Smart feeding system and livestock cloud communicating with the same

Abstract

According to the present disclosure, a smart feeding system may be provided comprising a feed feeding device installed in a structure for feeding feed to individuals in a livestock barn, a management server, and a data relay for relaying data between the feed feeding device and the management server.

Description

Technology Field

[0001] The embodiments of the present disclosure relate to automatic feeding technology, and more specifically, to a smart feeding system that automatically recognizes and feeds a target animal, a method for controlling a feed dispensing device of the smart feeding system, and a livestock cloud that communicates with a plurality of smart feeding systems. Background Technology

[0002] A livestock barn refers to a building used for raising livestock. A barn serves two functions: to streamline livestock management and to protect the animals from natural weather conditions. Therefore, the requirements for a barn include good location, orientation, ventilation, lighting, air circulation, and insulation, as well as being equipped with appropriate facilities for feeding, cleaning, and hygiene management.

[0003] Feed dispensers are installed in such livestock barns. These dispensers vary widely in design, ranging from structures that simply hold feed in open-topped bowls to designs that automatically dispense a fixed amount.

[0004] However, even in the case of automatic feed dispensers, feeding monitoring is required for each individual. Prior art literature

[0005] Published Patent Application No. 10-2016-0053222 (May 13, 2016) The problem to be solved

[0006] However, these conventional automatic feeding devices had a problem in that the amount of food fed was not automatically managed on an individual basis.

[0007] The embodiments of the present disclosure aim to solve various problems, including those mentioned above, by providing a smart feeding system that accurately manages feeding amounts for each individual animal and a livestock cloud that communicates with the same. However, these problems are exemplary and the scope of the present disclosure is not limited by them. means of solving the problem

[0008] A smart feeding system according to one aspect of the present disclosure comprises: a feed dispensing device installed in a structure for dispensing feed to individuals in a livestock barn; a management server; and a data relayer for relaying data between the feed dispensing device and the management server.

[0009] The above feed supply device may include a communication unit; a sensing unit including a plurality of sensors; a feeding unit; and a control unit.

[0010] The control unit can identify the feeding target object through the sensing unit when the feeding target object enters the structure one by one through the opening and closing door, and control the feeding unit so that feed is supplied to the feed container in an amount of feed corresponding to the feeding target object, while controlling the feeding unit by reflecting the amount of feed left in the feed container by the previous object.

[0011] According to the present embodiment, the sensing unit of the feed dispensing device may include: a first sensor that scans identification information of an individual entering the structure; a second sensor positioned at the bottom of the structure to measure the weight of the individual; a third sensor that measures the movement of an individual located within the structure; a fourth sensor that measures the amount of feed in the feed container; and a fifth sensor that measures the opening or closing of the opening and closing door of the structure.

[0012] According to the present embodiment, the management server may include a memory; and a processor electrically connected to the memory. The processor may store in the memory object information including at least one of object identification information, weight information, and movement information, manager input information, and program management information.

[0013] According to the present embodiment, when the control unit of the feed dispensing device recognizes the RFID (radio frequency identification) tag of an individual through the first sensor when the individual enters the structure, it can transmit the amount of feed in the feed container measured using the fourth sensor to the data relay unit through the communication unit.

[0014] According to the present embodiment, when an individual enters the structure, the control unit of the feed device can measure the weight of the individual through the second sensor and transmit the measured weight of the individual to the data relay through the communication unit.

[0015] According to the present embodiment, the control unit of the feed dispensing device can transmit the weight of the individual to the data relay unit through the communication unit when the individual exits the structure through the opening and closing door after eating the feed and the weight of the individual that ate the feed is less than a preset weight.

[0016] According to the present embodiment, the feed dispensing device further includes a camera, and the control unit can recognize an object using an object recognition model that has been pre-trained based on deep learning, using an image captured through the camera.

