KR102097248B1 - Method for controlling the seafood transport environment - Google Patents

Abstract

Disclosed is a method of controlling a seafood transport environment. According to an embodiment of the present invention, a method of controlling a seafood transport environment based on artificial intelligence comprises: a step in which seafood detection video cameras in a transport water tank photographs a video for each segment for two minutes; a step in which a water quality management sensor acquires water quality state data; a step in which an embedded computer of the transport water tank acquires automobile operation information; a step in which the embedded computer generates a first input signal based on a video photographing result, a water quality state data acquisition result and an automobile operation information acquisition result; a step in which the embedded computer inputs a first input signal to a convolution neural network of a block chain network including the embedded computer; a step in which the embedded computer acquires a first output signal from the convolution neural network; a step in which the embedded computer controls a liquid oxygen controller and a water quality manager based on the first output signal; a step in which the embedded computer re-acquires the video for each segment, the water quality state data and the automobile operation information every two minutes based on a control result; a step in which the embedded computer updates the first input signal based on a re-acquisition result; a step in which the embedded computer generates a first learning signal based on abnormal seafood detection result data within the first input signal; and a step in which the embedded computer learns by applying the first learning signal to the convolution neural network based on a generation result of the first learning signal.

Description

METHOD FOR CONTROLLING THE SEAFOOD TRANSPORT ENVIRONMENT}

The embodiments below relate to a method of controlling a marine product transportation environment.

Control of oxygen saturation, temperature and salinity using liquefied oxygen is essential for the transportation of aquatic products. In general, the transportation process of aquatic products provides an automated control mechanism for such adjustment, but it is a reality that a means for providing an environment suitable for each aquatic product is not properly provided. In addition, the car operating elements of the transportation process are not properly reflected, and accordingly, the mortality rate of marine products is significantly increasing. Therefore, research is needed to improve the safety and freshness of the marine product transportation process and to adapt it to changing environments.

KR101378894 KR101542718 KR1020160077863 KR1020190044814

The embodiments are intended to safely and freshly manage aquatic product transportation by applying deep learning technology to a method of controlling a marine product transportation environment.

The embodiments are intended to provide feedback on environmental information for aquatic products based on the information on the aquatic product.

The embodiments intend to make information big data through a blockchain network and use enhanced security.

A method of controlling a marine product transportation environment according to an embodiment includes a method of controlling a transportation environment of aquatic products based on artificial intelligence, wherein the marine products detection image cameras in a transportation tank capture an image of each segment for 2 minutes; Obtaining a water quality state data by the water quality management sensor, wherein the water quality state data includes an amount of water, salinity, oxygen saturation, temperature, and pollution level; Obtaining, by the embedded computer of the tank for transportation, vehicle operation information, wherein the vehicle operation information includes a vehicle average speed, an instantaneous speed, a planned transportation distance, and a remaining transportation distance; Generating, by the embedded computer, a first input signal based on the image photographing result, the result of acquiring the water quality status data, and the result of acquiring the automatic manipulation information; Inputting the first input signal to the convolutional neural network of a blockchain network including the embedded computer by the embedded computer; Acquiring a first output signal from the convolutional neural network by the embedded computer; Based on the first output signal, the embedded computer controlling a liquid oxygen regulator and a water quality controller; Re-acquiring the image for each segment, the water quality data, and the vehicle operation information at 2-minute intervals based on the control result; Updating, by the embedded computer, the first input signal based on the re-acquisition result; Generating, by the embedded computer, a first learning signal based on the result of detecting the abnormal seafood in the first input signal; And based on a result of generating the first learning signal, the embedded computer may learn by applying the first learning signal to a convolutional neural network.

According to an embodiment, the step of generating the first input signal by the embedded computer may include acquiring photographs of the cameras as pictures of 60 frames per second; Classifying the same time frames of the respective cameras into same time picture data of the first input signal; Generating the result of detecting the abnormal aquatic product for a target aquatic product having no motion through frame-by-frame comparison of the same-time photo data; Recording the water quality state data and the vehicle operation information at 60 standardized values per second; And generating a data sheet combining the same-time photograph data, the abnormal seafood detection result data, the water quality condition data, and the vehicle operation information in 60 unit units per second.

