System and method for automatically processing meat through image analysis

Abstract

An automated meat processing system and method through image analysis are provided. An automated meat processing method through image analysis according to various embodiments of the present invention comprises, in a method performed through a meat processing system, the steps of transporting meat to be processed, processing the transported meat, performing image analysis on an image including the processed meat, and packaging the processed meat based on the result of the performed image analysis.

Description

Technology Field

[0001] Various embodiments of the present invention relate to a system and method for automated meat processing through image analysis, and more specifically, to a system and method for automated meat processing through image analysis that enables meat to be processed and packaged more efficiently by automatically processing and packaging meat or by providing a guide for processing and packaging meat through image analysis. Background Technology

[0002] Processing various types of meat, such as beef, pork, chicken, duck, goat, and lamb, involves a series of processes including extracting only the necessary parts, removing unnecessary parts, tenderizing the meat, removing the characteristic smell of meat, and freezing the processed meat.

[0003] In other words, the meat processing process can be defined as the process of deboning, which involves locating and cutting the joints between the flesh and bones of slaughtered meat, and trimming, which involves removing unnecessary parts such as fat to process the meat into a product, followed by packaging and delivery to consumers.

[0004] Meanwhile, since the marketability of meat is determined by the deboning and trimming methods, as well as the storage methods after deboning and trimming, processing meat more quickly and accurately is a very important factor. However, existing general meat-related technologies have focused only on the processing techniques themselves, such as improving meat quality and removing meat odors, and there is a problem in that technologies for processing meat more effectively and the working environment of the workers who actually process the meat have been neglected. Prior art literature

[0005] Korean Registered Patent No. 10-2254656 (May 21, 2021) The problem to be solved

[0006] The problem that the present invention aims to solve is to provide an automated meat processing method system and method through image analysis, which enables more accurate and efficient meat processing procedures by automatically performing a series of processes related to meat processing, such as transporting, processing, and packaging meat, or by guiding workers to perform these processes more easily, with the purpose of resolving the aforementioned conventional problems.

[0007] Another problem that the present invention aims to solve is to provide an automated meat processing method system and method through image analysis that derives processing information about meat through image analysis based on a pre-trained artificial intelligence model, and guides workers to process meat automatically or more easily based on this information, thereby enabling more accurate and efficient meat processing as well as allowing workers with little experience in meat processing to process meat more easily.

[0008] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0009] An automated meat processing method through image analysis according to an embodiment of the present invention for solving the above-mentioned problem may include, in a method performed through a meat processing system, a step of transporting meat to be processed, a step of processing the transported meat, a step of performing image analysis on an image including the processed meat, and a step of packaging the processed meat based on the result of the performed image analysis.

[0010] In various embodiments, the step of performing the image analysis includes the step of acquiring an image generated by photographing the processed meat and the step of determining the attributes of the processed meat by analyzing the acquired image based on an image analysis model, wherein the determined attributes may include at least one of the type, size, and grade of the processed meat.

[0011] In various embodiments, the step of packaging the processed meat may include the step of issuing a sticker containing information regarding the determined attribute and the step of attaching the issued sticker to the packaged meat.

[0012] In various embodiments, the step of packaging the processed meat may include the step of determining a packaging method of the processed meat based on the determined attribute and the step of packaging the processed meat based on the determined packaging method.

[0013] In various embodiments, the step of determining the attributes of the processed meat may include the step of extracting a plurality of features by analyzing a plurality of images having different resolutions for the processed meat, and the step of determining the attributes of the processed meat based on the extracted plurality of features.

[0014] In various embodiments, the step of processing the transported meat may include the step of acquiring a meat image generated by photographing the meat to be processed through a camera module included in the meat processing module of the meat processing system, the step of deriving processing information of the transported meat by analyzing the generated meat image, and the step of processing the transported meat based on the derived processing information.

[0015] In various embodiments, the step of deriving processing information includes the step of extracting reference points by analyzing the acquired meat image based on a previously trained artificial intelligence model, and the step of setting the cutting portion and cutting line of the transported meat as processing information for the transported meat using the extracted reference points. The step of setting the cutting portion and cutting line of the transported meat may include, when a plurality of reference points are extracted from the acquired meat image, the step of selecting at least one reference point among the plurality of extracted reference points based on the attributes of the transported meat—the attributes of the transported meat include at least one of the type, size, use, part to be extracted, part to be removed, and grade of the transported meat—and the step of setting the cutting portion and cutting line of the transported meat using the selected at least one reference point.

[0016] In various embodiments, the derived processing information includes information regarding the cutting area and cutting line of the transported meat and information regarding the cutting method of the transported meat, and the step of processing the transported meat based on the derived processing information includes the step of marking the cutting area and cutting line on the transported meat by irradiating a laser onto the transported meat through a laser irradiation module included in the meat processing module or spraying an edible marker onto the transported meat through an edible marker spraying module included in the meat processing module, and the step of marking the cutting area and cutting line on the transported meat may include the step of determining the attribute of a line corresponding to the cutting line—the attribute of the line includes at least one of the type, size, and grade of the transported meat and the cutting method—and the step of marking a line corresponding to the determined attribute on the transported meat.

[0017] Other specific details of the present invention are included in the detailed description and drawings. Effects of the invention

[0018] According to various embodiments of the present invention, there is an advantage in that a more accurate and efficient meat processing procedure can be performed by automatically carrying out a series of processes related to meat processing, such as transporting, processing, and packaging meat, or by guiding workers to perform processes related to meat processing more easily.

