KR102549092B1 - Method and apparatus for managing meat according to a freshness of the meat using a neural network - Google Patents

Abstract

Embodiments suggest a method and apparatus for managing meat according to the freshness of the meat using a neural network. In the method according to an embodiment, information on meat managed by the management server is received from an external server, and the information on the meat includes item name, slaughter date, processing date, import date, packing date, part name, information related to weight and aging of the meat and storage temperature, wherein first inspection information on the meat is received from an inspection device, wherein the first inspection information on the meat is a value for each of a plurality of components of the meat; , a first pH value of the meat, a first reflectance value for each of a plurality of wavelengths of the meat, and a first image of the meat, based on the information on the meat and the first inspection information on the meat The first freshness of the meat is determined through a first freshness determination model using a first neural network, and information related to sterilization of the meat is transmitted to the sterilization device based on the information on the meat and the first freshness. Sterilization water is sprayed on the meat by the sterilizer according to information related to the sterilization of the meat, and information on a storage method of the meat is transmitted to a storage device based on the first freshness and a preset reference value. , The meat is frozen and stored by the storage device based on the fact that the first freshness is less than the preset reference value, receives an order message for the meat from at least one customer terminal, and based on the order message, The method may include transmitting information related to freshness of meat to the at least one customer terminal.

Description

METHOD AND APPARATUS FOR MANAGING MEAT ACCORDING TO A FRESHNESS OF THE MEAT USING A NEURAL NETWORK

Embodiments of the present disclosure relate to a technique for managing meat according to the freshness of the meat, and to a technique for managing meat according to the freshness of the meat using a neural network.

On the other hand, meat generally refers to the meat of slaughtered animals used as food ingredients, and includes beef, pork, chicken, lamb, and the like. Such meat may require efficient management according to the condition of the meat at each stage from slaughtering to processing, preservation, and distribution before consumption by consumers.

Recently, technologies for managing meat using IoT (Internet of Things) technology are emerging. Methods for identifying the freshness of meat using big data and artificial intelligence and sterilizing, storing, and packaging meat according to the freshness of the meat , devices, and systems are required.

On the other hand, in order to store meat in the prior art, an expert judges the freshness of the meat and stores the meat, but there is a problem in that it is difficult for non-experts to grasp the state of the meat. In addition, it may be difficult to maintain the meat in an optimal state by storing the meat only in a frozen storage method without considering the state of the meat.

Accordingly, the server managing meat determines the freshness of the meat through a freshness determination model using a neural network based on the meat information received from the external server and the meat inspection information obtained by the inspection device, and There is a need for a method for comprehensively managing meat by determining information for sterilizing and storing meat according to freshness and transmitting information related to the freshness of meat to a customer terminal purchasing meat.

Embodiments of the present disclosure may provide a method and apparatus for managing meat according to the freshness of the meat using a neural network.

Technical tasks to be achieved in the embodiments are not limited to those mentioned above, and other technical tasks not mentioned will be considered by those skilled in the art from various embodiments to be described below. can

A method for managing meat according to the freshness of meat by a management server using a neural network according to an embodiment includes receiving information on meat managed by the management server from an external server, and The information on the meat includes item name, slaughter date, processing date, import date, packing date, part name, information related to the weight and aging of the meat, and storage temperature, and the first inspection information for the meat is received from the inspection device, The first inspection information for the meat is a value for each of a plurality of components of the meat, a first pH value of the meat, a first reflectivity value for each of a plurality of wavelengths of the meat, and a first image of the meat. and determining the first freshness of the meat through a first freshness determination model using a first neural network based on the information on the meat and the first inspection information on the meat, and determining the information on the meat and transmitting information related to sterilization of the meat to a sterilization device based on the first freshness, and sterilizing water is sprayed on the meat by the sterilization device according to the information related to the sterilization of the meat, and the first freshness and prior Information on a storage method of the meat is transmitted to a storage device based on a set reference value, and the meat is frozen and stored by the storage device based on the fact that the first freshness is less than the preset reference value, and at least one The method may include receiving an order message for the meat from a customer terminal, and transmitting information related to the freshness of the meat to the at least one customer terminal based on the order message.

For example, the information related to the freshness of the meat may include a second freshness of the meat and a second image of the meat. The second freshness of the meat may be determined through a second freshness determination model using a second neural network based on information about the meat, storage condition information about the meat, and second inspection information about the meat. Based on the receipt of the order message, a release message may be transmitted to the storage device and the inspection device. Storage state information on the meat may be received from the storage device based on the delivery message. The storage state information may include information about a storage temperature of the meat, a storage time of the meat, and a storage method of the meat. Second inspection information on the meat may be received from the inspection device based on the delivery message. The second inspection information for the meat includes a second pH value of the meat measured by the inspection device, a second reflectance value for each of a plurality of wavelengths of the meat measured by a spectrometer provided in the inspection device, and A second image of the meat photographed by the inspection device may be included.

According to an embodiment, a plurality of components of the meat may be measured by an electronic nose provided in the inspection device. The plurality of ingredients for the meat may include cadaverine, putrescine, xanthine and hypoxanthine. The first pH value of the meat and the second pH value of the meat may be measured based on the color of the cellulose paper provided in the test device. A first reflectance value for each of a plurality of wavelengths of the meat and a second reflectance value of each of a plurality of wavelengths of the meat may be measured by a spectrometer included in the inspection device. The first image of the meat and the second image of the meat may be captured by a camera included in the inspection device.

According to an embodiment, the sterilizing water may be generated through corona discharge by the sterilizing device. The information related to the sterilization of the meat may include the capacity of the sterilizing water. The capacity of the sterilizing water may be determined by the following equation.

In the above equation, V is the capacity for the sterilizing water, P _e is the expected storage period for the meat, P _avg is the average storage period for the meat, and m _d is the portion of the meat. may be a preset density value, w _m may be the weight of the meat, and f may be the first freshness. The P _e , the P _avg , and the m _d in the above formula may be determined as different values depending on the type of meat and the part of the meat.

For example, a first input vector and a second input vector may be generated through data preprocessing of the information on the meat and the first inspection information on the meat. The first input vector is a value for a type of meat, a value for a part of meat, a value for a period elapsed after slaughter, a value related to aging of meat, a value for each of a plurality of components of meat, and a first input vector for meat. It may consist of a pH value and a first reflectance value for each of a plurality of wavelengths of meat. The second input vector may consist of pixel values of the first meat image. The first neural network may include a first input layer, one or more first hidden layers, and a first output layer. Each of the learning data consisting of a plurality of first input vectors, a plurality of second input vectors, and a plurality of first correct answers is input to the first input layer of the first neural network, and is input to the at least one first hidden layer and the first hidden layer. It passes through 1 output layer and is output as a first output vector, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is connected to the first output vector. A first loss value may be output using a first loss function that compares a first correct answer vector for learning data of , and parameters of the first neural network may be learned in a direction in which the first loss value becomes smaller. A first freshness of the meat may be output based on input of the first input vector and the second input vector to the first freshness determination model.

For example, a third input vector and a fourth input vector may be generated through data preprocessing of the information on the meat, the storage state information on the meat, and the second inspection information on the meat. The third input vector may consist of a value for the type of meat, a value for a part of the meat, a value related to the storage condition of the meat, a second pH value of the meat, and a second reflectance value for each of a plurality of wavelengths of the meat. can The fourth input vector may be composed of pixel values of the second image of meat. The second neural network may include a second input layer, one or more second hidden layers, and a second output layer. Each of the learning data consisting of a plurality of third input vectors, a plurality of fourth input vectors, and a plurality of second fresh answers is input to the second input layer of the second neural network, and is input to the at least one second hidden layer and the second freshness. It passes through two output layers and is output as a second output vector, the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer is connected to the second output vector. A second loss value may be output using a second loss function that compares a second correct answer vector for learning data of , and parameters of the second neural network may be learned in a direction in which the second loss value becomes smaller. A second freshness of the meat may be output based on input of the third and fourth input vectors to the second freshness determination model.

Information related to meat sterilization may include the average size of the high voltage and the capacity for sterilizing water. Additionally, for example, the average magnitude of the high voltage can be determined by the following equation.

In the above equation, Volt is an average magnitude of the high voltage, f _avg is an average first freshness value for the meat, f is the first freshness value, and Volt _d is a basic value of the high voltage. .

Through this, the sterilization device can efficiently preserve the state of the meat by adjusting the sterilizing power of the sterilizing water according to the freshness of the meat without generating the sterilizing water at a fixed voltage value.

Additionally, for example, the preset reference value may be determined by the following equation.

In Equation 3, f _th is the preset reference value, w _max is the maximum weight that the storage device can freeze-storage meat, and w _s is the weight of meat currently being frozen-stored by the storage device , wherein o _n is the number of currently unprocessed order messages, o _d is a basic value for the number of order messages, n is the number of meats currently frozen and stored in the storage device, and f _i is i It may be the first freshness of the second meat.

Additionally, for example, the average intensity of the oscillating magnetic field may include an expected storage period for the meat, an average storage period for the meat, a preset density value for a portion of the meat, a weight of the meat, and the first freshness level. can be determined based on For example, the average intensity of the vibrating magnetic field may be determined by the following equation.

In the above equation, M is the average strength of the oscillating magnetic field, Pe is the expected storage period for the meat, P _avg is the average storage period for the meat, and m _d is the expected storage period for the meat. A preset density value, w _m is the weight of the meat, f is the first freshness, and M _d is a basic value of the vibrating magnetic field.

Through this, when the storage device stores meat in a supercooled state, it is possible to efficiently maintain the supercooled state of the meat by outputting an oscillating magnetic field of appropriate intensity according to the volume of the meat and the freshness of the meat.

According to embodiments, since the management server determines the first freshness of the meat through a first freshness determination model using a first neural network based on the information on the meat and the first inspection information on the meat, The first freshness of the meat may be more accurately determined by considering external variables such as the period after the meat is slaughtered and the aging period, in addition to information about the meat itself, such as the image of the meat and various inspection information about the meat.