[0017] A control method for a feed dispensing device according to one aspect of the present disclosure may include: a step of sensing and identifying a feed target individual when the feed target individual enters a structure one by one through an opening and closing door; and a step of supplying feed to the feed target individual by reflecting the amount of feed left in the feed container by the previous individual, in order to supply feed to the feed target individual in an amount of feed that is stored in advance.

[0018] A livestock cloud managing a smart feeding system according to one aspect of the present disclosure collects feeding activity data from a smart feeding system corresponding to each livestock barn, wherein the feeding activity data may include at least one of a collection period, category, data format, unit, range, whether it is a platform standard, collection source, person in charge, and person in charge contact information.

[0019] According to the present embodiment, the livestock cloud can check and manage the data when the amount of feed entered by the manager and the actual amount of feed given to the individual differ by more than a preset value among the feeding activity data collected from the smart feeding system corresponding to a specific livestock barn.

[0020] Other aspects, features, and advantages other than those described above will become clear from the following specific details, claims, and drawings for implementing the invention.

[0021] In addition, these general and specific aspects may be implemented using a system, method, computer program, or any combination of a system, method, or computer program. Effects of the invention

[0022] According to the exemplary embodiment of the present disclosure as described above, a smart feeding system and a livestock cloud communicating therewith can be implemented, in which user convenience is enhanced by automatically and accurately managing the feeding amount for each individual. Of course, the scope of the present disclosure is not limited by such effects. Brief explanation of the drawing

[0023] FIG. 1 is a schematic diagram illustrating an integrated livestock management system according to an exemplary embodiment of the present disclosure. FIG. 2 is a block diagram showing the configuration of a feed supply device according to an exemplary embodiment of the present disclosure. FIG. 3 is a diagram illustrating the process of an integrated livestock management system according to an exemplary embodiment of the present disclosure. FIGS. 4 to 5(c) are drawings for explaining the structure of a feed feeding device according to an exemplary embodiment of the present disclosure. FIG. 6 is a diagram illustrating the process of a smart feed system according to an exemplary embodiment of the present disclosure. FIG. 7 shows a protocol for transmitting data measured by a sensing unit of a feed dispensing device according to an exemplary embodiment of the present disclosure. FIGS. 8 to 13 are drawings illustrating a method for managing and displaying data collected in a livestock cloud according to an exemplary embodiment of the present disclosure. FIGS. 14(a1) to 19 are drawings for explaining a method of recognizing an object using a deep learning algorithm according to an exemplary embodiment of the present disclosure. Specific details for implementing the invention

[0024] The present disclosure is capable of various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various forms.

[0025] In the following embodiments, terms such as first, second, etc. are used not in a limiting sense, but for the purpose of distinguishing one component from another component.

[0026] In the following examples, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0027] In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other features or components may be added.

[0028] In the following embodiments, when a part such as a layer, region, or component is described as being on or above another part, it includes not only cases where it is directly on top of another part, but also cases where another region, component, etc. is interposed in between.

[0029] In the drawings, the size of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are depicted arbitrarily for convenience of explanation, and therefore the present disclosure is not necessarily limited to what is depicted.

[0030] Where an embodiment can be implemented differently, a specific sequence of operations may be performed differently from the order described. For example, two steps described consecutively may be performed substantially simultaneously or proceed in the reverse order of the description.

[0031] In this specification, “A and / or B” indicates the case where it is A, B, or A and B. And, “at least one of A and B indicates the case where it is A, B, or A and B.”

[0032] In the following embodiments, when layers, regions, components, etc. are described as being connected, this includes cases where the layers, regions, components are directly connected, or / or cases where other layers, regions, components are interposed between the layers, regions, components to form an indirect connection. For example, when layers, regions, components, etc. are described as being electrically connected in this specification, it indicates cases where the layers, regions, components, etc. are directly electrically connected, and / or cases where other layers, regions, components, etc. are interposed between them to form an indirect electrical connection.