[0019] In addition, by deriving processing information for meat through image analysis based on a pre-trained artificial intelligence model and guiding workers to process meat automatically or more easily based on this information, there is an advantage in that not only can meat be processed more accurately and efficiently, but an environment can also be provided where even workers with little experience in meat processing can process meat more easily.

[0020] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0021] FIG. 1 is a diagram illustrating a system providing an automated meat processing method service through image analysis according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating the components of a meat processing system according to another embodiment of the present invention. FIGS. 3 and 4 are exemplary drawings illustrating a meat cutting module implemented in the form of a robot arm in various embodiments. FIG. 5 is a diagram illustrating, in various embodiments, an auxiliary arm of a meat cutting module being inserted into the cutting portion of meat to open the cutting portion. FIG. 6 is a drawing illustrating an exemplary shape of an auxiliary arm applicable to various embodiments. FIG. 7 is a flowchart of an automated meat processing method through image analysis according to another embodiment of the present invention. FIG. 8 is a hardware configuration diagram of a computing device included in a meat processing system in various embodiments. Specific details for implementing the invention

[0022] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims.

[0023] The terms used herein are for describing the embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components in addition to the components mentioned.

[0024] Throughout this specification, the same reference numerals refer to the same components, and "and / or" includes each of the mentioned components and all combinations of one or more thereof. Although terms such as "first," "second," etc., are used to describe various components, they are not limited by these terms. These terms are used merely to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the scope of the technical concept of the present invention.

[0025] As used herein, the terms “part” or “module” refer to hardware components such as software, FPGAs, or ASICs, and the “part” or “module” performs certain roles. However, the “part” or “module” is not limited to software or hardware. The “part” or “module” may be configured to reside in an addressable storage medium or configured to run on one or more processors. Thus, by example, the “part” or “module” includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and “parts” or “modules” may be combined into a smaller number of components and “parts” or “modules,” or further separated into additional components and “parts” or “modules.”

[0026] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to facilitate the description of the relationship between one component and other components as illustrated in the drawings. Spatially relative terms should be understood as encompassing different orientations of components during use or operation, in addition to the orientations depicted in the drawings. For example, if a component depicted in a drawing is inverted, a component described as "below" or "beneath" of another component may be placed "above" of that component. Therefore, the exemplary term "below" may encompass both the lower and upper directions. Components may also be oriented in other directions, and accordingly, spatially relative terms may be interpreted according to the orientation.

[0027] Expressions such as "first," "second," or "first," "second" as used in this specification are used to distinguish one object from another when referring to a plurality of objects of the same kind, unless otherwise indicated by the context, and do not limit the order or importance of said objects.

[0028] Expressions used herein such as “A, B, and C,” “A, B, or C,” “A, B, and / or C,” or “at least one of A, B, and C,” “at least one of A, B, or C,” “at least one of A, B, and / or C,” “at least one selected from A, B, and C,” “at least one selected from A, B, or C,” “at least one selected from A, B, and / or C,” etc., may mean each of the listed items or all possible combinations of the listed items. For example, “at least one selected from A and B” may refer to (1) A, (2) at least one of A, (3) B, (4) at least one of B, (5) at least one of A and at least one of B, (6) at least one of A and B, (7) at least one of B and A, and (8) all of A and B.

[0029] As used herein, the expression “based on” is used to describe one or more factors affecting an act or action of a decision or judgment described in the phrase or sentence containing such expression, and such expression does not exclude additional factors affecting said act or action of a decision or judgment.

[0030] As used in this specification, the expression that a certain component (e.g., a first component) is "connected" or "connected" to another component (e.g., a second component) may mean that the said certain component is not only directly connected or connected to the said other component, but is also connected or connected through a new other component (e.g., a third component).

[0031] As used herein, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," or "capable of." Such expression is not limited to the meaning of "specifically designed in hardware," and, for example, a processor configured to perform a specific operation may mean a generic-purpose processor capable of performing that specific operation by executing software.

[0032] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0033] In this specification, the term "computer" refers to any type of hardware device comprising at least one processor, and may be understood to include software configurations operating on said hardware device according to the embodiments. For example, the term "computer" may be understood to include smartphones, tablet PCs, desktops, laptops, and user clients and applications running on each of these devices, but is not limited thereto.

[0034] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0035] Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and depending on the embodiment, at least some of each step may be performed on different devices.

[0037] FIG. 1 is a diagram illustrating a system providing an automated meat processing method service through image analysis according to an embodiment of the present invention.

[0038] Referring to FIG. 1, a system providing an automated meat processing method service through image analysis according to one embodiment of the present invention may include a meat processing system (100), a worker terminal (200), an external server (300), and a network (400).

[0039] Here, the system providing an automated meat processing method service through image analysis illustrated in FIG. 1 is according to one embodiment, and its components are not limited to the embodiment illustrated in FIG. 1 and may be added, changed, or deleted as needed.

[0040] In one embodiment, the meat processing system (100) may perform a series of operations related to meat processing. For example, the meat processing system (100) may perform a meat transport operation for transporting meat to be processed, a meat processing operation for processing the transported meat, and a meat packaging operation for packaging the processed meat, but is not limited thereto.