According to embodiments, the management server transmits information related to meat sterilization to the sterilizer based on the information on the meat and the first freshness, thereby adjusting the number of sterilizations according to the freshness of the meat, thereby efficiently maintaining the state of the meat. can be preserved

According to embodiments, the management server transmits information on a storage method of meat to a storage device based on the first freshness and a preset reference value, thereby changing the storage method according to the freshness of the meat, thereby effectively managing the state of the meat. can be preserved as

Effects obtainable from the embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

BRIEF DESCRIPTION OF THE DRAWINGS Included as part of the detailed description to aid understanding of the embodiments, the accompanying drawings provide various embodiments and, together with the detailed description, describe technical features of the various embodiments.
1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.
2 is a diagram showing the configuration of a program according to an embodiment.
3 illustrates a management system for managing meat according to the freshness of the meat using a neural network according to an embodiment.
4 illustrates a method in which a management server manages meat according to freshness of meat using a neural network according to an embodiment.
5 is an example of a first freshness determination model according to an embodiment.
6 is an example of a second freshness determination model according to an embodiment.
7 is a flowchart illustrating a method of determining, by a management server, a first freshness of meat using a neural network according to an embodiment, and managing the meat according to the first freshness;
8 is a flowchart of a method of determining, by a management server, the second freshness of meat using a neural network according to an embodiment, and managing the meat according to the second freshness.
9 is a signal exchange diagram for a method in which a management server manages meat according to freshness of meat using a neural network according to an embodiment.
10 is a block diagram illustrating a configuration of a management server according to an exemplary embodiment.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood by those skilled in the art are not described. did

Throughout the specification, when a part is said to "comprising" or "including" a certain element, it means that it may further include other elements, not excluding other elements, unless otherwise stated. do. In addition, terms such as “… unit”, “… unit”, and “module” described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, “a or an”, “one”, “the” and like terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, both the singular and the plural can be used.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent a single embodiment.

In addition, specific terms used in various embodiments are provided to help understanding of various embodiments, and the use of these specific terms may be changed into other forms without departing from the technical spirit of various embodiments. .

1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.

1 is a block diagram of an electronic device 101 within a network environment 100, according to various embodiments. Referring to FIG. 1 , in a network environment 100, an electronic device 101 communicates with an electronic device 102 through a first network 198 (eg, a short-range wireless communication network) or through a second network 199. It may communicate with at least one of the electronic device 104 or the server 108 through (eg, a long-distance wireless communication network). According to one embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108 . According to an embodiment, the electronic device 101 includes a processor 120, a memory 130, an input module 150, an audio output module 155, a display module 160, an audio module 170, a sensor module ( 176), interface 177, connection terminal 178, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196 , or the antenna module 197 may be included. In some embodiments, in the electronic device 101, at least one of these components (eg, the connection terminal 178) may be omitted or one or more other components may be added. In some embodiments, some of these components (eg, sensor module 176, camera module 180, or antenna module 197) are integrated into a single component (eg, display module 160). It can be. The electronic device 101 may also be referred to as a client, terminal, or peer.

The processor 120, for example, executes software (eg, the program 140) to cause at least one other component (eg, hardware or software component) of the electronic device 101 connected to the processor 120. It can control and perform various data processing or calculations. According to one embodiment, as at least part of data processing or operation, the processor 120 transfers instructions or data received from other components (e.g., sensor module 176 or communication module 190) to volatile memory 132. , processing commands or data stored in the volatile memory 132 , and storing resultant data in the non-volatile memory 134 . According to one embodiment, the processor 120 may include a main processor 121 (eg, a central processing unit or an application processor) or a secondary processor 123 (eg, a graphic processing unit, a neural network processing unit ( NPU: neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, when the electronic device 101 includes the main processor 121 and the auxiliary processor 123, the auxiliary processor 123 may use less power than the main processor 121 or be set to be specialized for a designated function. can The secondary processor 123 may be implemented separately from or as part of the main processor 121 .

The secondary processor 123 may, for example, take the place of the main processor 121 while the main processor 121 is in an inactive (eg, sleep) state, or the main processor 121 is active (eg, running an application). ) state, together with the main processor 121, at least one of the components of the electronic device 101 (eg, the display module 160, the sensor module 176, or the communication module 190) It is possible to control at least some of the related functions or states. According to one embodiment, the auxiliary processor 123 (eg, image signal processor or communication processor) may be implemented as part of other functionally related components (eg, camera module 180 or communication module 190). there is. According to an embodiment, the auxiliary processor 123 (eg, a neural network processing device) may include a hardware structure specialized for processing an artificial intelligence model.

AI models can be created through machine learning. Such learning may be performed, for example, in the electronic device 101 itself where the artificial intelligence model is performed, or may be performed through a separate server (eg, the server 108). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning or reinforcement learning, but in the above example Not limited. The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the foregoing, but is not limited to the foregoing examples. The artificial intelligence model may include, in addition or alternatively, software structures in addition to hardware structures.

The memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176) of the electronic device 101 . The data may include, for example, input data or output data for software (eg, program 140) and commands related thereto. The memory 130 may include volatile memory 132 or non-volatile memory 134 .

The program 140 may be stored as software in the memory 130 and may include, for example, an operating system 142 , middleware 144 , or an application 146 .

The input module 150 may receive a command or data to be used by a component (eg, the processor 120) of the electronic device 101 from the outside of the electronic device 101 (eg, a user). The input module 150 may include, for example, a microphone, a mouse, a keyboard, a key (eg, a button), or a digital pen (eg, a stylus pen).

The sound output module 155 may output sound signals to the outside of the electronic device 101 . The sound output module 155 may include, for example, a speaker or a receiver. The speaker can be used for general purposes such as multimedia playback or recording playback. A receiver may be used to receive an incoming call. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 may visually provide information to the outside of the electronic device 101 (eg, a user). The display module 160 may include, for example, a display, a hologram device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module 160 may include a touch sensor set to detect a touch or a pressure sensor set to measure the intensity of force generated by the touch.

The audio module 170 may convert sound into an electrical signal or vice versa. According to one embodiment, the audio module 170 acquires sound through the input module 150, the sound output module 155, or an external electronic device connected directly or wirelessly to the electronic device 101 (eg: Sound may be output through the electronic device 102 (eg, a speaker or a headphone).

The sensor module 176 detects an operating state (eg, power or temperature) of the electronic device 101 or an external environmental state (eg, a user state), and generates an electrical signal or data value corresponding to the detected state. can do. According to one embodiment, the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a bio sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device 101 to an external electronic device (eg, the electronic device 102). According to one embodiment, the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 178 may include a connector through which the electronic device 101 may be physically connected to an external electronic device (eg, the electronic device 102). According to one embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 179 may convert electrical signals into mechanical stimuli (eg, vibration or motion) or electrical stimuli that a user may perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 may capture still images and moving images. According to one embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 188 may manage power supplied to the electronic device 101 . According to one embodiment, the power management module 188 may be implemented as at least part of a power management integrated circuit (PMIC), for example.

The battery 189 may supply power to at least one component of the electronic device 101 . According to one embodiment, the battery 189 may include, for example, a non-rechargeable primary cell, a rechargeable secondary cell, or a fuel cell.

The communication module 190 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (eg, the electronic device 102, the electronic device 104, or the server 108). Establishment and communication through the established communication channel may be supported. The communication module 190 may include one or more communication processors that operate independently of the processor 120 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (eg, : a local area network (LAN) communication module or a power line communication module). Among these communication modules, a corresponding communication module is a first network 198 (eg, a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (eg, legacy It may communicate with the external electronic device 104 through a cellular network, a 5G network, a next-generation communication network, the Internet, or a telecommunications network such as a computer network (eg, a LAN or a WAN). These various types of communication modules may be integrated as one component (eg, a single chip) or implemented as a plurality of separate components (eg, multiple chips). The wireless communication module 192 uses subscriber information (eg, International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199. The electronic device 101 may be identified or authenticated.

The wireless communication module 192 may support a 5G network after a 4G network and a next-generation communication technology, for example, NR access technology (new radio access technology). NR access technologies include high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and access of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low latency (URLLC)). -latency communications)) can be supported. The wireless communication module 192 may support a high frequency band (eg, mmWave band) to achieve a high data rate, for example. The wireless communication module 192 uses various technologies for securing performance in a high frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), and full-dimensional multiplexing. Technologies such as input/output (FD-MIMO: full dimensional MIMO), array antenna, analog beam-forming, or large scale antenna may be supported. The wireless communication module 192 may support various requirements defined for the electronic device 101, an external electronic device (eg, the electronic device 104), or a network system (eg, the second network 199). According to one embodiment, the wireless communication module 192 is a peak data rate for eMBB realization (eg, 20 Gbps or more), a loss coverage for mMTC realization (eg, 164 dB or less), or a U-plane latency for URLLC realization (eg, Example: downlink (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) may be supported.

The antenna module 197 may transmit or receive signals or power to the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (eg, PCB). According to one embodiment, the antenna module 197 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is selected from the plurality of antennas by the communication module 190, for example. can be chosen A signal or power may be transmitted or received between the communication module 190 and an external electronic device through the selected at least one antenna. According to some embodiments, other components (eg, a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module 197 in addition to the radiator.

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, the mmWave antenna module includes a printed circuit board, an RFIC disposed on or adjacent to a first surface (eg, a lower surface) of the printed circuit board and capable of supporting a designated high frequency band (eg, mmWave band); and a plurality of antennas (eg, array antennas) disposed on or adjacent to a second surface (eg, a top surface or a side surface) of the printed circuit board and capable of transmitting or receiving signals of the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (eg, a bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and signal ( e.g. commands or data) can be exchanged with each other.

According to an embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199 . Each of the external electronic devices 102 or 104 may be the same as or different from the electronic device 101 . According to an embodiment, all or part of operations executed in the electronic device 101 may be executed in one or more external electronic devices among the external electronic devices 102 , 104 , or 108 . For example, when the electronic device 101 needs to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device 101 instead of executing the function or service by itself. Alternatively or additionally, one or more external electronic devices may be requested to perform the function or at least part of the service. One or more external electronic devices receiving the request may execute at least a part of the requested function or service or an additional function or service related to the request, and deliver the execution result to the electronic device 101 . The electronic device 101 may provide the result as at least part of a response to the request as it is or additionally processed. To this end, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an internet of things (IoT) device. Server 108 may be an intelligent server using machine learning and/or neural networks. According to one embodiment, the external electronic device 104 or server 108 may be included in the second network 199 . The electronic device 101 may be applied to intelligent services (eg, smart home, smart city, smart car, or health care) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and can provide a service to the connected electronic device 101 . In addition, the server 108 may proceed with a membership sign-up procedure, store and manage various types of information of users subscribed as members, and provide various purchase and payment functions related to services. In addition, the server 108 may share execution data of service applications executed in each of the plurality of electronic devices 101 in real time so that the service can be shared among users. This server 108 may have the same configuration as a conventional web server or service server in terms of hardware. However, in terms of software, it may include a program module that is implemented through any language such as C, C++, Java, Python, Golang, or kotlin and performs various functions. In addition, the server 108 is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, and receives requests from clients or other servers to perform tasks and derives and provides work results. It means a computer system and the computer software (server program) installed for it. In addition, the server 108, in addition to the above-described server program, a series of application programs operating on the server 108 and various databases (DB: Database, hereinafter referred to as It should be understood as a broad concept including DB"). Accordingly, the server 108 classifies member registration information and various information and data about games, stores them in a DB, and manages them. This DB may be implemented inside or outside the server 108 . In addition, the server 108 may be implemented using server programs that are provided in various ways according to operating systems such as Windows, Linux, UNIX, and Macintosh on general server hardware, As a representative example, a web service can be implemented using IIS (Internet Information Server) used in a Windows environment and CERN, NCSA, APPACH, TOMCAT, etc. used in a Unix environment. In addition, the server 108 may interoperate with an authentication system and a payment system for user authentication of services or payment for purchases related to services.

