online livestock auction device in which the amount is the auction starting price. According to claim 1,
The description of the identified entity is an artificial intelligence-based online livestock auction device including at least one of an image of the identified entity, entity number, weight, height, body width, and information on the livestock house in which the identified entity was bred. . An artificial intelligence-based online livestock auction method using an artificial intelligence-based online livestock auction device including a data collection module, an object identification and emotion module, an auction execution module, and a display module, the method comprising:
generating, by the display module, a screen for transmitting a photographed image of a livestock subject to an auction request, and providing it to a seller terminal device;
receiving, by the data collection module, the photographed image of the livestock from the seller terminal device;
analyzing, by the entity identification and emotion module, the captured image of the livestock to identify the entity;
calculating, by the entity identification and emotion module, the weight of the identified entity using the captured image and an AI-based image analysis model;
The entity identification and emotion module derives a plurality of feature points from the captured image of the livestock using the artificial intelligence-based image analysis model and image feature point detection algorithm, and the distance between the feature points and the lines connecting the feature points examining the appearance of the identified object by calculating an angle;
determining, by the auction performing module, an auction start price by appraising the identified entity with reference to the calculated weight and appearance evaluation results;
providing, by the auction performing module, bidding information including a description of the identified entity and the auction start price to a terminal device of a bidding candidate; and
determining, by the auction performing module, a successful bidder with reference to the bid amount registered by the bidder terminal device; including,
The step of identifying the object is performed by analyzing the face of the identified object in the captured image using an artificial intelligence-based facial recognition model,
The auction start price is determined based on the calculated weight and the evaluation result of the appearance,
An artificial intelligence-based online livestock auction method in which the photographed image of the livestock is taken with a two-dimensional camera.

Images