[0041] In various embodiments, the meat processing system (100) can perform an automated meat processing method operation through image analysis. The configuration of the meat processing system (100) and the form of its operation will be described later with reference to FIG. 2.

[0042] In various embodiments, the meat processing system (100) may be connected to a worker terminal (200) via a network (400) and may provide various information related to an automated meat processing method service through image analysis to the worker terminal (200). For example, the meat processing system (100) may provide results derived by performing meat image analysis (e.g., attribute information such as the type and quality of the meat, information related to processing, etc.) and / or guide information based on the derived results (e.g., information regarding the cutting part, cutting line, and cutting method of the meat, etc.).

[0043] Here, as a terminal of a worker processing meat, the worker terminal (200) may refer to any form of entity(s) in a system having a mechanism for communicating with the meat processing system (100). For example, such a worker terminal (200) may include a PC (personal computer), a notebook, a mobile terminal, a smartphone, a tablet PC, and a wearable device, and may include any type of terminal capable of connecting to a wired / wireless network. Additionally, the worker terminal (200) may include any computing device implemented by at least one of an agent, an API (Application Programming Interface), and a plug-in. Additionally, the user terminal (200) may include an application source and / or a client application.

[0044] Additionally, the network (400) may refer to a connection structure capable of exchanging information between each node, such as multiple terminals and servers. For example, the network (400) may include a Local Area Network (LAN), a Wide Area Network (WAN), the World Wide Web (WWW), a wired or wireless data network, a telephone network, a wired or wireless television network, etc.

[0045] Wireless data communication networks may include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0046] In one embodiment, an external server (300) may be connected to a meat processing system (100) via a network (400) and may store and manage various information and data necessary for the meat processing system (100) to provide an automated meat processing method service through image analysis, or receive, store, and manage various information and data derived as the meat processing system (100) provides an automated meat processing method service through image analysis. For example, the external server (300) may be a storage server separately provided outside the meat processing system (100), but is not limited thereto. Hereinafter, with reference to FIG. 2, the configuration and operation of the meat processing system (100) providing an automated meat processing method service through image analysis will be described in more detail.

[0047] FIG. 2 is a block diagram illustrating the components of a meat processing system according to another embodiment of the present invention.

[0048] Referring to FIG. 2, in various embodiments, a meat processing system (100) may perform a series of operations related to meat processing and may provide an automated meat processing method service through image analysis. To this end, the meat processing system (100) may include a meat transport module (110), a meat processing module (120), and a meat packaging module (130) that perform a series of operations related to meat processing, and a computing device (140) that controls the operations of these modules. However, it is not limited thereto.

[0049] In one embodiment, the meat transport module (110) can transport meat to be processed according to a control command of the computing device (140) described below.

[0050] In various embodiments, the meat transport module (110) may include a conveyor (111) connecting a place for storing meat to be processed, a meat processing module (120), and a meat packaging module (130), and the meat to be processed may be transported to the meat processing module (120) through the conveyor (111), and the processed meat may be transported to the meat packaging module (130) through the meat processing module (120).

[0051] In one embodiment, the meat processing module (120) can process meat transported through the meat transport module (110) according to a control command of the computing device (140) described below.

[0052] Here, processing meat may refer to the process of cutting the meat to extract only the necessary parts, removing unnecessary parts, or classifying it by part, but is not limited thereto.

[0053] In various embodiments, the meat processing module (120) can perform pretreatment on the meat to be processed and can cut the meat using the results of the pretreatment. To this end, the meat processing module (120) may include a meat pretreatment module (121) and a meat cutting module (122).

[0054] First, the meat preprocessing module (121) can perform preprocessing on meat according to the control command of the computing device (140) described later.

[0055] In various embodiments, the meat pretreatment module (121) can mark cutting areas and cutting lines on the meat to be processed as a pretreatment for the meat to be processed. To this end, the meat pretreatment module (121) may include a camera module (121a) and a display module (121b).

[0056] The camera module (121a) can be placed and installed on the path of the meat transport module (110) (e.g., conveyor (111)), and can generate a meat image by photographing the meat transported through the meat transport module (110) according to a control command of the computing device (140) described later, and can provide the generated meat image to the computing device (140) described later.

[0057] In various embodiments, the camera module (121a) may include a plurality of camera modules installed at different positions and angles to photograph the transported meat from different views, but is not limited thereto, and may additionally include a rotating member to rotate the meat 360 degrees as needed, and may be implemented so that images of the meat from different views can be collected by rotating the meat being moved while the rotating member is hung in the form of a carcass.

[0058] The display module (121b) can display information related to processing on the meat according to the control command of the computing device (140) described later.

[0059] For example, the display module (121b) may include a laser irradiation module (not shown) and can display a cutting area and a cutting line on the meat by irradiating a laser according to a control command obtained from the computing device (140).

[0060] As another example, the display module (121b) may include an edible marker spraying module (not shown) and may display a cutting area and a cutting line on the meat by spraying an edible marker according to a control command obtained from the computing device (140). However, it is not limited thereto.

[0061] Next, the meat cutting module (122) can perform a cutting operation on meat preprocessed through the meat preprocessing module (121) (e.g., meat with a cutting section and a cutting line marked) according to a control command obtained from the computing device (140) described later. To this end, the meat cutting module (122) may include a cutting section (122a) and a motor section (122b), but is not limited thereto.