The first network 198 and the second network 199 are a connection structure capable of exchanging information between nodes such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104. means (Network). The first network 198 and the second network 199 include Internet, Local Area Network (LAN), Wireless Local Area Network (Wireless Local Area Network), Wide Area Network (WAN), Personal Area Network (PAN), and 3G , 4G, LTE, 5G, Wi-Fi, etc., but are not limited thereto. The first network 198 and the second network 199 may be closed first networks 198 and second networks 199 such as LAN and WAN, but are preferably open such as the Internet. The Internet includes protocols such as the TCP/IP protocol, TCP, and User Datagram Protocol (UDP), and various services that exist in the upper layer, such as HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), and DNS (Domain Name System). ), Simple Mail Transfer Protocol (SMTP), Simple Network Management Protocol (SNMP), Network File Service (NFS), and Network Information Service (NIS). ) structure.

A database may have a general data structure implemented in a storage space (hard disk or memory) of a computer system using a database management program (DBMS). The database may have a data storage form in which data can be freely searched for (extracted), deleted, edited, added, and the like. Databases are relational database management systems (RDBMS) such as Oracle, Informix, Sybase, and DB2, or object-oriented database management such as Gemston, Orion, and O2. It can be implemented according to the purpose of an embodiment of the present disclosure using a system (OODBMS) and XML Native Databases such as Excelon, Tamino, and Sekaiju, and its functions may have appropriate fields or elements to achieve.

2 is a diagram showing the configuration of a program according to an embodiment.

2 is a block diagram 200 illustrating a program 140 according to various embodiments. According to one embodiment, the program 140 includes an operating system 142, middleware 144, or an application 146 executable in the operating system 142 for controlling one or more resources of the electronic device 101. can include The operating system 142 may include, for example, Android™, iOS™, Windows™, Symbian™, Tizen™, or Bada™. At least some of the programs 140 are, for example, preloaded in the electronic device 101 at the time of manufacture, or when used by a user, an external electronic device (eg, the electronic device 102 or 104), or a server ( 108)) can be downloaded or updated. All or part of program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or reclamation) of one or more system resources (eg, process, memory, or power) of the electronic device 101 . Operating system 142 may additionally or alternatively include other hardware devices of electronic device 101 , such as input module 150 , sound output module 155 , display module 160 , audio module 170 . , sensor module 176, interface 177, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196, or It may include one or more driver programs for driving the antenna module 197.

The middleware 144 may provide various functions to the application 146 so that the function or information provided from one or more resources of the electronic device 101 may be used by the application 146 . The middleware 144 includes, for example, the application manager 201, the window manager 203, the multimedia manager 205, the resource manager 207, the power manager 209, the database manager 211, and the package manager 213. ), connectivity manager 215, notification manager 217, location manager 219, graphics manager 221, security manager 223, call manager 225, or voice recognition manager 227. can

The application manager 201 may manage the life cycle of the application 146 , for example. The window manager 203 may manage one or more GUI resources used in a screen, for example. The multimedia manager 205 identifies, for example, one or more formats necessary for reproducing media files, and encodes or decodes a corresponding media file among the media files using a codec suitable for the selected format. can be done The resource manager 207 may manage a source code of the application 146 or a memory space of the memory 130 . The power manager 209 may manage, for example, the capacity, temperature, or power of the battery 189, and determine or provide related information necessary for the operation of the electronic device 101 by using corresponding information among them. . According to an embodiment, the power manager 209 may interoperate with a basic input/output system (BIOS) (not shown) of the electronic device 101 .

The database manager 211 may create, search, or change a database to be used by the application 146, for example. The package manager 213 may manage installation or update of applications distributed in the form of package files, for example. The connectivity manager 215 may manage, for example, a wireless connection or a direct connection between the electronic device 101 and an external electronic device. The notification manager 217 may provide a function for notifying a user of occurrence of a designated event (eg, an incoming call, message, or alarm), for example. The location manager 219 may manage location information of the electronic device 101, for example. The graphic manager 221 may manage, for example, one or more graphic effects to be provided to a user or a user interface related thereto.

Security manager 223 may provide system security or user authentication, for example. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101 . The voice recognition manager 227 transmits, for example, the user's voice data to the server 108, and at least partially based on the voice data, a command corresponding to a function to be performed in the electronic device 101; Alternatively, text data converted at least partially based on the voice data may be received from the server 108 . According to one embodiment, the middleware 244 may dynamically delete some existing components or add new components. According to one embodiment, at least part of the middleware 144 may be included as part of the operating system 142 or may be implemented as separate software different from the operating system 142 .

The application 146 includes, for example, a home 251, a dialer 253, an SMS/MMS 255, an instant message (IM) 257, a browser 259, a camera 261, and an alarm 263. , Contacts (265), Voice Recognition (267), Email (269), Calendar (271), Media Player (273), Albums (275), Watch (277), Health (279) (e.g. exercise or blood sugar) measurement of biometric information) or environmental information 281 (eg, measurement of atmospheric pressure, humidity, or temperature information). According to an embodiment, the application 146 may further include an information exchange application (not shown) capable of supporting information exchange between the electronic device 101 and an external electronic device. The information exchange application may include, for example, a notification relay application configured to transmit designated information (eg, a call, message, or alarm) to an external electronic device, or a device management application configured to manage an external electronic device. there is. The notification relay application, for example, transmits notification information corresponding to a designated event (eg, mail reception) generated in another application (eg, the email application 269) of the electronic device 101 to an external electronic device. can Additionally or alternatively, the notification relay application may receive notification information from an external electronic device and provide the notification information to the user of the electronic device 101 .

The device management application is, for example, a power source (eg, turn-on or turn-off) of an external electronic device that communicates with the electronic device 101 or some component thereof (eg, a display module or a camera module of the external electronic device). ) or functions (eg brightness, resolution, or focus). The device management application may additionally or alternatively support installation, deletion, or update of an application operating in an external electronic device.

Throughout this specification, a neural network, a neural network, and a network function may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may be generally referred to as “nodes”. These “nodes” may also be referred to as “neurons”. A neural network includes at least two or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more “links”.

In a neural network, two or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, the input node to output node relationship can be created around the link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values between the links, the two neural networks may be recognized as different from each other.

3 illustrates a management system for managing meat according to the freshness of the meat using a neural network according to an embodiment. One embodiment of FIG. 3 may be combined with various embodiments of the present disclosure.

Referring to FIG. 3, the management system 300 for managing meat according to the freshness of the meat using a neural network includes a management server 310, an external server 320, an inspection device 330, a sterilization device 340, It may include a storage device 350 and a customer terminal 360 .

The management server 310 may be a server for determining the freshness of meat through a first freshness determination model using a neural network based on meat inspection information, and managing the corresponding meat according to the freshness of the meat. Here, the meat may include various types of meat such as beef, pork, and lamb. For example, the management server 310 may determine information for sterilizing meat according to the freshness of the meat and transmit the information for sterilizing the meat to the sterilization device 330 . For example, the management server 310 may determine information for storing meat according to the freshness of the meat and transmit the information for storing the meat to the storage device 340 . For example, the management server 310 may transmit a shipment message to the storage device 350 according to the order information received from the customer terminal 360 . The delivery message is a message for notifying the storage device 350 of the meat for which delivery has been determined according to the order information. The management server 310 may receive inspection information on meat before shipment from the inspection device 330 . The management server 310 re-determines the freshness of the meat through a second freshness determination model using a neural network based on the storage state information of the meat stored in the storage device 350 and the inspection information about the meat before shipment. and transmits information related to the freshness of the meat to the customer terminal 360. For example, the second freshness determination model may be a model that quickly derives freshness using fewer variables than the first freshness determination model. For example, management server 310 may include server 108 of FIG. 1 .

The external server 320 may be a server related to meat delivery. For example, the external server 320 may transmit information about meat to be delivered to the management server 310 . For example, external server 320 may include server 108 of FIG. 1 .

The inspection device 330 may be a device that performs various inspections on meat managed by the management server 310 . For example, the inspection device 330 may include an electronic nose that senses a plurality of components related to meat in the air, a spectrometer that irradiates light for each wavelength to the meat and senses reflected light for each wavelength, and measures the pH value of the meat. It may include a camera for taking an image of the pH indicator and the meat for measuring. For example, the type of sensor used when the inspection device 330 is brought in from the outside and inspects meat for the first time may be different from the type of sensor used when inspecting the meat stored in the storage device 350. can For example, the testing device 330 may include the processor 120, memory 130, and communication module 190 of FIG. 1 .

The sterilization device 340 may be a device for sterilizing meat managed by the management server 310 . For example, the sterilization device 340 may spray sterilizing water generated through corona discharge to meat managed by the management server 310 . At this time, the amount of sterilizing water sprayed on the meat may be adjusted by the management server 310 . For example, the sterilization device 340 may include the processor 120, memory 130, and communication module 190 of FIG. 1 .

The storage device 350 may be a device for storing meat managed by the management server 310 . For example, the storage device 350 may supercool or freeze the meat according to the freshness of the meat. The storage device 350 may freeze-storage the meat based on whether the freshness of the meat is less than a preset reference value. The storage device 350 may supercool the meat based on whether the freshness of the meat is equal to or greater than a predetermined reference value. For example, the storage device 350 may include the processor 120, memory 130, and communication module 190 of FIG. 1 .

The storage device 350 may further include a device for packaging meat. For example, when the storage device 350 receives a delivery message for specific meat from the management server 310, the specific meat may be packaged through a meat packaging device provided in the storage device 350.

The customer terminal 360 may be a terminal that purchases meat managed by the management server 310 . For example, the customer terminal 360 may transmit order information on meat desired to be purchased to the management server 310 . The customer terminal 360 may receive the freshness of the purchased meat and the meat image from the management server 310 . For example, the customer terminal 360 may include the electronic device 101 of FIG. 1 .

4 illustrates a method in which a management server manages meat according to freshness of meat using a neural network according to an embodiment. One embodiment of FIG. 4 may be combined with various embodiments of the present disclosure.

Referring to FIG. 4 , in step S401, the management server may receive information on meat managed by the management server from an external server.