[0033] The x-axis, y-axis, and z-axis are not limited to the three axes of an orthogonal coordinate system but can be interpreted in a broader sense that includes them. For example, the x-axis, y-axis, and z-axis may be orthogonal to each other, but they may also refer to different directions that are not orthogonal to each other.

[0034] The advantages and features of the present disclosure 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 disclosure 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 is complete and to fully inform those skilled in the art of the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims.

[0035] The terms used in this disclosure are for describing the embodiments and are not intended to limit this disclosure. In this disclosure, the singular form may include the plural form unless specifically stated otherwise in the text. The terms “comprises” and / or “comprising” used in this disclosure do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the disclosure, the same reference numerals refer to the same components, and “and / or” may include each of the mentioned components and all combinations of one or more. Although terms such as “first,” “second,” etc., are used to describe various components, these components 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 technical scope of this disclosure.

[0036] The word "exemplary" is used in this disclosure to mean "used as an example or illustration." Any embodiment described as "exemplary" in this disclosure should not be interpreted as being preferred or having an advantage over other embodiments.

[0037] Embodiments of the present disclosure may be described in terms of functions or blocks performing functions. A block, which may be referred to as a “part” or “module” in the present disclosure, may be physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory, passive electronic components, active electronic components, optical components, hardwired circuits, etc., and may optionally be driven by firmware and software. Additionally, the term “part” as used in the disclosure refers to a hardware element such as software, FPGA, or ASIC, and the “part” may perform certain roles. However, the meaning of “part” is not limited to software or hardware. The “part” may be configured to reside in an addressable storage medium or may be configured to run one or more processors. Accordingly, as an example, a "part" may include elements such as software elements, object-oriented software elements, class elements, and task elements, 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 functionality provided within the elements and "parts" may be combined into a smaller number of elements and "parts" or further separated into additional elements and "parts."

[0038] Embodiments of the present disclosure may be implemented using at least one software program running on at least one hardware device and may perform network management functions to control elements.

[0039] 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.

[0040] Unless otherwise defined, all terms used in this disclosure (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0041] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted.

[0042] FIG. 1 is a schematic diagram showing a livestock integrated management system (1000) according to an exemplary embodiment of the present disclosure.

[0043] The livestock integrated management system (1000) may include a smart feeding system (AA) installed at each livestock farm to automatically operate individual feeding, and a livestock cloud (400) that manages the smart feeding system (AA) in an integrated manner.

[0044] The smart feeding system (AA) may include a feed dispensing device (100) installed in a livestock barn, a data relay (200), and a management server (300).

[0045] The feed supply device (100) is a device that automatically performs feed supply and can recognize individual entities and supply feed according to a preset amount of feed for the recognized individual entities.

[0046] The data relay (200) is a device for relaying data moving between the feed device (100) and the management server (300). The feed device (100) can provide numerical values ​​measured from a plurality of sensors to the management server (300) through the data relay (200), and the management server (300) can calculate the feeding amount of each individual and provide it to the feed device (100) through the data relay (200). However, according to the embodiment, the feed device (100) can determine the feeding amount of each individual based on pre-stored information.

[0047] The livestock cloud (400) can collect feeding activity data from the smart feeding system (AA) and manage each smart feeding system based on the collected feeding activity data.

[0048] FIG. 2 is a block diagram showing the configuration of a feed feeding device (100) according to an exemplary embodiment of the present disclosure.

[0049] The feed dispensing device (100) may include a communication unit (110), a sensing unit (120) including a plurality of sensors, a feeding unit (130), a memory (150), and a control unit (190). The components of the feed dispensing device (100) illustrated in FIG. 2 are not essential for implementing the feed dispensing device (100) according to the present disclosure, so the feed dispensing device (100) described in this specification may have more or fewer components than those listed above. For example, the feed dispensing device (100) may include one or more cameras, displays, and various input modules, but the embodiments are not limited thereto.