[0062] Here, the meat cutting module (122) may be implemented in the form of a robot arm capable of movement and rotation in three axes (e.g., x, y, z axes), as shown in FIGS. 3 and 4, and a cutting part (122a) for cutting meat and a motor part (122b) for operating the cutting part (122a) may be disposed on the head of the robot arm, but is not limited thereto.

[0063] The cutting section (122a) can cut meat to be processed. For example, the cutting section (122a) may include a rotary blade, and the meat can be cut by rotating the rotary blade in a predetermined direction.

[0064] In various embodiments, the meat cutting module (122) may include a plurality of cutting sections (122a) each comprising a different type of rotary blade, and depending on the situation such as the type of meat, one of the cutting sections (122a) may be selectively operated to cut the meat.

[0065] The motor unit (122b) can control the rotational movement of the cutting unit (122a). For example, the motor unit (122b) can control the rotation of a rotary blade included in the cutting unit (122a) according to a control command obtained from a computing device (140) described later. However, it is not limited thereto.

[0066] In various embodiments, the meat cutting module (122) may further include a sub-arm (122c) positioned at both ends of the cutting section (122a).

[0067] The auxiliary arm (122c) can be inserted into the area cut through the cutting portion (122a) and perform the function of opening the area to expand it. For example, the auxiliary arm (122c) can be implemented with a pointed end so that it can be easily inserted into the area cut, as shown in FIG. 5.

[0068] Additionally, as shown in FIG. 5 (a), the auxiliary arm (122c) can be inserted into the incision site, and then both auxiliary arms (122c) can be moved outward (e.g., in a direction that widens the incision site) to expand the incision site. Additionally, depending on the case, as shown in FIG. 5 (b), the auxiliary arm (122c) can be inserted into the incision site, and then only the part inserted into the incision site can be widened outward (e.g., widened so that the angle between both auxiliary arms (122c) increases) to expand the incision site.

[0069] At this time, the auxiliary arm (122c) may have a hook shape at its end (e.g., a shape that bends outward) so that the meat part that opens up can be fixed as shown in FIG. 6, but is not limited thereto. Also, if the area of ​​the auxiliary arm (122c) is narrow, the meat may be damaged by the auxiliary arm (122c), so the area of ​​the part in contact with the meat may be formed wide as shown in FIG. 6.

[0070] In one embodiment, the meat packaging module (130) can perform packaging for meat processed through the meat processing module (120) according to a control command of the computing device (140) described below. To this end, the meat packaging module (130) may include, but is not limited to, a fat removal module (131), a vinyl packaging module (132), a code assignment module (133), and a box packaging module (134). For example, the meat packaging module (130) can remove an unnecessary fat layer present in the meat through the fat removal module (131), package the fat-removed meat in vinyl through the vinyl packaging module (132), issue and assign a code corresponding to the meat through the code assignment module (133), and perform packaging for the meat in a box through the box packaging module (134).

[0071] In various embodiments, the meat packaging module (130) can perform image analysis on an image containing processed meat and can package the processed meat based on the results of the image analysis.

[0072] In one embodiment, the computing device (140) can control the operation of components included in the meat processing system (100). For example, the computing device (140) can control the operation of the meat transport module (110) to allow the meat to be transported to the meat processing module (120) and the meat packaging module (130). Additionally, the computing device (140) can control the operation of the meat processing module (120) to allow the meat to be processed. Additionally, the computing device (140) can control the operation of the meat packaging module (130) to allow the meat to be packaged.

[0073] In various embodiments, the computing device (140) can perform an automated meat processing method through image analysis. Hereinafter, with reference to FIG. 7, it will be described in more detail.

[0075] FIG. 7 is a flowchart of an automated meat processing method through image analysis according to another embodiment of the present invention.

[0076] Referring to FIG. 7, the computing device (140) can transport meat to be processed by controlling the operation of the meat transport module (110).

[0077] In various embodiments, the computing device (140) can control the meat to be processed to be transported to the meat processing module (120) through the meat transport module (110) by providing a control command to the meat transport module (110) that controls the operation of the meat transport module (110). This is not limited thereto.

[0078] In step S120, the computing device (140) can process the meat transported through step S110 by controlling the operation of the meat processing module (120).

[0079] In various embodiments, the computing device (140) can control the meat processing module (120) to process meat by providing a control command to the meat processing module (120) to control the operation of the meat processing module (120).

[0080] In various embodiments, the computing device (140) can process meat through artificial intelligence-based image analysis.

[0081] More specifically, first, the computing device (140) can obtain an image of meat generated by photographing meat through the camera module (121a).

[0082] Afterwards, the computing device (140) can derive processing information of the meat by analyzing the meat image using a previously trained artificial intelligence model.

[0083] Here, the previously trained artificial intelligence model is a model trained using multiple meat images labeled with information regarding reference points and / or information regarding cutting areas and cutting lines as training data, and may be a model that derives information regarding reference points identified on a specific meat image using a specific meat image as input data.

[0084] An artificial intelligence model (e.g., a neural network) consists of one or more network functions, and one or more network functions may consist of a set of interconnected computational units that can generally be referred to as 'nodes'. These 'nodes' may also be referred to as 'neurons'. One or more network functions are composed of at least one node. The nodes (or neurons) constituting one or more network functions may be interconnected by one or more 'links'.