Information on meat may include item name, slaughter date, processing date, import date, packaging date, part name, weight of meat, information related to meat grade and aging, and storage temperature. Here, the item name is a name for an item of meat, and for example, the item name may include an HS code and an item name for the corresponding HS code. The HS code is an item classification number assigned to each item according to the International Convention on the Harmonized Commodity Description and Coding System (HS Convention), and may consist of a total of 6 digits. For example, the first two digits are for classification by product group, the next two digits are for subclassification, and the items within the same category are classified by type and degree of processing. Alternatively, classification according to function may be indicated. The slaughter date may indicate the date the meat was slaughtered. The processing date may indicate the date the meat is processed. The date of import may indicate the date on which meat was imported into Korea from abroad. The packaging date may indicate the date the meat is packaged. A part name is a name for a part of meat, and the name may be different depending on the type of meat. The grade of meat may be a grade representing quality and quantity of meat. For example, in the case of beef, the meat grade may include a meat quantity grade and a meat quality grade. The meat quality grade may be a grade determined as 1++, 1+, 1, 2, or 3 depending on the quality of meat, meat color, fat color, texture, and maturity. The meat grade may be a grade determined as A, B, or C by integrating the amount of meat obtained from the carcass, carcass weight, back fat thickness, and sirloin cross-sectional area. The weight of meat may represent the weight of meat brought in from the outside. Information related to aging may include information on whether or not the meat is aged and the aging period. The storage temperature may be a temperature at which meat is stored when brought in from the outside. For example, if the information does not exist among item name, slaughter date, processing date, import date, packing date, part name, information related to weight and aging of meat, and storage temperature, the value of the corresponding information may be a value of 0. . For example, if the processing date does not exist, the value of the processing date may be 0.

In step S402, the management server may receive first inspection information on meat from the inspection device.

The first inspection information on the meat may include a value for each of a plurality of components of the meat, a first pH value of the meat, a first reflectance value for each of a plurality of wavelengths of the meat, and a first image of the meat. .

For example, a plurality of ingredients for meat may be measured by an electronic nose provided in the inspection device. Multiple ingredients for meat may include cadaverine, putrescine, xanthine and hypoxanthine.

Here, the electronic nose is a device using the principle of detecting and identifying the smell with a sensor when the smell comes in, focusing on the smell of the human nose. For example, sensors embedded in the electronic nose can respond to odors, convert the odor into electrical signals and collect data, and the electronic nose can use the collected data to identify odors. For example, the electronic nose may detect a plurality of components through an olfactory receptor and determine a concentration value of each of the plurality of detected components. Cadaverine is a malodorous diamine compound produced by the decay of animal tissue. Cadaverine is a toxic diamine with the chemical formula NH ₂ (CH ₂ ) ₅ NH ₂ and has a structure similar to putrescine (NH ₂ (CH ₂ ) ₄ NH ₂ ). Putrescine is an organic compound with the formula NH ₂ (CH ₂ ) ₄ NH ₂ . Putrescine is also known as 1,4-diaminobutane or 1,4-butanediamine, and putrescine and cadaverine are both living and dead organisms. It can be produced by the breakdown of amino acids in Xanthine is a purine organic compound, and has a structure of 3,7-Dihydropurine-2,6-dione. Hypoxanthine is a naturally occurring purine derivative, and xanthine It is one of the products of xanthine oxidase for

For example, the first pH value of meat may be measured based on the color of cellulose paper provided in the test device. Here, the cellulose paper is a film immersed in a natural pigment, and the first pH value may be determined through a color change of the cellulose paper. For example, the cellulose paper may be a filter paper in which the number of pores immersed in a natural dye of a specific concentration is greater than or equal to a predetermined number and the size of pores is less than or equal to a predetermined value. For example, it may be red at pH 1.0 to 3.0, pink at pH 4.0 to 6.0, purple at pH 7.0 to 8.0, blue at pH 9.0 to 11.0, and gray at pH 12.0 or higher. At this time, the first pH value may be determined based on the RGB value of the color of the cellulose paper.

For example, a first reflectivity value for each of a plurality of wavelengths for meat may be measured by a spectrometer provided in an inspection device. Here, the spectrometer may be a device for measuring components of meat using a diffuse reflectance spectroscopy (DRS) method. The DRS method may be a method of measuring relative light intensity with respect to a wavelength based on basic diffuse reflectance. Information on pre-stored chromophores to estimate moisture and fat in meat or determine myoglobin content in meat through the shape of the intensity spectrum constructed based on the diffuse reflectance measured by spectroscopy. can be used. For example, the spectrometer may include a light source lamp including an optical fiber for a light source and a detection lamp including an optical fiber for detection. The light source lamp and the detection lamp may be spaced apart from the surface of the meat by a specific range of millimeters (mm). The light source lamp may provide broadband light in a steady state to meat, and the detection lamp may detect diffuse reflectance based on a reference value of reflectance set for each specific wavelength.

For example, the spectrometer can detect diffuse reflectance for wavelengths between 750 nm and 900 nm through a detection lamp to estimate the moisture and fat content of meat. The spectrometer can detect diffuse reflectance for a wavelength between 450 nm and 750 nm through a detection lamp to estimate myoglobin in meat. The color of meat is governed by myoglobin. Myoglobin is a complex pigmented protein present in the muscle tissue of all animals. Myoglobin serves as an oxygen store and transporter in vivo. Myoglobin performs the above function by reversibly binding oxygen molecules, serving as an intercellular oxygen source for mitochondria. Pork and poultry are lighter in color than beef because they contain less myoglobin than beef. Myoglobin consists of a non-protein part called heme and a protein part called globin. The protein portion is a long polypeptide chain that determines the three-dimensional structural form of the myoglobin molecule. The heme moiety consists of iron atoms within a planar ring. The globin moiety surrounds the heme group and interacts with the heme group in a way that stabilizes the myoglobin molecule. The heme group is the reactive center of myoglobin. Heme groups have open bonds that attract ligands. The ligand must be small enough to bind well inside the heme pocket and have a suitable electron configuration to bind to the iron atom. Oxygen perfectly satisfies these conditions, so myoglobin delivers oxygen to the mitochondria through the blood.

For example, the first image of the meat may be captured by a camera included in the inspection device.

In step S403, the management server may determine the first freshness of the meat through a first freshness determination model using a first neural network based on the information on the meat and the first inspection information on the meat.

For example, a first input vector and a second input vector may be generated through data pre-processing on meat information and first inspection information on meat. The first input vector is a value for a type of meat, a value for a part of meat, a value for a period elapsed after slaughter, a value related to aging of meat, a value for each of a plurality of components of meat, and a first pH of meat. value, a first reflectance value for each of a plurality of wavelengths of meat. The second input vector may consist of pixel values for the first image of meat.

The value for the type of meat may be determined according to the HS code included in the meat information. For example, when the HS code represents beef, the value for the type of meat may be 1. For example, when the HS code represents pork, the value for the type of meat may be 2. For example, if the HS code represents rearing, the value for the type of meat may be 3.

The value for the meat part may be determined according to the HS code and part name included in the meat information. For example, when the value for the type of meat is 1, the value for the part of meat may be determined from values corresponding to each of a plurality of preset part names related to beef. When the meat part is rib meat, a value corresponding to the rib meat among values corresponding to each of a plurality of preset part names related to beef may be determined as a value for the meat part. For example, when the value for the type of meat is 2, the value for the part of meat may be determined from among values corresponding to each of a plurality of preset part names related to pork. For example, when the value for the type of meat is 3, the value for the part of meat may be determined from values corresponding to each preset part name related to rearing.

The value for the period elapsed after slaughter may be a value indicating a period from when the meat is slaughtered until it is inspected by the inspection device.

The value related to aging of meat may include a value for an aging period. For example, if the value related to the aging of meat is 30, it may indicate that the meat has been aged for 30 days. For example, when the value related to the aging of meat is 0, it may be a value indicating that the meat is not aged.

The value for each of the plurality of components of meat may include a concentration value of cadaverine, putrescine, a concentration value of xanthine, and a concentration value of hypoxanthine.

The first pH value of the meat may be determined based on the RGB values of the color of the cellulose paper. Here, the RGB value is composed of an x-coordinate representing red color, a y-coordinate representing green color, and a z-coordinate representing blue color, and each coordinate has a value between 0 and 255. For example, as the value of the x coordinate is 255, the value of the y coordinate is 0, and the value of the z coordinate is closer to 0 in RGB values, a value closer to pH 1 may be determined. For example, as the value of the x-coordinate is 255, the value of the y-coordinate is 51, and the value of the z-coordinate is closer to 153 in RGB values, the pH value may be determined to be closer to 5. For example, as the value of the x-coordinate is 139, the value of the y-coordinate is 0, and the value of the z-coordinate is closer to 255 in RGB values, a value closer to pH 7 may be determined. For example, as the value of the x-coordinate is 0, the value of the y-coordinate is 0, and the value of the z-coordinate is closer to 255 in the RGB values, a value closer to pH 10 may be determined.

The first reflectance value for each of a plurality of wavelengths of meat is a first diffuse reflectance for wavelengths between 750 nm and 900 nm for estimating the percentage of water and fat of meat and 450 nm to 450 nm for estimating the concentration of myoglobin in meat. A second diffuse reflectance for a wavelength between 750 nm and 750 nm may be included.

The pixel values of the first image of meat may include RGB values of each pixel of the first image.

For example, a first neural network may include a first input layer, one or more first hidden layers, and a first output layer. Each of the learning data consisting of a plurality of first input vectors, a plurality of second input vectors, and a plurality of first correct answers is input to the first input layer of the first neural network, and is input to the at least one first hidden layer and the first hidden layer. It passes through 1 output layer and is output as a first output vector, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is connected to the first output vector. A first loss value may be output using a first loss function that compares a first correct answer vector for learning data of , and parameters of the first neural network may be learned in a direction in which the first loss value becomes smaller.

For example, the first freshness of meat may be output based on input of the first input vector and the second input vector to the first freshness determination model. For example, the first freshness may be a value greater than 0 and less than 100.

In step S404, the management server may transmit meat sterilization-related information to the sterilizer based on the meat information and the first freshness.

For example, sterilizing water may be sprayed onto meat by a sterilizing device according to information related to meat sterilization. Sterilizing water may be generated through corona discharge by the sterilizing device. Here, the corona discharge may be an operation in which, when a predetermined voltage or more is applied between the two electrodes, the fluid between the two electrodes is ionized, thereby inducing a state in which insulation is destroyed.

For example, the sterilization device may include an inner space accommodating water and a plurality of electrically connected discharge pin sets. A plurality of discharge pin sets may be disposed within the inner space. The sterilization device may apply different high voltage and high frequency pulses to each of a plurality of sets of discharge pins. The sterilization device may include an electromagnetic field generating device. The sterilization device may move electrons and radicals emitted from the discharge pin through the electromagnetic field generating device. For example, the sterilization device may generate an electromagnetic field that moves electrons and radicals emitted from the discharge pin from the upper side of the water to the lower side through the electromagnetic field generator. For example, the sterilizer may determine the magnitude of the high voltage in inverse proportion to the first freshness of the meat. At this time, the greater the average magnitude of the high voltage applied to the plurality of discharge pin sets, the stronger the sterilizing power of the sterilizing water. For example, the average magnitude of the high voltage may be between 20 kV and 35 kV.

Information related to meat sterilization may include the average size of the high voltage and the capacity for sterilizing water.

Additionally, for example, the average magnitude of the high voltage may be determined by Equation 1 below.