According to an embodiment, the step of generating the abnormal seafood detection result data may include identifying target marine products from the same-time photographic data; Identifying a marine product having no change of 300 pixels or more during 1800 frames among the target marine products through frame-by-frame comparison of the same-time photo data; Classifying the unchanged marine product as an abnormal marine product and storing additional picture information in the remarks of the data sheet, and recording the number; And correcting the abnormal seafood detection result data based on the first output for the vehicle manipulation information and the same-time photographic data, when the unchanged marine product shows a change of 300 pixels or more afterwards.

According to one embodiment, the blockchain network is a block comprising a comparison photograph data containing the average information of the target marine products and a database including an ideal water quality state and a vehicle operation state and the pre-trained convolutional neural network handling the same. field; Chains connecting each block in chronological order; And the network storage devices storing the respective blockchains, wherein the network storage devices are first network storage devices including primary providers of the targeted marine products; A second network storage device including manufacturers for manufacturing the water tank for transportation; A third network storage device including transporters transporting the targeted marine products to a secondary provider; A fourth network storage device including secondary providers receiving the target marine products; And a high-speed Internet connection network connecting the network storage devices.

According to an embodiment, the convolutional neural network inputs a first input signal in the form of a data sheet including the same time photograph data, the abnormal seafood detection result data, the water quality status data, and the vehicle operation information, and the target seafood Salinity, oxygen saturation and temperature of the water based on the type, size, number of the fish, the type, size, number of the abnormal aquatic products and the comparison of the water quality data and the vehicle operation information with the ideal water condition and the vehicle operation status A first output signal including correction information for the output may be used as an output, and learning may be performed through a first learning signal generated based on data stored in the remarks of the data sheet.

The apparatus according to an embodiment may be controlled by a computer program stored in a medium in order to execute the method of any one of the above-described methods in combination with hardware.

Embodiments can safely and freshly manage aquatic product transportation by applying deep learning technology to a method of controlling the aquatic product transportation environment.

Embodiments may provide feedback on environmental information for aquatic products based on information on the aquatic product.

Embodiments can make information big data through a blockchain network and use enhanced security.

1 is a flowchart illustrating a method of controlling a marine product transportation environment according to an embodiment.
2 is a view for explaining a method for generating photographic data at the same time according to an embodiment.
3 is a view for explaining a process of generating data for detecting abnormal seafood according to an embodiment.
4 is a view for explaining a blockchain network according to an embodiment.
5 is a diagram for describing a convolutional neural network according to an embodiment.
6 is an exemplary view of a configuration of an apparatus according to an embodiment according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, various changes may be made to the embodiments, and the scope of the patent application right is not limited or limited by these embodiments. It should be understood that all modifications, equivalents, or substitutes for the embodiments are included in the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be implemented in various forms. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes modifications, equivalents, or substitutes included in the technical spirit.

The terms first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from other components. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

When an element is said to be "connected" to another element, it should be understood that other elements may be present, either directly connected to or connected to the other element.

The terms used in the examples are for illustrative purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, the terms "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts or combinations thereof described herein, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the embodiment belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, when it is determined that detailed descriptions of related known technologies may unnecessarily obscure the subject matter of the embodiments, detailed descriptions thereof will be omitted.

Embodiments may be implemented in various types of products, such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent cars, kiosks, and wearable devices.

1 is a flowchart illustrating a method of controlling a marine product transportation environment according to an embodiment.

According to an embodiment, in a method of controlling a transportation environment of aquatic products based on artificial intelligence, aquatic product detection image cameras in a water tank for transportation may capture an image of each segment for 2 minutes (101).

According to one embodiment, the transport tank may include, but is not limited to, a seafood detection image camera, a water quality management sensor, an embedded computer, a liquid oxygen regulator, a water quality manager, and other electronic devices and control devices.

According to one embodiment, the electronic device may be a smart home appliance with a communication function. For smart appliances, for example, electronic devices are televisions, digital video disk (DVD) players, audio, refrigerators, air conditioners, vacuum cleaners, ovens, microwave ovens, washing machines, air cleaners, set-top boxes, TVs. It may include at least one of a box (eg, Samsung HomeSyncTM, Apple TVTM, or Google TVTM), game consoles, electronic dictionary, electronic keys, camcorder, or electronic picture frame.

According to an embodiment, the electronic device may include various medical devices (eg, magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), computed tomography (CT), imaging device, ultrasound device, etc.), navigation device, GPS receiver ( global positioning system receiver (EDR), event data recorder (EDR), flight data recorder (FDR), automotive infotainment devices, marine electronic equipment (e.g. navigational devices and gyro compasses, etc.), avionics, security It may include at least one of a device, a head unit for a vehicle, an industrial or household robot, an automated teller's machine (ATM) of a financial institution, or a point of sales (POS) of a store.