[0085] In an artificial intelligence model, one or more nodes connected via links can form a relative relationship between an input node and an output node. The concepts of input and output nodes are relative; any node in an output node relationship with respect to one node may be in an input node relationship with respect to another node, and vice versa. As previously mentioned, the input node versus output node relationship can be generated based on links. One or more output nodes may be connected to a single input node via links, and vice versa.

[0086] In a relationship between input and output nodes connected via a single link, the value of the output node can be determined based on data input into the input node. Here, the nodes interconnecting the input and output nodes may have weights. These weights can be variable and may be varied by a user or an algorithm to enable the artificial intelligence model to perform desired functions. For example, if one or more input nodes are interconnected to a single output node via respective links, the output node value can be determined based on the values ​​input into the input nodes connected to the output node and the weights set on the links corresponding to each input node.

[0087] As described above, an artificial intelligence model consists of one or more nodes interconnected through one or more links, forming input and output node relationships within the model. The characteristics of an artificial intelligence model can be determined by the number of nodes and links within the model, the relationships between the nodes and links, and the weight values ​​assigned to each link. For example, if two artificial intelligence models exist with the same number of nodes and links but different weight values ​​between the links, the two models may be perceived as different from each other.

[0088] Some of the nodes constituting an artificial intelligence model may form a layer based on their distances from the initial input node. For example, a set of nodes with a distance of n from the initial input node may form n layers. The distance from the initial input node can be defined by the minimum number of links that must be traversed to reach that node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within the artificial intelligence model may be defined in a way different from that described above. For example, the layer of nodes may be defined by their distance from the final output node.

[0089] The initial input node may refer to one or more nodes within the artificial intelligence model to which data is directly input without passing through links in relation to other nodes. Alternatively, within the artificial intelligence model network, in terms of relationships between nodes based on links, it may refer to nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes within the artificial intelligence model that do not have output nodes in relation to other nodes. Furthermore, the hidden node may refer to nodes constituting the artificial intelligence model that are neither the initial input node nor the final output node. An artificial intelligence model according to one embodiment of the present invention may have more nodes in the input layer than nodes in the hidden layer that are close to the output layer, and may be an artificial intelligence model in which the number of nodes decreases as it progresses from the input layer to the hidden layer.

[0090] An artificial intelligence model may include one or more hidden layers. The hidden nodes of a hidden layer can take the output of the previous layer and the output of neighboring hidden nodes as input. The number of hidden nodes for each hidden layer may be the same or different. The number of nodes in the input layer may be determined based on the number of data fields in the input data and may be the same or different from the number of hidden nodes. The input data fed into the input layer can be processed by the hidden nodes of the hidden layer and output by the fully connected layer (FCL), which is the output layer.

[0091] In various embodiments, the artificial intelligence model may be a deep learning model.

[0092] A deep learning model (e.g., a deep neural network (DNN)) can refer to an artificial intelligence model that includes multiple hidden layers in addition to input and output layers. Using a deep neural network, one can identify the latent structures of data. That is, one can identify the latent structures of photos, text, videos, voice, and music (e.g., what objects are in a photo, what the content and emotions of the text are, what the content and emotions of the voice are, etc.).

[0093] Deep neural networks may include, but are not limited to, convolutional neural networks (CNN), recurrent neural networks (RNN), autoencoders, Generative Adversarial Networks (GAN), restricted Boltzmann machines (RBM), deep belief networks (DBN), Q networks, U networks, and Siamese networks.

[0094] In various embodiments, the pre-trained artificial intelligence model may include a plurality of artificial intelligence models applicable to each of different types of meat, that is, models trained using images of different types of meat as training data, thereby performing image analysis only on images of specific types of meat. For example, the pre-trained artificial intelligence model may include, but is not limited to, a first artificial intelligence model that analyzes only beef images by being trained using beef images as training data, and a second artificial intelligence model that analyzes only pork images by being trained using pork images as training data.

[0095] In various embodiments, the computing device (140) can extract reference points by analyzing a meat image based on a previously trained artificial intelligence model, and can set a cutting section and a cutting line of the meat as processing information for the meat using the extracted reference points. For example, when the computing device (140) identifies a first reference point and a second reference point on the meat by analyzing a meat image through a previously trained artificial intelligence model, it can set a line connecting the first reference point and the second reference point as the cutting line of the meat, but is not limited thereto.

[0096] Here, reference points may be anatomical points and singularities (e.g., landmarks), but are not limited thereto.

[0097] In various embodiments, the computing device (140) can determine the type and part of the meat included in the meat image by performing a primary analysis on the meat image, and can set a cutting line for the meat by performing a secondary analysis on the meat image based on the result of the primary determination (e.g., type and part of the meat).

[0098] For example, the computing device (140) can extract a reference point by analyzing the specific meat image based on the analysis result of the specific meat image (or information input from the operator) when the specific meat image is a beef image (e.g., an artificial intelligence model trained using a beef image as training data), and can set a cutting line for the specific meat using the extracted reference point.

[0099] As another example, the computing device (140) can pre-set and store reference point information for the type of meat (e.g., chicken, beef, pork, lamb, etc.) and the part of the meat, and based on the analysis result of a specific meat image (or information input from an operator), if the specific meat image is a beef image, it can load reference point information corresponding to beef from the pre-stored information, and can extract reference points by analyzing the specific meat image based on the loaded reference point information, and can set a cutting line for the specific meat using the extracted reference points.