[0050] Among the above components, the communication unit (110) may include one or more components that enable communication with various devices equipped with a communication module, for example, may include at least one of a broadcast receiving module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0051] The sensing unit (120) may include a plurality of sensors, such as a first sensor (121) that scans identification information of an individual entering the structure of the feed dispensing device (100), a second sensor (123) that is positioned at the bottom of the structure to measure the weight of the individual, a third sensor (125) that measures the movement of an individual located within the structure, a fourth sensor (127) that measures the amount of feed in the feed container, and a fifth sensor (129) that measures the opening (open) or closing (close) of the opening / closing door of the structure, but the embodiment is not limited thereto. Each sensor of the sensing unit (120) may be implemented in a plurality.

[0052] The feeding unit (130) is configured to control a feeding storage cylinder in which feed is stored and a feeding door, and can feed feed into a feed container in a vertical drop manner according to the control of the control unit (190).

[0053] The memory (150) can store data supporting various functions of the feed dispensing device (100) and programs for the operation of the processor, and can store input / output data, and can store a number of application programs (or applications) running on the feed dispensing device (100), data for the operation of the device, and instructions. At least some of these application programs can be downloaded from an external server via wireless communication.

[0054] The memory (150) can store one or more instructions and can store a deep learning-based neural network model.

[0055] The memory (150) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (150) may be a database that is separated from the feed dispensing device (100) but connected via wired or wireless means, and may be implemented as a database system.

[0056] The control unit (190) may include one or more processors and may include at least one core. The processor may execute instructions stored in memory (150). The processor may be implemented as a memory that stores data regarding an algorithm or a program that reproduces the algorithm for controlling the operation of components within the feed dispensing device (100), and at least one processor that performs the aforementioned operation using the data stored in memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip. The processor may provide various UIs for safe operation of the workplace.

[0057] At least one component may be added or removed in response to the performance of the components shown in FIG. 2. Additionally, it will be readily understood by those skilled in the art that the relative positions of the components may be changed in response to the performance or structure of the system.

[0058] Meanwhile, each component illustrated in Figure 2 refers to a software and / or hardware component such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0059] FIG. 3 is a drawing for explaining the process of a livestock integrated management system (1000) according to an exemplary embodiment of the present disclosure.

[0060] The feed dispensing device (100) can measure the identification information (RFID, radio frequency identification), weight information, movement, and the amount of feed in the feed container of an individual. The identification information of an individual can be obtained through an RF tag attached to the neck of the individual, but the embodiment is not limited thereto. The weight information of an individual can be measured through a load cell placed at the bottom of the structure, and the movement of an individual can be measured using a plurality of ultrasonic sensors. The feeding unit (130) can be controlled according to the amount of feed set for each individual.

[0061] The data relay (200) can acquire data through serial-based communication (e.g., RS-485), but can acquire data through various communication methods depending on the embodiment.

[0062] The data relay (200) can process data into various formats (binary, hex, ascii, etc.) and provide the data to the management server (300) based on MQTT (message queuing telemetry transport) communication, but depending on the embodiment, the data may be provided to the management server (300) in various communication ways.

[0063] The management server (300) includes a database and can store a feeding management algorithm, and can perform feeding management using sensor collection information, user input information, and program management information. Sensor collection information includes identification information, weight information, movement information of an object, user input information includes information of an object and information on the amount of feed for an object, and program management information may include object information and feeding time information, but it is obvious that various data can be collected and used for feeding management depending on the embodiment.

[0064] FIGS. 4 to 5(c) are drawings for explaining the structure of a feed feeding device (100) according to an exemplary embodiment of the present disclosure.

[0065] The feed dispensing device (100) can be installed in a structure for dispensing feed to animals in a livestock barn. The control unit (190) of the feed dispensing device (100) can identify an animal through a first sensor (121) that scans identification information of the animal entering the structure when an animal enters through the opening / closing door (A3). As described above, the animal can be identified through RFID identification, but according to the embodiment, the animal may also be recognized by photographing the animal using a camera and analyzing the captured image.