According to one embodiment, the electronic device is a furniture or part of a building / structure including a communication function, an electronic board, an electronic signature receiving device, a projector, or various measurement devices. It may include at least one of a device (for example, water, electricity, gas, or radio wave measurement devices). The electronic device according to an embodiment may be a combination of one or more of the various devices described above. Also, the electronic device according to an embodiment may be a flexible device. Also, it is apparent to those skilled in the art that the electronic device according to an embodiment is not limited to the above-described devices. The term user used in various embodiments may refer to a person using an electronic device or a device using an electronic device (eg, an artificial intelligence electronic device).

An electronic device according to an embodiment includes a processor, a memory, a user interface, and a communication interface, and may be connected to another electronic device through a network. The communication interface may transmit and receive data to and from other electronic devices within a predetermined distance through a wired, wireless network, or wired serial communication. The network enables wired and wireless communication between electronic devices and various entities according to an embodiment. The electronic device can communicate with various entities over the network, and the network can use standard communication technologies and / or protocols. At this time, the network (network) includes, but is not limited to, the Internet (Internet), a local area network (LAN), a wireless local area network (LAN), a wide area network (WAN), a personal area network (PAN), and the like. Anyone who has ordinary knowledge in the field of communication technology can know that it may be another kind of network capable of transmitting and receiving information.

The embedded computer according to an embodiment may be an electronic device including a communication function. For example, the electronic device includes a smart phone, a tablet personal computer (PC), a mobile phone, a video phone, an e-book reader, a desktop personal computer (PC), and a laptop. A laptop personal computer (PC), a netbook computer, a personal digital assistant (PDA), a portable multimedia player (PMP), an MP3 player, a mobile medical device, a camera, or a wearable device (eg It may include at least one of a head-mounted-device (HMD) such as electronic glasses, an electronic garment, an electronic bracelet, an electronic necklace, an electronic appcessory, an electronic tattoo, a smart car, or a smart watch. You can.

The marine product detection image cameras according to an embodiment are detection image cameras for inspecting the life reaction of aquatic products, and a wide-angle lens may be fixed to divide the interior of the water tank into a total of nine divisions. Each camera can be located where each side of the hexahedral tank is divided into nine divisions, and can be shot in 24 frames, 30 frames, or more than 60 frames, generally based on 60 frames per second. The standard two-minute imaging process is performed, and after the liquid oxygen regulator and the water quality controller control are completed, the two-minute imaging may be continued.

According to one embodiment, the water quality sensor may acquire water quality status data (102).

The water quality management sensor according to an embodiment is an equipment that collects status data information of water quality, and each of them may be recorded in numerical values suitable for a unit. Water quality data may include, but are not limited to, the amount of water, salinity, oxygen saturation, temperature, and contamination. Pollution degree is based on heavy metal content, unsaturated oil content and green algae production, but is not limited thereto. The amount of water in ml, the salinity in g / ml, the oxygen saturation in%, the temperature in ℃ and the degree of contamination can be used for each standard unit.

According to one embodiment, the embedded computer of the transportation tank may acquire vehicle operation information (103).

According to an embodiment, the vehicle operation information may include an average vehicle speed, an instantaneous speed, a planned transportation distance, and a remaining transportation distance. The average vehicle speed and instantaneous speed information may be collected through GPS information embedded in the embedded computer, and the estimated transportation distance and remaining transportation distance may be calculated based on GPS information according to a user's destination input.

According to an embodiment, the information included in the vehicle operation information may cause shaking, tilting, rotation, and aquatic stress in the tank, and may be included in an input signal for safe distribution of aquatic products.

According to an embodiment, the embedded computer may generate the first input signal based on the image capturing result, the water quality data acquisition result, and the autonomous manipulation information acquisition result (104).

According to an embodiment, the embedded computer may generate the first input signal in the form of a data sheet, and each result may be recorded in pictures and numerical values. The description of the generation of the first input signal will be described later with reference to FIG. 2.

According to one embodiment, the embedded computer may input the first input signal to the convolutional neural network of the blockchain network including the embedded computer (105).