[0100] In various embodiments, when a plurality of reference points are extracted as the computing device (140) analyzes a meat image based on a previously trained artificial intelligence model, it can select at least one reference point among the plurality of reference points based on the attributes of the meat and set the cutting part and cutting line of the meat using the selected at least one reference point.

[0101] For example, when a plurality of reference points are identified from an image of meat, the computing device (140) can select at least one of the plurality of reference points based on at least one of the type, size, use, and grade (e.g., quality grade of meat) of the meat, and set the cutting part and cutting line of the meat using the selected at least one reference point.

[0102] As another example, when a plurality of reference points are identified from a meat image, the computing device (140) can select at least one of the plurality of reference points based on a part to be extracted or removed from the meat, and set a cutting part and a cutting line of the meat using the selected at least one reference point.

[0103] In various embodiments, the computing device (140) can determine the quality of the meat through image analysis, and if the determined quality is below a predetermined grade or, in some cases, is determined to be defective, it can provide a notification to the worker.

[0104] Afterwards, the computing device (140) can process meat based on processing information of meat derived through image analysis.

[0105] In various embodiments, when processing information of meat is derived through image analysis, the computing device (140) can display processing information on the meat and perform processing operations on the meat based on the displayed processing information.

[0106] In various embodiments, when the cutting area and cutting line of the meat are set as processing information of the meat through image analysis, the computing device (140) can display the cutting area and cutting line on the meat by irradiating a laser through a laser irradiation module or spraying an edible marker through an edible marker spraying module.

[0107] At this time, the computing device (140) displays a line corresponding to the cutting line on the meat through a laser irradiation module or an edible marker spraying module, and can determine the attribute of the line corresponding to the cutting line (e.g., at least one of type, size, and grade) based on the attribute of the meat (e.g., at least one of type, size, and grade) and the cutting method, and can control the operation of the laser irradiation module or the edible marker spraying module so that a line corresponding to the determined attribute is displayed. For example, the computing device (140) can display the cutting line as a solid line of a first thickness when the cutting method corresponding to the cutting line is a first method, and can display the cutting line as a dashed line of a second thickness when the cutting method is a second method. However, it is not limited thereto.

[0108] In addition, at this time, the computing device (140) may display a line corresponding to a cutting line on the meat through a laser irradiation module or an edible marker spraying module, and may determine the attributes of the line corresponding to the cutting line (e.g., at least one of type, size, shape, and color) depending on the entity performing the cutting operation on the meat, and may control the operation of the laser irradiation module or the edible marker spraying module so that a line corresponding to the determined attributes is displayed. For example, the computing device (140) may display the cutting line with a line having a first attribute when the cutting operation on the meat must be performed directly by a worker, and may display the cutting line with a line having a second attribute when the cutting operation on the meat can be performed by a worker or a meat cutting module (122).

[0109] In various embodiments, when a plurality of cutting lines are set on a piece of meat, the computing device (140) can display a line corresponding to each of the plurality of cutting lines on the meat by controlling the operation of a laser irradiation module or an edible marker spraying module. At this time, the computing device (140) can determine the order for each of the plurality of cutting lines based on importance (or work order) and can display information regarding the determined order (e.g., a number corresponding to the work order) along with the line corresponding to the cutting line.

[0110] In various embodiments, the computing device (140) can determine a control command to control the cutting of meat along a cutting line, and by providing the determined control command to the meat cutting module (122), the meat cutting module (122) can cut the meat along the cutting line.

[0111] In various embodiments, when the meat cutting module (122) includes a plurality of cutting sections (122a) each comprising a different type of rotary blade, the computing device (140) may determine a control command to control the operation of a motor section (122b) to rotate a rotary blade included in one of the cutting sections (122a) based on the type of part corresponding to the cutting line marked on the meat attribute meat.

[0112] In various embodiments, the computing device (140) can determine the number of rotations of a rotary blade included in the cutting section (122a) based on the type of part corresponding to the cutting line marked on the meat attribute meat, and can determine a control command to control the operation of the motor section (122b) to rotate the rotary blade included in the cutting section (122a) according to the determined number of rotations.

[0113] Here, the automated meat processing method through image analysis according to Fig. 6 is described as automatically performing processing procedures for meat based on processing information of meat derived through artificial intelligence-based image analysis, but in some cases, it may be implemented in a form that provides guide information so that a worker can directly perform the task of processing meat based on the processing information of meat.

[0114] Additionally, the automated meat processing method through image analysis can, in some cases, determine whether to perform the processing work on the meat directly by the operator or to perform it automatically through the meat processing module (120) based on the processing information of the meat, and accordingly, it can be implemented in a form that sends a control command to the meat processing module (120) or provides guide information related to meat processing to the operator.

[0115] For example, the computing device (140) can determine the difficulty of the meat processing operation based on the processing information of the meat derived by analyzing the meat image, and if the determined difficulty is greater than or equal to the standard difficulty (e.g., if advanced work is required), it can provide guide information so that the worker can directly perform the meat processing operation based on the processing information of the meat. Meanwhile, if the difficulty of the meat processing operation is less than the standard difficulty (e.g., if simple work is required), the computing device (140) can send a control command to the meat processing module (120) so that the processing procedure for the meat is automatically performed based on the processing information of the meat.