[0066] The feed dispensing device (100) can measure the weight of the individual through a second sensor (123) placed at the bottom (A2) of the structure.

[0067] The control unit (190) of the feed dispensing device (100) can control the feeding unit (130) so that feed is supplied to the feed container (A1) in an amount corresponding to the feed target individual. The feeding unit (130) can control the feeding door in the upper storage container where the feed is stored to supply feed to the feed container (A1), and can control the feeding unit (130) by reflecting the amount of feed left in the feed container (A1) by the previous individual. That is, the control unit (190) can supply additional feed to the amount of feed left by the previous individual so that feed is supplied to the feed container (A1) in an amount corresponding to the feed.

[0068] The control unit (190) of the feed dispensing device (100) can measure the opening or closing of the door (A3) of the structure through the fifth sensor (129) and can measure the movement of an object located within the structure through the third sensor (125). At this time, the ultrasonic sensors can be implemented in multiple numbers.

[0069] In one embodiment of the present disclosure, a door lock may be installed on the opening and closing door, and the control unit (190) may lock the opening and closing door when the feed target individual eats the feed at a level below a preset standard of the amount of feed and attempts to exit through the opening and closing door. In this case, the control unit (190) may call the manager by providing a notification to the manager terminal through the communication unit (110).

[0070] FIG. 6 is a diagram illustrating the process of a smart feed system according to an exemplary embodiment of the present disclosure.

[0071] The feed supply device (100) senses the identification information (RFID), weight information, and movement information of an individual, and then provides it to the data relay device (200). The data relay device (200) can convert the individual information and relay the individual information to provide it to the management server (300).

[0072] The management server (300) includes memory and a processor electrically connected to the memory, and the processor can store in the memory object information including at least one of object identification information, weight information, and movement information, input information of a manager (user) (object ID, amount of feed, etc.), and program management information.

[0073] Control information can be extracted through the user program of the management server (300), and the amount of feed and feeding time of each individual can be set.

[0074] When the data relay (200) relays feeding information to the feed dispensing device (100), it can manage the feeding time. For example, the data relay (200) can provide a command to the feed dispensing device (100) to perform feeding if the set feeding time is not exceeded, and can provide a command to stop feeding to the feed dispensing device (100) if the set feeding time is exceeded. The feeding time can be set five times a day for two hours each. In an embodiment, the data relay (200) can manage the feeding time and amount of feeding for individuals requiring management, as well as the feeding time corresponding to all individuals in the barn. For example, the data relay (200) can transmit a control command to the feed dispensing device (100) to lock the opening and closing door until a specific small individual (e.g., less than 50 kilograms) eats a preset amount of feeding.

[0075] In one embodiment of the present disclosure, the management server (300) can set feeding standards including the number of feedings and feeding times for each livestock barn based on the average feeding time of the livestock barn, and the data relay (200) can transmit control commands to the feed feeding device (100) according to the feeding start time, feeding end time, etc., according to the set feeding standards.

[0076] The feed dispensing device (100) can repeatedly measure the movement of an individual located within the structure using a third sensor (123), measure the amount of feed, and measure the feeding time, and can provide the relevant data to the management server (300) through the data relay (200).

[0077] The control unit (190) of the feed dispensing device (100) can transmit the amount of feed in the feed container measured using the fourth sensor to the data relay (200) through the communication unit (110) when the RFID (radio frequency identification) tag of the individual is recognized through the first sensor (121) when the individual enters the structure.

[0078] Then, the management server (300) receives data from the data relay (200) and can provide the feed amount information of the corresponding individual to the feed supply device (100) through the data relay (200). At this time, if there are specific details for each individual, a control command can be transmitted to the feed supply device (100) by reflecting these details.

[0079] The control unit (190) of the feed dispensing device (100) can measure the weight of the individual through the second sensor (123) when the individual enters the structure and transmit the measured weight of the individual to the data relay (200) through the communication unit (110).