In Equation 1, the Volt is the average magnitude of the high voltage, the f _avg is the average first freshness value for the meat, the f is the first freshness, and the Volt _d is the basic value of the high voltage. can

For example, the f _avg is an average value of first freshness values of a plurality of meats having the same type and part of the corresponding meat, and may be pre-stored in the management server.

Through this, the sterilization device can efficiently preserve the state of the meat by adjusting the sterilizing power of the sterilizing water according to the freshness of the meat without generating the sterilizing water at a fixed voltage value.

Additionally, for example, the capacity for sterilizing water can be determined by Equation 2 below.

In Equation 2, V is the capacity for the sterilizing water, P _e is the expected storage period for the meat, P _avg is the average storage period for the meat, and m _d is the storage period for the meat. A preset density value for a part, w _m may be the weight of the meat, and f may be the first freshness.

A plurality of expected storage periods may be pre-stored in the management server according to the type of meat and the part of the meat. The P _e of Equation 2 may be determined as a value matching the first freshness among a plurality of preset expected storage periods. The P _avg and the m _d of Equation 2 may be preset to different values according to the type of meat and the part of the meat.

For example, the P _avg is an average value of expected storage periods for a plurality of meats having the same type and part of the corresponding meat, and may be pre-stored in the management server.

Through this, the sterilizer may spray an appropriate amount of sterilizing water according to the volume of the meat and the freshness of the meat when sterilizing the meat.

In step S405, the management server may transmit information about a meat storage method to the storage device based on the first freshness and a preset reference value.

For example, the meat may be frozen and stored by the storage device based on the fact that the first freshness is less than a preset reference value. For example, the storage device may include a device for frozen storage of meat. At this time, the meat may be stored frozen by the storage device at -4 degrees or less.

Additionally, for example, the preset reference value may be determined by Equation 3 below.

In Equation 3, f _th is the preset reference value, w _max is the maximum weight that the storage device can freeze-storage meat, and w _s is the weight of meat currently being frozen-stored by the storage device , wherein o _n is the number of currently unprocessed order messages, o _d is a basic value for the number of order messages, n is the number of meats currently frozen and stored in the storage device, and f _i is i It may be the first freshness of the second meat.

For example, the maximum weight of frozen meat may be preset in the management server. The management server may receive the weight of the meat currently being stored frozen from the storage device. The order message is a message received by the management server from the customer terminal, and is a message for ordering a specific meat. The order message may include order information for meat. For example, the order message may include item name, part name, weight of meat, purchase price, and delivery address. Thereafter, meat corresponding to the order message may be delivered to the delivery address. The unprocessed order message may be an order message in a state before delivery of meat corresponding to the order message is determined. A basic value for the number of order messages may be preset in the management server. For example, n can be a positive integer greater than zero.

For example, the management server may reduce the weight of meat to be stored frozen by decreasing a preset reference value as the weight of meat stored frozen in the storage device increases. The management server may increase the weight of meat to be stored frozen by increasing a preset reference value as the weight of meat that can be stored increases. The management server may increase the weight of meat to be stored frozen by increasing the preset reference value as the number of unprocessed order messages increases. The management server may adjust the preset reference value according to the average first freshness of the frozen meat.

Therefore, the management server may flexibly adjust the preset reference value in consideration of the state of the frozen meat, the weight of the meat, and the number of current orders, without determining whether the frozen storage is performed with a fixed reference value for the first freshness. .

For example, the meat may be stored in a supercooled state by the storage device based on a first freshness equal to or greater than a preset reference value.

For example, the storage device may be a storage device using an Electric Field Refrigerator System. The electric field supercooling system can maintain a supercooled state of -3 degrees to -1 degrees by suppressing the formation of ice crystals by vibrating water molecules in food by adding energy in an electric field. For example, the storage device may suppress the formation of ice crystals by continuously vibrating moisture in the meat by allowing a weak current to flow through the meat being stored. At this time, for example, the pulsed electric field applying current to the meat may have a frequency band of 20 kHz, and the oscillating magnetic field may have a magnetic field strength ranging from 50 to 500 mT. For example, the average intensity of the vibrating magnetic field may have a larger value as the weight of the meat increases. For example, the average intensity of the oscillating magnetic field may be inversely proportional to the first freshness of the meat.

Additionally, for example, the average intensity of the oscillating magnetic field may include an expected storage period for the meat, an average storage period for the meat, a preset density value for a portion of the meat, a weight of the meat, and the first freshness level. can be determined based on For example, the average intensity of the oscillating magnetic field may be determined by Equation 4 below.

In Equation 4, M is the average strength of the oscillating magnetic field, P _e is the expected storage period for the meat, P _avg is the average storage period for the meat, and m _d is the expected storage period for the meat. A preset density value for a part, w _m is the weight of the meat, f is the first freshness, and M _d is a basic value of the oscillating magnetic field.

Through this, when the storage device stores meat in a supercooled state, it is possible to efficiently maintain the supercooled state of the meat by outputting an oscillating magnetic field of appropriate intensity according to the volume of the meat and the freshness of the meat.

In step S406, the management server may receive an order message for meat from at least one customer terminal. The order message may include item name, part name, weight of meat, purchase price and delivery address.

For example, the management server may determine meat to be delivered to at least one customer terminal based on the order message. The management server may classify the meat corresponding to the item name and part name by grade, and preset a price per gram for each grade and freshness. For example, if the order message is beef, tenderloin, 500g, and 50,000 won, the management server provides meat with a meat grade and freshness equivalent to 10,000 won per 100g among a plurality of pre-set prices per gram for beef and tenderloin to the customer. Meat to be delivered to the terminal may be determined.

In step S407, the management server may transmit information related to freshness of meat to at least one customer terminal based on the order message.

For example, information related to the freshness of meat may include a second freshness of the meat and a second image of the meat. The second freshness of the meat may be determined through a second freshness determination model using a second neural network based on the information about the meat, the storage condition information about the meat, and the second inspection information about the meat. Based on the receipt of the order message, a release message may be transmitted to the storage device and the inspection device. For example, the release message may include an identification value for identifying a specific meat. The inspection device may perform inspection on a specific meat based on the identification value. The storage device may transmit storage state information of a specific meat to the management server based on the identification value.

Storage state information on the meat may be received from the storage device based on the delivery message. The storage state information may include information about a storage temperature of the meat, a storage time of the meat, and a storage method of the meat. Here, the storage temperature of the meat is the temperature at which the meat is stored in the storage device, the storage time of the meat is the time the meat is stored in the storage device, and the storage method of the meat indicates how the meat is stored in the storage device.

Second inspection information on the meat may be received from the inspection device based on the delivery message. The second inspection information on the meat may include a second pH value of the meat measured by the inspection device, a second reflectance value for each of a plurality of wavelengths of the meat measured by a spectrometer provided in the inspection device, and the A second image of the meat photographed by the inspection device may be included.

For example, a third input vector and a fourth input vector may be generated through data preprocessing of meat information, storage state information of meat, and second inspection information of meat. The third input vector may include a value for the type of meat, a value for a part of the meat, a value related to the storage condition of the meat, a second pH value of the meat, and a second reflectance value for each of a plurality of wavelengths of the meat. there is. The fourth input vector may consist of pixel values of the second image of meat. For example, the second pH value of meat may be measured based on the color of cellulose paper provided in the test device. The second pH value of the meat may be determined based on the RGB values of the color of the cellulose paper. For example, the second reflectance value for each of a plurality of wavelengths for meat may be measured by a spectrometer provided in the inspection device. The second reflectance value for each of a plurality of wavelengths of meat is a third diffuse reflectance for wavelengths between 750 nm and 900 nm for estimating the percentage of water and fat of meat and 450 nm to 450 nm for estimating the concentration of myoglobin in meat. A fourth diffuse reflectance for a wavelength between 750 nm may be included. The pixel values of the second image of meat may include RGB values for each pixel of the second image.

Here, the value related to the storage condition of the meat may be determined based on information about the storage temperature of the meat, the storage time of the meat, and the storage method of the meat. At this time, for example, it is assumed that the storage temperature of the meat is below zero, and the storage time of the meat is assumed to be a specific time. The storage method of meat may represent a value of 1 in the case of supercooled storage and a value of 2 in the case of frozen storage. That is, when the temperature at which the meat is stored in the storage device is -4 degrees, the time the meat is stored in the storage device is 6 hours, and the meat is stored frozen, the values related to the storage condition of the meat are (4, 6 , 2). If the temperature at which the meat is stored in the storage unit is -1°C, the time the meat has been stored in the storage unit is 8 hours, and the meat is stored in supercooled storage, the values related to the storage condition of the meat are (1, 8, 1 ) can be.

For example, the second neural network may include a second input layer, one or more second hidden layers, and a second output layer. Each of the learning data consisting of a plurality of third input vectors, a plurality of fourth input vectors, and a plurality of second fresh answers is input to the second input layer of the second neural network, and is input to the at least one second hidden layer and the second freshness. It passes through two output layers and is output as a second output vector, the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer is connected to the second output vector. A second loss value may be output using a second loss function that compares a second correct answer vector for learning data of , and parameters of the second neural network may be learned in a direction in which the second loss value becomes smaller.

For example, the second freshness of meat may be output based on input of the third and fourth input vectors to the second freshness determination model.

At this time, since the inspection by the electronic nose provided in the inspection device takes a relatively long time compared to other devices, the inspection by the electronic nose may be excluded when determining the second freshness. Also, unlike the first input vector, the third input vector excludes values for each of a plurality of meat components, so that the second freshness determination model may determine the second freshness faster than the first freshness determination model. Therefore, after receiving the order message from the customer terminal, the management server simply inspects the meat using the spectrometer and the cellulose paper, and quickly transmits the second freshness to the customer terminal based on the inspection result.

5 is an example of a first freshness determination model according to an embodiment. The embodiment of FIG. 5 can be combined with various embodiments of the present disclosure.

Referring to FIG. 5 , the first freshness determination model may be a multivariate long short term memory networks (LSTM) model. In general, a recurrent neural network (RNN) can effectively model time-series information because the hidden layer value for an existing input stored therein is considered in the output for the next input value. However, since RNN is a structure that depends on past observation values, problems such as vanishing gradient or exploding gradient may occur. A model to solve this problem is LSTM, and by replacing nodes inside the LSTM with memory cells, information can be accumulated or some of past information can be deleted, and the problem of the RNN can be supplemented.