[0116] In various embodiments, the computing device (140) may allow a primary processing operation for a specific piece of meat to be performed by sending a control command to the meat processing module (120) when a secondary processing operation by a worker is required after a primary processing operation through the meat processing module (120), and may allow a secondary processing operation to be performed by a worker by providing guide information for the meat processing operation to the worker in response to the completion of the primary processing operation through the meat processing module (120).

[0117] In various embodiments, when the computing device (140) obtains a guide request for processing specific meat from a specific worker, it can extract a cutting pattern for specific meat by analyzing multiple processing information accumulated as multiple different workers process the same meat as specific meat, determine a cutting line and cutting method for specific meat based on the extracted cutting pattern, and generate guide information including information regarding the determined cutting line and cutting method and provide it to the specific worker.

[0118] In step S130, the computing device (140) can package the meat processed through step S120 by controlling the operation of the meat packaging module (130). For example, the computing device (140) can remove unnecessary fat layers present in the meat by controlling the fat removal module (131) of the meat packaging module (130). Additionally, the computing device (140) can package the fat-removed meat in plastic by controlling the plastic packaging module (132) of the meat packaging module (130). Furthermore, the computing device (140) can issue and assign a code corresponding to the meat by controlling the code assignment module (133) included in the meat packaging module (130). Additionally, the computing device (140) can perform packaging of the meat in a box by controlling the box packaging module (134) included in the meat packaging module (130).

[0119] In various embodiments, the computing device (140) can perform image analysis on an image containing processed meat and can package the processed meat based on the results of the image analysis.

[0120] Here, the image containing the processed meat may be an image generated by photographing the processed meat through another camera module (not shown) separately provided in the meat packaging module (130), but is not limited thereto, and may be implemented in various forms such as providing / uploading an image generated by photographing the processed meat through a camera provided in the worker terminal (200).

[0121] Additionally, the image analysis performed by the computing device (140) may be performed through an artificial intelligence-based image analysis model. In this case, the image analysis model is a model trained using training data in which a plurality of images containing processed meat are input variables and attributes of the processed meat (e.g., type, part, and grade, etc.) are output variables. It may be a model that determines attributes of a specific meat by using an image containing a specific meat as input data, and may have a structure similar to the artificial intelligence model described above, but is not limited thereto.

[0122] In various embodiments, the computing device (140) can extract multiple features by analyzing multiple images having different resolutions of processed meat, and can determine the attributes of the processed meat more accurately by determining the attributes of the meat based on the extracted multiple features.

[0123] In various embodiments, the computing device (140) can determine the attributes of the meat by analyzing an image generated by photographing the processed meat, determine a packaging method for the meat based on the determined attributes, and package the processed meat based on the determined packaging method.

[0124] For example, when a part is determined as an attribute of meat as the computing device (140) analyzes an image, it can determine a packaging method according to the size, shape, and storage method of the part, and can package the meat according to the determined packaging method.

[0125] As another example, when the computing device (140) determines the type of meat (e.g., chicken, beef, pork, etc.) as an attribute of the meat by analyzing an image, it can determine a packaging method according to the type and package the meat according to the determined packaging method.

[0126] As another example, when the computing device (140) determines the grade as an attribute of the meat by analyzing an image, it can determine the packaging method according to the grade (e.g., using high-quality packaging material as the grade is higher) and can package the meat according to the determined packaging method.

[0127] In various embodiments, the computing device (140) can determine the attributes of the meat by analyzing an image generated by photographing the processed meat, issue a sticker containing information regarding the determined attributes, and attach the sticker to the packaged meat. For example, the computing device (140) can generate a template in advance for producing the sticker, and can input and output information regarding the attributes determined by analyzing an image corresponding to the processed meat into the template.

[0128] At this time, the computing device (100) may request input and / or verification of information that cannot be derived through image analysis and / or information that has been derived through image analysis but requires verification, among the information to be entered into a pre-generated template from the worker terminal (200), and may produce a sticker by inputting all information into the pre-generated template according to the user input obtained from the worker terminal (200).

[0129] Here, the information to be entered into the pre-generated template may include, but is not limited to, various information such as meat cut information, size information, grade information, and date information.

[0130] Here, the operation of issuing a sticker may be performed by a separate sticker output device that outputs the sticker in response to a control command obtained from the computing device (140), but is not limited thereto. Depending on the case, the sticker output device may also be implemented in a form that stores sticker data generated from the computing device (140) (e.g., image data generated by inputting various information into a pre-generated template, etc.) and outputs a sticker corresponding to the sticker data upon obtaining user input (e.g., output button input) that corresponds to a request for sticker production by a worker.

[0132] The automated meat processing method through image analysis described above has been explained with reference to the flowchart illustrated in the drawings. For the sake of simplicity, the automated meat processing method through image analysis has been illustrated and described using a series of blocks; however, the present invention is not limited to the order of the blocks, and some blocks may be performed in a different order than that illustrated and performed in this specification or simultaneously. Additionally, new blocks not described in this specification and drawings may be added, or some blocks may be deleted or modified. Hereinafter, with reference to FIG. 8, the hardware configuration of a computing device (140) that performs the automated meat processing method through image analysis will be described.

[0134] FIG. 8 is a hardware configuration diagram of a computing device included in a meat processing system in various embodiments.