The convolutional neural network according to an embodiment enables the user to check the type, size, number, etc. of aquatic products based on the same time photograph data according to the result of the imaging, and obtain appropriate adjustment data based on the contents of the database. Such a convolutional neural network is composed of a feature extraction neural network and a classification neural network, and the feature extraction neural network proceeds by stacking the input signal sequentially in a convolutional layer and a pooling layer. The convolution layer includes a convolution operation, a convolution filter, and an active function. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. The active function generally uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The pooling layer is a layer that serves to reduce the matrix size of the input, and uses a method of extracting representative values by grouping pixels in a specific area. In the calculation of the pooling layer, an average value or a maximum value is generally used, but is not limited thereto. The operation is performed using a square matrix, and generally uses a 9X9 matrix. The convolutional layer and the pooling layer alternately repeat until the input is small enough while maintaining the difference.

According to one embodiment, the classification neural network has a hidden layer and an output layer. In the convolutional neural network for a marine product transportation control method, there are generally three or more hidden layers, and each hidden layer is designated as 100 nodes, but may be set to more or less depending on the case. The active function of the hidden layer uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The total number of output layer nodes of the convolutional neural network can be 80. The output layer activation function of the classification neural network uses a softmax function. The softmax function is a representative function of one-hot encoding, and the sum of all output nodes is 1 in total, and the output of the output node having the largest value is 1, and the output of the remaining output nodes is 0. . It is possible to select only one of the 80 outputs through the Softmax function.

The blockchain network according to an embodiment is composed of blocks storing a database and a chain connecting them in chronological order, and the database is a comparative picture data containing average information of marine products and an ideal water quality state and a car operation state accordingly You can save them in data sheet format. The stored database is managed as big data, and the blockchain network can help securely store information in this database and make it available to limited users. The description of the blockchain network and the convolutional neural network will be described later with reference to FIGS. 4 and 5.

According to one embodiment, the embedded computer may obtain a first output signal from the convolutional neural network (106).

According to an embodiment, the convolutional neural network may have 80 outputs, each of which may be the number of aquatic products handled by users in the blockchain network and related database viewing information. The first output signal may include correction information for salinity, oxygen saturation, and temperature of water based on comparison of the water quality condition data and the vehicle operation information with the ideal water condition and the vehicle operation status through one of the 80 outputs. Each piece of information can serve as a signal to control the liquid oxygen regulator and water quality controller.

According to one embodiment, based on the first output signal, the embedded computer may control the liquid oxygen regulator and the water quality controller (107).

Liquid oxygen regulator according to an embodiment is a device for adjusting the oxygen saturation inside the water, it can be controlled by exposing the liquefied oxygen to water. A control signal may be generated based on the difference between the ideal oxygen saturation and the actual oxygen saturation from the first output signal to determine whether liquid oxygen is exposed. If the oxygen saturation level is excessive, the equipment can be stopped, the results observed, and then readjusted.

The water quality manager according to an embodiment is equipment that can manage the salinity, temperature, and contamination of water. Inside the water quality manager, there is a storage tank that can store sodium chloride, and if necessary, sodium chloride can be exposed to the water to control the salinity of the water. When the salinity is excessive, the salinity can be lowered by separating water and sodium chloride through a sodium chloride purifier installed inside the water quality manager. The temperature can be controlled through a heater and a cooler inside the water quality manager. The degree of contamination can be managed through a filter inside the water quality controller, and the filter can send a replacement signal to the outside of the water tank as an acoustic and lighting signal depending on the replacement cycle and the degree of contamination. To manage the pollution level, the water quality controller can generate a wave of water by emitting an appropriate level of wavelength.

According to one embodiment, based on the control result, images for each segment, water quality data, and vehicle operation information may be re-acquired at 2-minute intervals. The image for each segment, water quality data, and vehicle operation information may be obtained in the same manner as in the conventional method, and may be continuously obtained based on the interval of 2 minutes.

According to an embodiment, based on the result of the re-acquisition, the embedded computer may update the first input signal. The first input signal may be updated based on the newly acquired image for each segment, water quality status data, and vehicle operation information, and thus the updated first output signal may be obtained. The series of processes are repeated at intervals of 2 minutes, and can be repeated until the time when the embedded internal GPS recognizes the arrival of the destination.

According to an embodiment, the embedded computer may generate the first learning signal based on the result data of detecting the abnormal seafood in the first input signal (108).

According to an embodiment, the embedded computer may generate the first learning signal based on the result data of the abnormal seafood detection found during the update of the first input signal. The first learning signal may basically include the same information as the first input signal, but may be generated by selecting only the abnormal seafood detection result data. The description of the abnormal seafood detection result data will be described later with reference to FIG. 3.

According to an embodiment, based on the result of generating the first learning signal, the embedded computer may learn by applying the first learning signal to the convolutional neural network (109).