For example, the first freshness determination model may include a first input layer 510 , one or more first hidden layers 520 and a first output layer 530 . For example, one or more first hidden layers 520 include one or more LSTM blocks, and one LSTM block includes a memory cell, an input gate, a forget gate, and an output gate. (output gate) may be included. For example, the memory cell is a node that outputs a result through an activation function, and the memory cell performs a recursive operation of using a value output from a memory cell at a previous point in time as its own input. can For example, when the current time point is t, a value output by a memory cell at the current time point t may be influenced by values of memory cells in the past. The memory cell may output a cell state (C _t ) value and a hidden state (h _t ) value. That is, the memory cell uses the cell state value (C _t-1 ) and the hidden state value (h _t-1 ) delivered by the memory cell at time t-1 as input values for calculating the cell state value and hidden state value at time t. can be used as

)가 활성화 함수인 레이어일 수 있다. 또한, 예를 들어, 입력 게이트(522), 삭제 게이트(521) 및 출력 게이트(523)를 통해 셀 스테이트(524)가 제어되고, 각 게이트와 입력에 따른 가중치들이 존재할 수 있다.For example, the input gate 522, the deletion gate 521, and the output gate 523 all include a sigmoid layer, and it may indicate how much information input through the sigmoid layer is transmitted. For example, a sigmoid layer is a sigmoid function (

) may be a layer whose activation function is Also, for example, the cell state 524 is controlled through the input gate 522, the deletion gate 521, and the output gate 523, and weights according to each gate and input may exist.

For example, a first input vector and a second input vector may be generated through data pre-processing on meat information and first inspection information on meat. The first input vector is a value for a type of meat, a value for a part of meat, a value for a period elapsed after slaughter, a value related to aging of meat, a value for each of a plurality of components of meat, and a first pH of meat. value, a first reflectance value for each of a plurality of wavelengths of meat. The second input vector may consist of pixel values for the first image of meat.

Each of the learning data consisting of a plurality of first input vectors, a plurality of second input vectors, and a plurality of first fresh answers is input to the first input layer 510 of the first neural network, and is then input to the one or more first hidden layers. 520 and the first output layer 530 are output as a first output vector, the first output vector is input to a first loss function layer connected to the first output layer 530, and the first The loss function layer outputs a first loss value by using a first loss function that compares the first output vector with a first correct answer vector for each training data, and the parameter of the first neural network is the first loss value. It can be learned in a direction in which the value becomes smaller.

Here, the first freshness of the correct answer may be a correct answer vector indicating a first freshness value corresponding to the first input vector and the second input vector. That is, in the first neural network, a plurality of training sets including the first input vector, the second input vector, and the first fresh answers corresponding to the first input vector and the second input vector may be collected. The first neural network may be learned through a plurality of collected training sets.

Specifically, for example, a first input vector and a second input vector are input to the first input layer, and the deletion gate is h _t-1 generated based on the first input vector and the second input vector. Based on (hidden state at time t-1) and x _t (input value at time t), a value between 0 and 1 can be transferred to C _t-1 . Here, a value between 0 and 1 is the amount of information that has gone through the deletion process. The closer to 0, the more information is deleted, and the closer to 1, the more intact information can be transmitted.

For example, the input gate 522 may determine values to be updated through the sigmoid layer, and the tanh layer may generate C _t vectors, which are new candidate values, and store them in the cell state 524 . For example, a new cell state C _t may be created by updating the previous cell state C _t-1 . That is, information about the cell state 524 is deleted by multiplying f _t by the cell state, and a value obtained by scaling the update value may be added. For example, tanh means a nonlinear activation function (hyperbolic tangent function).

For example, the output gate 523 may determine a portion of a cell state to be output based on a first input vector and a second input vector in the sigmoid layer. The determined cell state may be multiplied with a value output as a value between -1 and 1 through the tanh layer.

Therefore, the management server may use the parameters of the first neural network learned through the first freshness determination model, and the management server may use the meat image in addition to information about the meat itself, such as various inspection information about the meat. The first freshness of meat may be more accurately determined by considering external variables such as a period after slaughtering and an aging period.

6 is an example of a second freshness determination model according to an embodiment. The embodiment of FIG. 6 can be combined with various embodiments of the present disclosure.

Referring to FIG. 6 , the second freshness determination model may be a gated recurrent unit (GRU) based neural network model. Here, the GRU may be a model modified from a recurrent neural network (RNN). The second neural network used in the second freshness determination model may be a GRU-based neural network.

The second neural network may include a second input layer 610 , one or more second hidden layers 620 and a second output layer 630 .

For example, a third input vector and a fourth input vector may be generated through data preprocessing of meat information, storage state information of meat, and second inspection information of meat. The third input vector may include a value for the type of meat, a value for a part of the meat, a value related to the storage condition of the meat, a second pH value of the meat, and a second reflectance value for each of a plurality of wavelengths of the meat. there is. The fourth input vector may consist of pixel values of the second image of meat.

)가 활성화 함수인 레이어일 수 있다. 예를 들어, 리셋 게이트 및 업데이트 게이트를 통해 히든 스테이트가 제어되고, 각 게이트와 입력에 따른 가중치들이 존재할 수 있다.For example, one or more second hidden layers 620 may include one or more GRU blocks, and one GRU block may include a reset gate and an update gate. Here, the reset gate and the update gate may include sigmoid layers. For example, a sigmoid layer is a sigmoid function (

) may be a layer whose activation function is For example, the hidden state may be controlled through a reset gate and an update gate, and weights according to each gate and input may exist.

For example, a third input vector and a fourth input vector may be generated through data preprocessing of meat information, storage state information of meat, and second inspection information of meat. The third input vector may include a value for the type of meat, a value for a part of the meat, a value related to the storage condition of the meat, a second pH value of the meat, and a second reflectance value for each of a plurality of wavelengths of the meat. there is. The fourth input vector may consist of pixel values of the second image of meat.

Each of the learning data consisting of a plurality of third input vectors, a plurality of fourth input vectors, and a plurality of second fresh answers is input to the second input layer 610 of the second neural network, and is then input to the one or more second hidden layers. 620 and the second output layer 630 to be output as a second output vector, the second output vector is input to a second loss function layer connected to the second output layer 630, and the second output vector The loss function layer outputs a second loss value by using a second loss function that compares the second output vector with a second correct answer vector for each training data, and the parameter of the second neural network is the second loss value. It can be learned in a direction in which the value becomes smaller.

Here, the second freshness of the correct answer may be a correct answer vector representing second freshness values corresponding to the third input vector and the fourth input vector. That is, in the second neural network, a plurality of learning sets including the third input vector, the fourth input vector, and the second fresh answers corresponding to the third and fourth input vectors may be collected. The second neural network may be learned through a plurality of collected training sets.

Specifically, for example, the reset gate resets past information, and the weight r(t) derived through the previous hidden layer may be determined by Equation 5.

For example, a plurality of third input vectors and a plurality of fourth input vectors are input to the second input layer 610, and the reset gate is configured based on the plurality of third input vectors and the plurality of fourth input vectors. When the generated input value (x _t ) at the current time is input, the dot product is performed with the weight W _r at the current time, and the hidden state (h _(t-1) ) is the dot product with the weight U _r at the previous point in time, and finally, the sum of the two values is input to the sigmoid function, and the result can be output as a value between 0 and 1. Through the value between 0 and 1, it may be determined how much to utilize the hidden state value of the previous time.

The update gate determines the update rate for past and present information, and z(t) is the amount of information at the current time, which can be determined by Equation 6.

For example, if the input value (x _t ) at the current time is input, the dot product is performed with the weight W _z at the current time, and the hidden state (h _(t-1) ) at the previous time is the dot product with the weight U _z at the previous time. Finally, by adding the two values and inputting them to the sigmoid function, the result can be output as a value between 0 and 1. In addition, 1-z(t) may be multiplied by information (h _(t-1) ) of the previous hidden layer.

Through this, z(t) can reflect how much current information will be used and how much 1-z(t) will be used for past information.

By multiplying the result of the reset gate, the information candidate group of the current time point t can be determined by Equation 7.

For example, if the input value (x _t ) at the current time is input, the dot product of the weight W _h at the current time and the hidden state (h _(t-1) ) at the previous time is the weight U _h at the previous time It can be input to the tanh function by summing the dot product with and multiplied by r(t).

By combining the result of the update gate and the candidate group, the weight of the hidden layer at the current time can be determined by Equation 8.

For example, the value obtained by multiplying the output value z(t) of the update gate by the current hidden state (h(t)), the value 1-z(t) discarded from the update gate, and the hidden state (h( The weight of the hidden layer at the current time may be determined as the sum of values multiplied by t-1)).

For example, dropout may be applied to a neural network used in the second freshness determination model. Here, dropout is a technique of removing neurons with a probability between 0 and 1 from layers connected to each other. For example, the dropout ratio may be set to 0.5. In this case, if there are 4 neurons in a specific layer, each of the 4 neurons may be randomly removed with a probability of 0.5. Through this, overfitting to the false scoring model can be prevented.

Through this, the management server may use parameters of the second neural network learned through the second freshness determination model. The second freshness determination model may output result values faster than the first freshness determination model by using a smaller number of variables than the number of variables used in the first freshness determination model.

7 is a flowchart illustrating a method of determining, by a management server, a first freshness of meat using a neural network according to an embodiment, and managing the meat according to the first freshness; The embodiment of FIG. 7 can be combined with various embodiments of the present disclosure.

Referring to FIG. 7 , in step S701, the management server may generate a first input vector and a second input vector. For example, the management server may generate a first input vector and a second input vector through data preprocessing on meat information and first inspection information on meat.

In step S702, the management server may determine the first freshness of the meat by inputting the first input vector and the second input vector to a first freshness determination model using a first neural network.

In step S703, the management server may determine an expected meat quality grade based on the first reflectance value for each of a plurality of wavelengths of the meat and the first image of the meat.

Additionally, for example, the management server may determine an answer image having the highest similarity to the first meat image through a CNN model using a third neural network. The management server may determine a predetermined expected grade of the correct answer image as a candidate grade.

For example, the third neural network may include a third input layer, one or more third hidden layers, and a third output layer. Each training data consisting of a plurality of first meat images and correct meat images is input to the third input layer of the third neural network, passes through one or more third hidden layers and a third output layer, and outputs a third A vector is output, and the third output vector is input to a third loss function layer connected to the third output layer, and the third loss function layer is a third answer vector for the third output vector and each training data. A third loss value may be output using a third loss function that compares , and parameters of the third neural network may be learned in a direction in which the third loss value decreases.

In addition, for example, the management server determines the ratio of the moisture ratio of meat to the fat ratio of meat through the first diffuse reflectance included in the first reflectance value, and the myoglobin through the second diffuse reflectance included in the first reflectance value. concentration can be determined. The management server compares the meat moisture ratio, the meat fat ratio, and the myoglobin concentration determined based on the first reflectance value with the preset meat moisture ratio, the preset meat fat ratio, and the preset myoglobin concentration in the correct answer image. Thus, component similarity can be determined.

The management server may determine a candidate grade determined through the CNN model as an expected meat quality grade when the component similarity is equal to or greater than a preset similarity.

When the component similarity is smaller than the preset similarity, the management server may determine a grade lower than the candidate grade determined through the CNN model as the predicted meat quality grade.