[0080] The control unit (190) of the feed dispensing device (100) can transmit the weight of the individual through the communication unit (110) to a data relay when the individual exits the structure through the opening and closing door after eating the feed and the weight of the individual that ate the feed is less than a preset weight. The transmitted data can be provided to the management server (300) and the livestock cloud (400) and used to manage the individual.

[0081] In one embodiment of the present disclosure, a control method for a feed supply device (100) may include the steps of: sensing and identifying a feed target individual when the feed target individual enters the structure one by one through an opening and closing door; and supplying feed to the feed target individual by reflecting the amount of feed left in the feed container by the previous individual, in an amount of feed stored in advance.

[0082] FIG. 7 shows a protocol for transmitting data measured by a sensing unit of a feed dispensing device according to an exemplary embodiment of the present disclosure.

[0083] The control unit (190) can transmit the weight of the feed container when an individual is recognized (R1), transmit the weight of the individual when the movement of the individual is recognized by the third sensor (125) (R2), transmit the sensing value of the third sensor (125, e.g., four ultrasonic sensors) until the individual exits the opening / closing door (R3), and when the individual exits the opening / closing door, if the individual's weight is less than a preset weight (e.g., 50 kilograms), it can transmit the remaining amount of the feed container and transmit the feeding amount per individual. At this time, after the feeding amount per individual is set to 0, feed may not be supplied. The ultrasonic sensor of the third sensor (125) may be installed on the top of the feed container, the side and front of the feed container, etc., but the embodiment is not limited thereto.

[0084] In one embodiment of the present disclosure, when sensing information is not received, the data relay (200) checks the corresponding sensing value as 'F', and then manages the value separately and provides it to the management server (300).

[0085] FIGS. 8 to 13 are drawings illustrating a method for managing and displaying data collected in a livestock cloud (400) according to an exemplary embodiment of the present disclosure.

[0086] Referring to Fig. 8, the livestock cloud (400) managing the smart feeding system can collect feeding activity data from the smart feeding system corresponding to each livestock barn.

[0087] Feeding activity data may include at least one of the collection period, category, data format, unit, range, whether it is a platform standard, collection source, person in charge and / or person in charge's history. Here, the category may be divided into major categories (e.g., farming, feeding, production, control, etc.), medium categories (e.g., livestock, feeding, rearing, sensor information, etc.), and minor categories (RFID, feed intake, weight, ultrasound, measurement date and time, etc.).

[0088] Referring to FIGS. 9 and 10, the livestock cloud (400) can check and manage the data when the amount of feed entered by the manager and the actual amount of feed given to the individual differ by more than a preset value (e.g., 10 grams) among the feeding activity data collected from the smart feeding system (100) corresponding to a specific livestock barn.

[0089] Referring to FIG. 11(a) and FIG. 11(b), the livestock cloud (400) can manage the feeding history for each individual farm animal and display it in the form of a graph.

[0090] Referring to Fig. 12, the livestock cloud (400) can manage data measuring the movement of individuals at each livestock farm.

[0091] Referring to FIG. 13(a) and FIG. 13(b), the livestock cloud (400) can output data measured and / or analyzed from various devices.

[0092] FIGS. 14(a1) to 19 are drawings for explaining a method of recognizing an object using a deep learning algorithm according to an exemplary embodiment of the present disclosure.

[0093] Functions related to artificial intelligence according to one embodiment of the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0094] A predefined rule of action or an artificial intelligence model is characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using a number of training data by a learning algorithm, thereby creating a predefined rule of action or an artificial intelligence model configured to perform a desired characteristic (or objective). Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0095] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a Deep Neural Network (DNN), such as a Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), or Deep Q-Networks, but is not limited to the examples mentioned above.

[0096] The processor can create a neural network, train or learn a neural network, perform operations based on received input data, generate an information signal based on the results of the operation, or retrain the neural network.