[0135] Referring to FIG. 8, in various embodiments, a computing device (140) may include one or more processors (141), a memory (142) for loading a computer program (145a) executed by the processor (141), a bus (143), a communication interface (144), and a storage (145) for storing the computer program (145a). Here, FIG. 8 illustrates only the components related to the embodiments of the present invention. Therefore, a person skilled in the art to which the present invention pertains will understand that other general-purpose components may be included in addition to the components illustrated in FIG. 8.

[0136] The processor (141) controls the overall operation of each component of the computing device (140). The processor (141) may be configured to include a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphic Processing Unit), or any form of processor well known in the art of the present invention.

[0137] Additionally, the processor (141) may perform operations for at least one application or program for executing the method according to embodiments of the present invention, and the computing device (140) may have one or more processors.

[0138] In various embodiments, the processor (141) may further include RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor (141). Additionally, the processor (141) may be implemented in the form of a system-on-chip (SoC) comprising at least one of a graphics processing unit, RAM, and ROM.

[0139] Memory (142) stores various data, instructions and / or information. Memory (142) may load a computer program (145a) from storage (145) to execute a method / operation according to various embodiments of the present invention. When the computer program (145a) is loaded into memory (142), the processor (141) may perform the method / operation by executing one or more instructions constituting the computer program (145a). Memory (142) may be implemented as volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

[0140] The bus (143) provides communication functions between components of the computing device (140). The bus (143) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0141] The communication interface (144) supports wired and wireless internet communication of the computing device (140). Additionally, the communication interface (144) may support various communication methods other than internet communication. To this end, the communication interface (144) may be configured to include a communication module well known in the art of the present invention. In some embodiments, the communication interface (144) may be omitted.

[0142] Storage (145) can store a computer program (145a) non-temporarily. When performing an automated meat processing method process through image analysis via a computing device (140), storage (145) can store various information necessary to provide the automated meat processing method process through image analysis.

[0143] Storage (145) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0144] A computer program (145a) may include one or more instructions that cause a processor (141) to perform a method / operation according to various embodiments of the present invention when loaded into memory (142). That is, the processor (141) may perform the method / operation according to various embodiments of the present invention by executing the one or more instructions.

[0145] In one embodiment, the computer program (145a) may include one or more instructions for performing an automated meat processing method through image analysis, the steps of transporting meat to be processed, processing the transported meat, performing image analysis on an image including the processed meat, and packaging the processed meat based on the results of the performed image analysis.

[0146] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0147] The components of the present invention may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors.

[0149] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. Explanation of the symbols

[0150] 100: Meat Processing System 200 : Worker terminal 300 : External server 400 : Network

Claims

Claim 1 A method performed through a meat processing system comprises: a step of transporting meat to be processed; a step of processing the transported meat; a step of performing image analysis on an image including the processed meat; and a step of packaging the processed meat based on the result of the performed image analysis, wherein the step of processing the transported meat comprises: a step of acquiring a meat image generated by photographing the meat to be processed through a camera module included in a meat processing module of the meat processing system; a step of deriving processing information of the transported meat by analyzing the generated meat image; and a step of processing the transported meat based on the derived processing information, wherein the step of deriving processing information comprises: a step of extracting a reference point by analyzing the acquired meat image based on a pre-trained artificial intelligence model; The method comprises the step of setting a cutting section and a cutting line of the transported meat as processing information for the transported meat using the extracted reference point, wherein the step of setting the cutting section and a cutting line of the transported meat includes: when a plurality of reference points are extracted from the acquired meat image, selecting at least one reference point among the plurality of extracted reference points based on the attributes of the transported meat—the attributes of the transported meat include at least one of the type, size, use, part to be extracted, part to be removed, and grade of the transported meat—and setting the cutting section and a cutting line of the transported meat using the selected at least one reference point. Claim 2 The method for automated meat processing through image analysis according to claim 1, wherein the step of performing the image analysis comprises: a step of acquiring an image generated by photographing the processed meat; and a step of determining the attributes of the processed meat by analyzing the acquired image based on an image analysis model, wherein the determined attributes include at least one of the type, size, and grade of the processed meat. Claim 3 In paragraph 2, the step of packaging the processed meat comprises: a step of issuing a sticker containing information regarding the determined attribute; and a step of attaching the issued sticker to the packaged meat, an automated meat processing method through image analysis. Claim 4 In paragraph 2, the step of packaging the processed meat comprises: a step of determining a packaging method for the processed meat based on the determined attribute; and a step of packaging the processed meat based on the determined packaging method, wherein the automated meat processing method through image analysis. Claim 5 In paragraph 2, the step of determining the attributes of the processed meat comprises: a step of extracting multiple features by analyzing multiple images having different resolutions of the processed meat; and a step of determining the attributes of the processed meat based on the extracted multiple features, an automated meat processing method through image analysis. Claim 6 delete Claim 7 delete Claim 8 In claim 1, the derived processing information includes information regarding the cutting area and cutting line of the transported meat and information regarding the cutting method of the transported meat, and the step of processing the transported meat based on the derived processing information includes the step of marking the cutting area and cutting line on the transported meat by irradiating a laser onto the transported meat through a laser irradiation module included in the meat processing module or spraying an edible marker onto the transported meat through an edible marker spraying module included in the meat processing module, and the step of marking the cutting area and cutting line on the transported meat includes the step of determining the attribute of a line corresponding to the cutting line—the attribute of the line includes at least one of the type, size, and grade of the transported meat and the cutting method—and the step of marking a line corresponding to the determined attribute on the transported meat.

Images