In step S704, the management server may determine whether the expected meat quality grade exceeds the existing grade. For example, the existing grade may be a meat quality grade included in meat information. For example, if the meat quality is classified as 1++, 1+, 1, 2, or 3, the expected meat quality is 1, and the existing grade is 2, the management server determines the expected meat quality. It can be determined that the grade exceeds the existing grade.

In step S705, when the expected meat quality grade exceeds the existing grade, the management server may increase the first freshness by a preset value. For example, the management server may increase the preset value in proportion to the expected grade minus the existing grade.

In step S706, the management server may determine whether the expected meat quality grade is the same as the existing grade.

In step S707, when the expected grade and the existing grade are the same grade, the management server may maintain the first freshness as it is.

In step S708, if the expected grade and the existing grade are not the same grade, the management server may decrease the first freshness by a preset value. For example, the management server may decrease the preset value in proportion to a value obtained by subtracting the expected grade from the existing grade.

In step S709, the management server may determine the average magnitude of the high voltage applied by the sterilization device. For example, the management server may determine the average magnitude of the high voltage by Equation 1 described above.

In step S710, the management server may determine the amount of sterilizing water sprayed from the sterilization device. For example, the management server may determine the capacity of the sterilizing water by Equation 2 above.

For example, the management server may transmit information related to meat sterilization to the sterilization device. Information related to meat sterilization may include the average size of the high voltage and the capacity for sterilizing water.

In step S711, the management server may determine whether the first freshness is equal to or greater than a preset first reference value. For example, the management server may determine the preset first reference value by Equation 3 above.

In step S712, when the first freshness is equal to or greater than a preset first reference value, the management server may transmit information about supercooled storage to the storage device. Information about supercooled storage may include a storage temperature of meat, a weight of meat to be stored, and an average strength of an oscillating magnetic field.

In step S711, when the first freshness is greater than or equal to the first preset reference value, the management server may transmit information about refrigerated storage to the storage device. The information about the frozen storage may include the storage temperature of meat and the weight of the meat to be stored.

8 is a flowchart of a method of determining, by a management server, the second freshness of meat using a neural network according to an embodiment, and managing the meat according to the second freshness. The embodiment of FIG. 8 can be combined with various embodiments of the present disclosure.

Referring to FIG. 8 , in step S801, the management server may receive an order message for meat from at least one customer terminal.

Additionally, for example, the order message may include body information about a particular person. Here, the specific person may be a person who plans to consume meat. For example, body information may include uric acid level, gender, age, height, and weight. The management server may determine gout risk based on uric acid level, sex, age, height and weight. For example, the risk of gout may be a value representing a degree of risk of a specific person suffering from gout. For example, the ventilation risk may be determined by Equation 9 below.

In Equation 9, G is the risk of gout, a is a weight according to gender, X is the age of a specific person, X _d is a reference value for age, and w _h is the weight of a specific person , wherein U _a is a specific person's uric acid level, and h may be a specific person's height.

For example, a reference value for age may be preset in the management server. Here, the ventilation risk may be a value between 0 and 100.

In step S802, the management server may determine whether the ventilation risk is equal to or greater than a preset score.

In step S803, when the risk of ventilation is equal to or greater than a preset score, the management server may select stored meat having a minimum fat ratio from among at least one stored meat. Here, the at least one stored meat may be meat that is determined as meat to be delivered to at least one customer terminal based on the order message among the meat stored in the storage device.

The management server may classify the meat corresponding to the item name and part name by grade, and preset a price per gram for each grade and freshness. For example, if the order message is beef, tenderloin, 500g, and 50,000 won, the management server selects at least meat with a meat grade and freshness corresponding to 10,000 won per 100g among a plurality of preset prices per gram for beef and tenderloin. It can be determined with one stored meat. Here, the freshness may be the first freshness. In this case, the higher the grade of the meat, the higher the price per gram, and the higher the first freshness of the meat, the higher the price per gram. For example, when a plurality of stored meats are determined, each of the plurality of stored meats may have different meat grades and first freshness.

The management server may determine a meat fat ratio for at least one stored meat based on the meat information and the meat inspection information. For example, the management server may determine the meat fat ratio with respect to at least one stored meat through a first diffuse reflectance included in the first reflectance value for the meat moisture ratio and the meat fat ratio. Additionally, for example, a first absorption value at which a first difference between a predetermined diffuse reflectance and a first diffuse reflectance for moisture of meat is minimized may be determined. A second absorption value at which a second difference between a predetermined diffuse reflectance and the first diffuse reflectance of meat fat is minimized may be determined. A concentration value matching the first absorption value may be determined as the moisture concentration of meat. A concentration value matching the second absorption value may be determined as the fat concentration of meat. For example, the moisture value of meat may be a value obtained by multiplying the moisture concentration of meat by an extinction coefficient for moisture. For example, the fat value of meat may be a value obtained by multiplying the fat concentration of the meat by the extinction coefficient for the fat. The moisture ratio of the meat may be a value obtained by dividing the moisture value of the meat by the sum of the moisture value of the meat and the fat value of the meat. The fat ratio of the meat may be a value obtained by dividing the fat value of the meat by the sum of the moisture value of the meat and the fat value of the meat. In this case, the preset diffuse reflectance, the concentration value matching the first absorption value, the concentration value matching the second absorption value, the extinction coefficient for water, and the extinction coefficient for fat may be different for each type and part of meat. The concentration value matching the first absorption value, the concentration value matching the second absorption value, the extinction coefficient for water, and the extinction coefficient for fat may be preset values in the server.

In step S804, when the ventilation risk is less than the preset score, the management server may select stored meat having the lowest first freshness from among the at least one stored meat.

In step S805, the management server sets a second freshness level using a second neural network based on the information on the meat, the storage state information on the meat, and the second inspection information on the meat for the meat selected from among the at least one stored meat. The second freshness may be determined through the determination model. Here, the storage state information on meat may be transmitted from the storage device to the management server based on the management server transmitting the release message to the storage device. The second inspection information for the meat may be transmitted from the inspection device to the management server based on the management server transmitting the shipment message to the inspection device.

In step S806, the management server may determine whether the second freshness is greater than or equal to a preset second reference value. Here, the preset second reference value may be a reference value for determining a packaging method according to the second freshness. The preset second reference value may be different according to a difference between the first freshness and the second freshness. For example, the preset second reference value may increase as a value obtained by subtracting the second freshness from the first freshness increases. As the value obtained by subtracting the second freshness from the first freshness decreases, the preset second reference value may decrease.

In step S807, when the second freshness is greater than or equal to a preset second reference value, the management server may transmit information on the first package to the storage device. Here, the first packaging may be a method of packaging meat in a vacuum state. That is, the information on the first packaging may be a value indicating the first packaging for packaging meat in a vacuum state.

In step S808, when the second freshness is less than the preset second reference value, the management server may transmit information on the second package to the storage device. Here, the second packaging may be a method of packaging by adding a mixture containing nitrogen oxide to maintain the meat color for a longer time before packaging in a vacuum state. For example, a mixture containing nitrogen oxides may be placed in a container and contacted with meat. At this time, nitrogen oxides may generate nitric oxide in contact with the meat. For example, nitrogen oxide may be either nitrite or sodium nitrite.

In step S809, the management server may transmit information related to the freshness of meat to at least one customer terminal.

9 is a signal exchange diagram for a method in which a management server manages meat according to freshness of meat using a neural network according to an embodiment. The embodiment of FIG. 9 can be combined with various embodiments of the present disclosure.

Referring to FIG. 9 , in step S901, the management server may receive information on meat from an external server.

In step S902, the management server may receive first inspection information on meat from the inspection device.

In step S903, the management server may determine the first freshness of the meat through a first freshness determination model based on the information on the meat and the first inspection information on the meat.

In step S904, the management server may transmit information related to meat sterilization to the sterilization device. For example, the management server may transmit information related to meat sterilization to the sterilization device based on determining the first freshness of the meat. Information related to meat sterilization may include the average size of the high voltage and the capacity for sterilizing water.

In step S905, the management server may transmit information on the meat storage method to the storage device. For example, the management server may transmit information on a storage method of the meat to the storage device based on determining the first freshness of the meat. For example, based on the fact that the first freshness is less than a preset reference value, the information on the storage method of meat may include a value indicating frozen storage. For example, based on the fact that the first freshness is greater than or equal to a preset reference value, the information on the storage method of meat may include a value indicating supercooled storage. In this case, when a value representing supercooled storage is included, the information on the meat storage method may include the average strength of the oscillating magnetic field.

In step S906, the management server may receive an order message from the customer terminal. For example, the order message may include the item name, part name, weight of the meat, purchase price, and shipping address, as well as body information about a particular person.

In step S907, the management server may transmit the release message to the inspection device and the storage device. For example, the management server may select meat to be delivered to the customer terminal from among at least one stored meat based on the order message. For example, the release message may include an identification value for identifying the selected meat.

In step S908, the management server may receive second inspection information on meat from the inspection device. For example, the inspection device may perform a second inspection on the meat identified according to the identification value and transmit second inspection information to the management server.

In step S909, the management server may receive storage state information on meat from the storage device. The storage device may transmit storage state information on the meat identified according to the identification value to the management server.

In step S910, the management server may determine the second freshness of the meat through a second freshness determination model based on the information about the meat, the storage state information about the meat, and the second inspection information about the meat. For example, the meat for which the second freshness is determined may be meat scheduled to be delivered to the customer terminal.

In step S911, the management server may transmit information about the meat packaging method to the storage device. For example, the information on the meat packaging method may include information on the first packaging or information on the second packaging.

In step S912, the management server may transmit information related to the freshness of meat to the customer terminal.

10 is a block diagram illustrating a configuration of a management server according to an exemplary embodiment. One embodiment of FIG. 10 may be combined with various embodiments of the present disclosure.

As shown in FIG. 10 , the management server 1000 may include a processor 1010 , a communication unit 1020 and a memory 1030 . However, not all components shown in FIG. 10 are essential components of the management server 1000 . The management server 1000 may be implemented by more components than those shown in FIG. 10, or the management server 1000 may be implemented by fewer components than those shown in FIG. For example, the management server 1000 according to some embodiments may further include a user input interface (not shown), an output unit (not shown), etc. in addition to the processor 1010, the communication unit 1020, and the memory 1030. there is.

The processor 1010 controls overall operations of the management server 1000 in general. The processor 1010 may include one or more processors to control other elements included in the management server 1000 . For example, the processor 1010 may generally control the communication unit 1020 and the memory 1030 by executing programs stored in the memory 1030 . In addition, the processor 1010 may perform the functions of the management server 1000 described in FIGS. 3 to 9 by executing programs stored in the memory 1030 .

The communication unit 1020 may include one or more components that allow the management server 1000 to communicate with other devices (not shown) and servers (not shown). The other device (not shown) may be a computing device such as the management server 1000 or a sensing device, but is not limited thereto. The communication unit 1020 may receive a user input from another electronic device or data stored in an external device from an external device through a network.