According to an embodiment, the convolutional neural network may learn the neural network through the first learning signal and update the database. All update information can be stored hourly through the blockchain network, and can be inquired by users when necessary.

The marine product transportation control method according to an embodiment may apply deep learning technology to safely and freshly manage marine product transportation.

2 is a view for explaining a method of generating photographic data 202 at the same time according to an embodiment.

Referring to FIG. 2, generation of the same-time photo data 202 may be achieved through image capturing results 201 for each segment.

According to an embodiment, the embedded computer may acquire the photographing result 201 of the cameras as a picture of 60 frames per second in the process of generating the first input signal. The image shooting result may be generally composed of 60 frames per second, but may be more or less in some cases. Each camera can consist of a total of 54, each of 9 divisions along the six sides of the cube.

According to an embodiment, the embedded computer may classify the same time frame of each camera as the same time picture data 202 of the first input signal.

Cameras according to an embodiment may proceed to shooting based on precisely coordinated time data, and at the same time, starting at 0 frames of the reference point, 60 frames per second may be taken. Each camera can be divided into numbers such as first, second, and third, and can be expressed in Korean and English depending on the case. By synchronizing each separated camera in units of frames, simultaneous frames can be combined to create simultaneous photographic data 202 with the output of 9 images on each side of the cube. The same-time photograph data 202 may be one of photographing results included in the first input signal.

According to an embodiment, the embedded computer may generate abnormal seafood detection result data for a target marine product without movement through frame-by-frame comparison of the same-time photo data. The description of the abnormal seafood detection result data will be described later with reference to FIG. 3.

According to an embodiment, the embedded computer may record water quality status data and vehicle operation information at 60 standardized values per second, along with photographic data and abnormal fish detection result data at the same time. The embedded computer can generate a data sheet that combines simultaneous photographic data, abnormal seafood detection result data, water quality status data, and vehicle operation information in 60 unit units per second.

Water quality data and vehicle operation information according to an embodiment may be recorded with numerical information in units as described in FIG. 1, and may acquire numerical information at 60 per second for synchronization with photographic data at the same time. 60 numerical information per second is information for synchronization, and a significant data change can be set based on a trend line through about 1800 numerical information. The data sheet combined with 60 unit units per second may be another representation of the first input signal.

3 is a view for explaining a process of generating data for detecting abnormal seafood according to an embodiment.

According to an embodiment, the embedded computer may identify target marine products 301 from the photographic data at the same time in the process of generating the result data for detecting abnormal marine products.

According to one embodiment, the embedded computer may go through the process of identifying the same target aquatic products 301 on the same time photographic data taken by cameras paired with nine on each side of the cube. The photos taken by each camera can record the positional coordinates of the target marine products 301 based on the individual XY coordinates, and the X coordinate of one side can function as the X coordinate, Y coordinate and Z coordinate of the other side. have. For example, on the same-time photographic data as viewed from above, the X-coordinate may intersect two faces containing two parallel X-axes. The planes that include these two X-axes can function identically as the X-axis. Conversely, the Y coordinate on the same time photograph data viewed from the same above can function as the X axis on two sides including two parallel Y axes. However, in order to avoid the confusion that may arise from this, the X-axis, Y-axis and Z-axis on the water tank can be arbitrarily set, and zero point can likewise be set. In this case, each photograph of the same time can be calculated by encoding the coordinate values according to an arbitrarily set axis. Based on the coordinate information, the target seafoods 301 may have respective position coordinates, and the target seafoods captured by the same position coordinates from different cameras may be defined as the same target seafood. The target marine products 301 overlapping in the same time photograph data or captured by only one camera may be calculated by reflecting the location data in the next same time photograph data. In the same-frame photographic data of the next frame, the target aquatic product having the closest position can be designated as an existing target aquatic product. Similarly, based on this, it is possible to designate target aquatic products by analyzing the photographic data of each side of the cube.

According to an embodiment, the embedded computer may identify a seafood product having no change of 300 pixels or more during 1800 frames of the target marine products 301 through frame-by-frame comparison of the photographic data at the same time.

According to an embodiment, the embedded computer may identify a seafood product having no change of 300 pixels or more during 1800 frames corresponding to a time of 30 seconds in the photographic data at the same time. 300 pixels may be calculated based on a line in which the appearance of the target marine product is separated from the background, but the size may be adjusted according to the number of pixels in which the target marine product on the corresponding photographic data is captured. The adjustment process can be performed automatically by the embedded computer.