[0097] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning Machine), ESN (Echo It will be understood by a person skilled in the art that any neural network may be included, but is not limited to, State Network, Deep Residual Network, Differential Neural Computer, Neural Turning Machine, Capsule Network, Kohonen Network, and Attention Network.

[0098] According to exemplary embodiments of the present disclosure, the processor comprises a Convolutional Neural Network (CNN) such as GoogleNet, AlexNet, VGG Network, Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restructured Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for Natural Language Processing, Visual Analytics, Visual Understanding, Video Synthesis for Vision Processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization for ResNet Data Intelligence, Various artificial intelligence structures and algorithms, such as recommendation and data creation, may be used, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0099] Referring to FIGS. 14(a1) to FIGS. 14(b3), the feed dispensing device (100) further includes a camera, and the control unit (190) of the feed dispensing device can recognize an object using an object recognition model that has been pre-trained based on deep learning, using an image captured through the camera. In one embodiment of the present disclosure, the object recognition process may be performed on a management server or a livestock cloud.

[0100] The control unit (190) can photograph an object using a camera. At this time, an image sensor may be provided for camera object recognition. The control unit (190) can map the captured object image to 2D coordinates and then determine the outer area (bounding box) of the object. Next, the control unit (190) can divide the object and distinguish areas based on key points by volume of the divided object. The control unit (190) can distinguish areas using pre-stored key points by volume of the object.

[0101] Referring to FIG. 15(a), the control unit (190) can accurately distinguish the outline of an object by highlighting it. Referring to FIG. 15(b) and FIG. 15(c), the control unit (190) may make a labeling error when part of the object is not included in the labeling, when the labeling is larger than the shape of the object, when part of the object is not included in the labeling, when part of the object is cut off, or when the image outline is unclear in the shading. The control unit (190) can correct the labeling error while learning the object recognition model.

[0102] The control unit (190) can perform labeling of the upper captured image. If the method of extraction from the source data is standardized and can be automated, it can be performed in automatic mode, and matters that are difficult for the machine to judge can be performed in semi-automatic mode or manual mode. At this time, the control unit (190) can perform the semi-automatic mode before the manual mode, and if the result in the semi-automatic mode is less than a preset result value, it can be switched to manual mode. The semi-automatic mode is a mode in which the labeling is performed automatically first, and then modified by the user afterwards.

[0103] Referring to FIG. 16, the control unit (190) can perform distance correction of a 3D image based on the difference in object distance. The control unit (190) can perform the task of detecting an object considered important within the image. The control unit (190) can convert the image to grayscale and predict a salient map in which the probability that a salient object belongs to each pixel in the image is expressed as an intensity value.

[0104] The control unit (190) can correct the 3D image by using the 2D image and 3D image of the object to divide the 3D image into gray colors according to distance.

[0105] Referring to FIG. 17, the control unit (190) may use CDNet with applied SOD (salient object detection) algorithm, which may be an algorithm for automatically detecting major targets or unique objects in images or videos.

[0106] Specifically, a base image is input into an RGB encoder to calculate a depth map prediction value based on a depth map, and the calculated depth map prediction value and the original depth map are input into a Siamose depth encoder to fuse depth features and output a prediction image corresponding to the base image based on cross-modal feature fusion.

[0107] The control unit (190) can apply depth values ​​to RGB through a saliency-informative depth selection method to detect objects considered important within an image.

[0108] Referring to FIG. 18, the control unit (190) can recognize only the target object from multiple objects by applying the algorithm, and referring to FIG. 19, the control unit (190) can count the number of objects.

[0109] Up to this point, the description has primarily focused on electronic feed dispensing devices, but the present disclosure is not limited thereto. For instance, a method for manufacturing such electronic devices is also considered to fall within the scope of the present disclosure.

[0110] Although the present disclosure has been described with reference to the embodiments illustrated in the drawings, this is merely illustrative, and those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of the present disclosure should be determined by the technical spirit of the appended claims. Explanation of the symbols

[0111] AA: Smart feeding system, 100: Feed dispenser, 200: Data Repeater, 300: Management Server, 400: Livestock Cloud.