For example, the communication unit 1020 may transmit/receive a message for establishing a connection with at least one device. The communication unit 1020 may transmit information generated by the processor 1010 to at least one device connected to the management server. The communication unit 1020 may receive information from at least one device connected to the management server. The communication unit 1020 may transmit information related to the received information in response to information received from at least one device.

The memory 1030 may store programs for processing and control of the processor 1010 . For example, the memory 1030 may store information input to a server or information received from another device through a network. Also, the memory 1030 may store data generated by the processor 1010 . The memory 1030 may store information input to the management server 1000 or output from the management server 1000 .

The memory 1030 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), RAM (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk , an optical disk, and at least one type of storage medium.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (12)

A method in which a management server manages meat according to the freshness of meat using a neural network,
Receiving information about meat from an external server;
The information on the meat includes item name, slaughter date, processing date, import date, packaging date, part name, information related to weight and aging of meat, and storage temperature,
receiving first inspection information on the meat from an inspection device;
The first inspection information for the meat is a value for each of a plurality of components of the meat, a first pH value of the meat, a first reflectivity value for each of a plurality of wavelengths of the meat, and a first image of the meat. including,
determining a first freshness of the meat through a first freshness determination model using a first neural network based on the information about the meat and the first inspection information about the meat;
transmitting information related to sterilization of the meat to a sterilizer based on the information on the meat and the first freshness;
Sterilizing water is sprayed on the meat by the sterilizing device according to information related to the sterilization of the meat;
transmitting information about a storage method of the meat to a storage device based on the first freshness and a preset reference value;
The meat is stored frozen by the storage device based on the first freshness being less than the preset reference value,
Receiving an order message for the meat from at least one customer terminal; and
Transmitting information related to the freshness of the meat to the at least one customer terminal based on the order message,
method.
According to claim 1,
The information related to the freshness of the meat includes a second freshness of the meat and a second image of the meat,
The second freshness of the meat is determined through a second freshness determination model using a second neural network based on the information about the meat, the storage condition information about the meat, and the second inspection information about the meat;
Based on the receipt of the order message, a release message is transmitted to the storage device and the inspection device;
Storage state information for the meat is received from the storage device based on the shipment message,
The storage state information includes information about the storage temperature of the meat, the storage time of the meat, and the storage method of the meat,
Second inspection information for the meat is received from the inspection device based on the shipment message,
The second inspection information for the meat includes a second pH value of the meat measured by the inspection device, a second reflectance value for each of a plurality of wavelengths of the meat measured by a spectrometer provided in the inspection device, and Including a second image of the meat taken by the inspection device,
method.
According to claim 2,
A plurality of ingredients for the meat are measured by an electronic nose provided in the inspection device,
The plurality of ingredients for the meat include cadaverine, putrescine, xanthine and hypoxanthine,
The first pH value of the meat and the second pH value of the meat are measured based on the color of the cellulose paper provided in the test device,
A first reflectance value for each of a plurality of wavelengths of the meat and a second reflectance value of each of a plurality of wavelengths of the meat are measured by a spectrometer provided in the inspection device,
The first image of the meat and the second image of the meat are taken by a camera provided in the inspection device.
method.
According to claim 3,
The sterilizing water is generated through corona discharge by the sterilizing device,
The information related to the sterilization of the meat includes the capacity of the sterilizing water,
The capacity for the sterilizing water is determined by the following equation,

In the above equation, V is the capacity for the sterilizing water, P _e is the expected storage period for the meat, P _avg is the average storage period for the meat, and m _d is the portion of the meat. is a preset density value for, wherein w _m is the weight of the meat, f is the first freshness,
The P _e , the P _avg and the m _d in the above equation are determined to be different values depending on the type of meat and the part of the meat,
method.
According to claim 2,
A first input vector and a second input vector are generated through data preprocessing of the information on the meat and the first inspection information on the meat;
The first input vector is a value for a type of meat, a value for a part of meat, a value for a period elapsed after slaughter, a value related to aging of meat, a value for each of a plurality of components of meat, and a first input vector for meat. It consists of a pH value and a first reflectance value for each of a plurality of wavelengths of meat,
The second input vector consists of pixel values for the first image of meat,
The first neural network includes a first input layer, one or more first hidden layers and a first output layer;
Each of the learning data consisting of a plurality of first input vectors, a plurality of second input vectors, and a plurality of first correct answers is input to the first input layer of the first neural network, and is input to the at least one first hidden layer and the first hidden layer. It passes through 1 output layer and is output as a first output vector, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is connected to the first output vector. A first loss value is output using a first loss function that compares a first correct answer vector for learning data of , and parameters of the first neural network are learned in a direction in which the first loss value becomes smaller,
A first freshness of the meat is output based on input of the first input vector and the second input vector to the first freshness determination model;
A third input vector and a fourth input vector are generated through data preprocessing on the information on the meat, the storage state information on the meat, and the second inspection information on the meat;
The third input vector is composed of a value for the type of meat, a value for a part of the meat, a value related to the storage condition of the meat, a second pH value of the meat, and a second reflectance value for each of a plurality of wavelengths of the meat, ,
The fourth input vector consists of pixel values for a second image of meat,
The second neural network includes a second input layer, one or more second hidden layers, and a second output layer;
Each of the learning data consisting of a plurality of third input vectors, a plurality of fourth input vectors, and a plurality of second fresh answers is input to the second input layer of the second neural network, and is input to the at least one second hidden layer and the second freshness. It passes through two output layers and is output as a second output vector, the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer is connected to the second output vector. A second loss value is output using a second loss function that compares a second answer vector for the learning data of , and the parameters of the second neural network are learned in a direction in which the second loss value becomes smaller,
A second freshness of the meat is output based on the third input vector and the fourth input vector being input to the second freshness determination model.
method.
In a management server that manages meat according to the freshness of meat using a neural network,
The management server includes at least one processor, at least one memory and a communication unit,
Receive information about meat from an external server,
The information on the meat includes item name, slaughter date, processing date, import date, packaging date, part name, information related to weight and aging of meat, and storage temperature,
Receiving first inspection information for the meat from an inspection device;
The first inspection information for the meat is a value for each of a plurality of components of the meat, a first pH value of the meat, a first reflectivity value for each of a plurality of wavelengths of the meat, and a first image of the meat. including,
Determine a first freshness of the meat through a first freshness determination model using a first neural network based on the information on the meat and the first inspection information on the meat;
Transmitting information related to sterilization of the meat to a sterilizer based on the information on the meat and the first freshness;
Sterilizing water is sprayed on the meat by the sterilizing device according to information related to the sterilization of the meat;
Transmitting information on a storage method of the meat to a storage device based on the first freshness and a preset reference value;
The meat is stored frozen by the storage device based on the first freshness being less than the preset reference value,
Receiving an order message for the meat from at least one customer terminal;
Transmitting information related to the freshness of the meat to the at least one customer terminal based on the order message,
management server.
According to claim 6,
The information related to the freshness of the meat includes a second freshness of the meat and a second image of the meat,
The second freshness of the meat is determined through a second freshness determination model using a second neural network based on the information about the meat, the storage condition information about the meat, and the second inspection information about the meat;
Based on the receipt of the order message, a release message is transmitted to the storage device and the inspection device;
Storage state information for the meat is received from the storage device based on the shipment message,
The storage state information includes information about the storage temperature of the meat, the storage time of the meat, and the storage method of the meat,
Second inspection information for the meat is received from the inspection device based on the shipment message,
The second inspection information for the meat includes a second pH value of the meat measured by the inspection device, a second reflectance value for each of a plurality of wavelengths of the meat measured by a spectrometer provided in the inspection device, and Including a second image of the meat taken by the inspection device,
management server.
According to claim 7,
A plurality of ingredients for the meat are measured by an electronic nose provided in the inspection device,
The plurality of ingredients for the meat include cadaverine, putrescine, xanthine and hypoxanthine,
The first pH value of the meat and the second pH value of the meat are measured based on the color of the cellulose paper provided in the test device,
A first reflectance value for each of a plurality of wavelengths of the meat and a second reflectance value of each of a plurality of wavelengths of the meat are measured by a spectrometer provided in the inspection device,
The first image of the meat and the second image of the meat are taken by a camera provided in the inspection device.
management server.
According to claim 8,
The sterilizing water is generated through corona discharge by the sterilizing device,
The information related to the sterilization of the meat includes the capacity of the sterilizing water,
The capacity for the sterilizing water is determined by the following equation,

In the above equation, V is the capacity for the sterilizing water, P _e is the expected storage period for the meat, P _avg is the average storage period for the meat, and m _d is the portion of the meat. is a preset density value for, wherein w _m is the weight of the meat, f is the first freshness,
The P _e , the P _avg and the m _d in the above equation are determined to be different values depending on the type of meat and the part of the meat,
management server.
According to claim 7,
A first input vector and a second input vector are generated through data preprocessing of the information on the meat and the first inspection information on the meat;
The first input vector is a value for a type of meat, a value for a part of meat, a value for a period elapsed after slaughter, a value related to aging of meat, a value for each of a plurality of components of meat, and a first input vector for meat. It consists of a pH value and a first reflectance value for each of a plurality of wavelengths of meat,
The second input vector consists of pixel values for the first image of meat,
The first neural network includes a first input layer, one or more first hidden layers and a first output layer;
Each of the learning data consisting of a plurality of first input vectors, a plurality of second input vectors, and a plurality of first correct answers is input to the first input layer of the first neural network, and is input to the at least one first hidden layer and the first hidden layer. It passes through 1 output layer and is output as a first output vector, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is connected to the first output vector. A first loss value is output using a first loss function that compares a first correct answer vector for learning data of , and parameters of the first neural network are learned in a direction in which the first loss value becomes smaller,
A first freshness of the meat is output based on input of the first input vector and the second input vector to the first freshness determination model;
A third input vector and a fourth input vector are generated through data preprocessing on the information on the meat, the storage state information on the meat, and the second inspection information on the meat;
The third input vector is composed of a value for the type of meat, a value for a part of the meat, a value related to the storage condition of the meat, a second pH value of the meat, and a second reflectance value for each of a plurality of wavelengths of the meat, ,
The fourth input vector consists of pixel values for a second image of meat,
The second neural network includes a second input layer, one or more second hidden layers, and a second output layer;
Each of the learning data consisting of a plurality of third input vectors, a plurality of fourth input vectors, and a plurality of second fresh answers is input to the second input layer of the second neural network, and is input to the at least one second hidden layer and the second freshness. It passes through two output layers and is output as a second output vector, the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer is connected to the second output vector. A second loss value is output using a second loss function that compares a second answer vector for the learning data of , and the parameters of the second neural network are learned in a direction in which the second loss value becomes smaller,
A second freshness of the meat is output based on the third input vector and the fourth input vector being input to the second freshness determination model.
management server.
A computer program stored in a computer readable recording medium in order to execute the method of claim 1 in combination with hardware.
A computer readable recording medium storing a computer program combined with hardware to execute the method of claim 1.

Images