Claims

Claim 1 As a smart feeding system, a feed dispensing device installed in a structure for dispensing feed to animals in a livestock barn; a management server; and includes a data relay for relaying data between the feed dispensing device and the management server. The feed dispensing device includes a communication unit, a sensing unit including a plurality of sensors, a feeding unit, and a control unit. The control unit is configured to identify the feed target object through the sensing unit when the feed target object enters the structure one by one through the opening / closing door, and to control the feeding unit so that feed is supplied to the feed container in an amount corresponding to the feed target object, while reflecting the amount of feed left in the feed container by the previous object to control the feeding unit. The plurality of sensors includes a load cell placed at the bottom of the structure to measure the weight information of the feed target object. The control unit controls the opening / closing door to lock when the feed target object eats feed below a preset standard for the amount of feed and attempts to exit through the opening / closing door. The control unit identifies the feed target object using SOD (Salient Object Detection) based on 2D and 3D images acquired from a camera, and inputs the base image into an RGB encoder to depth A smart feed system characterized by detecting objects through a cross-modal fusion-based prediction image that calculates a depth map prediction value and fuses depth features by inputting the depth map prediction value and the original depth map into a depth encoder. Claim 2 A smart feeding system according to claim 1, wherein the sensing unit comprises: a first sensor that scans identification information of an individual entering the structure; a second sensor positioned at the bottom of the structure to measure the weight of the individual; a third sensor that measures the movement of an individual located within the structure; a fourth sensor that measures the amount of feed in the feed container; and a fifth sensor that measures the opening or closing of the opening and closing door of the structure. Claim 3 In paragraph 2, the management server comprises: a memory; and a processor electrically connected to the memory, wherein the processor is configured to store in the memory object information including at least one of object identification information, weight information, and movement information, manager input information, and program management information, a smart feed system. Claim 4 In paragraph 3, the control unit of the feed dispensing device is configured to transmit the amount of feed in the feed container measured using the fourth sensor to the data relay unit through the communication unit when the RFID (radio frequency identification) tag of the individual is recognized through the first sensor when the individual enters the structure. Claim 5 In paragraph 4, the control unit of the feed dispensing device is configured to measure the weight of the individual through the second sensor and transmit the measured weight of the individual to the data relay unit through the communication unit when the individual enters the structure, in a smart feeding system. Claim 6 In claim 5, the control unit of the feed dispensing device is configured to transmit the weight of the individual to the data relay unit through the communication unit when the individual exits the structure through the opening and closing door after eating the feed, if the weight of the individual that ate the feed is less than a preset weight. Claim 7 delete Claim 8 A method for controlling a feed dispensing device, comprising: a step of sensing and identifying a feed target individual when the feed target individual enters a structure one by one through an opening and closing door; and a step of supplying feed to the feed target individual by reflecting the amount of feed left in the feed container by the previous individual, in order to supply feed to the feed target individual in an amount of feed stored in advance. A control method comprising the step of controlling the opening and closing door to lock when the feed target individual eats feed below a preset standard for the amount of feed and attempts to exit through the opening and closing door, wherein the feed dispensing device is installed in a structure for dispensing feed to individuals in a livestock barn and comprises a plurality of sensors - the plurality of sensors include load cells disposed at the bottom of the structure to measure the weight information of the feed target individual; and the step of sensing and identifying the feed target individual is a step of identifying the feed target individual using SOD (Salient Object Detection) based on 2D images and 3D images acquired from a camera, comprising the steps of: inputting a base image into an RGB encoder to calculate a depth map prediction value; inputting the depth map prediction value and the original depth map into a depth encoder to fuse depth features; and detecting an object through a prediction image based on cross-modal fusion. Claim 9 delete Claim 10 delete Claim 11 delete Claim 12 delete

Images