According to one embodiment, the embedded computer may classify the unchanged marine product as an abnormal marine product 302, store additional picture information in the remarks of the data sheet, and record the number. The embedded computer may add a remark to the data sheet in the first input signal, and when an abnormal aquatic product 302 is detected, add photo information including all the same time photographic data capturing the abnormal aquatic product 302. If there is more than one corresponding aquatic product 302, it is possible to add photo information of all the aquatic aquatic products 302 including the number. The information in the remarks column added in this way may be collectively referred to as an abnormal seafood detection result data.

According to an embodiment of the present disclosure, when an unchanged marine product exhibits a change of 300 pixels or more on the same-frame photo data of subsequent frames, the embedded computer detects the abnormal product based on the first output of the vehicle operation information and the same-time photo data. Data can be modified. The above-mentioned aquatic products 302 correspond to the aquatic products that have died, and do not correspond to aquatic products that have been stunned or stopped at the moment. Accordingly, when the corresponding aquatic product 302 shows movement of 300 pixels or more during 1800 frames in subsequent frames, the aquatic product result data may be corrected based on the vehicle operation information and the first output. The vehicle operation information may reflect the amount of water movement according to the moving speed of the vehicle, and may be used as data for discriminating whether or not the seafood detected by the abnormal aquatic product 302 is moved. The first output is a response according to the first input and may be used as data for determining whether a wave of water generated by the water quality manager caused movement of the aquatic product detected as the abnormal aquatic product 302. Based on the data, when it is proved that the aquatic product detected as the abnormal aquatic product 302 is not the abnormal aquatic product 302, it is possible to generate an abnormal aquatic product detection result data by modifying the data, and based on this, the first aquatic product can be generated. The input signal and the learning signal can be updated.

The method for controlling the transportation of aquatic products according to an embodiment may feedback environmental information for aquatic products based on the information of the abnormal aquatic products 302.

4 is a view for explaining a blockchain network according to an embodiment.

Referring to FIG. 4, the blockchain network includes a block 401 including a comparative photo data containing average information of target marine products and a database including an ideal water quality state and a vehicle operation state and the pre-trained convolutional neural network handling the same. )field; Chains 402 connecting each block 401 in chronological order; And a first 410, a second 420, a third 430, and a fourth network storage 440 that stores each blockchain.

According to an embodiment, the block 401 of the blockchain network is a database that stores comparative photograph data containing average information of target marine products and thus ideal water quality and vehicle operation state in a data sheet format and pre-trained to deal with it And a convolutional neural network. Each block 401 is generally connected in chronological order, so that new blocks 401 can be produced at 10 minute intervals. The contents of the already generated block 401 are stored in all network storage devices, and cannot be changed unless the majority of the contents are changed in time. For example, in a blockchain network having a total of 3 network storage devices, when it is assumed that there is one block 401 for each network storage device, if the contents of two or more blocks 401 cannot be changed within a limited time, Each block 401 may change the value of the block 401 having a different content from the majority to be equal to the majority by verification. Accordingly, it is possible to maintain high security. In fact, the number of network storage devices participating in the blockchain network may reach tens to hundreds of thousands, and thus, it may exhibit higher security.

Chains 402 according to an embodiment may be configured with a hash value. The chains 402 allow the blocks 401 to be consecutive in chronological order. At this time, each block 401 may be connected using a hash value. In block 401, a database and a hash value of the database, a previous header, and a header of the current block may be stored. Here, the header of the current block functions as a previous header in the next block, so that each block 401 can be organically connected. In addition, the hash value is transformed into a completely different form when the contents of the block are changed even slightly, which effectively prevents an attempt to change the contents of the database. Since the header of the current block becomes the total hash value including the database, the hash value of the database, and the previous header, it is difficult to successfully attempt to compromise security by effectively modifying the database and the hash value. Because when the database and hash values are modified, the contents of the header are changed, and accordingly, the previous header that enters the next block is also changed, and accordingly, the header of the block is also changed, so that the previous header of the next block can be changed again. That is, all subsequent blocks 401 must be hacked. Therefore, it is possible to increase the security of the blockchain with the chain 402 through the hash value.

According to one embodiment, the network storage devices include a first network storage device 410 including primary providers of target marine products; A second network storage device 420 including manufacturers for manufacturing transportation tanks; A third network storage 430 including transporters that transport the targeted marine products to a secondary provider; A fourth network storage device 440 including secondary providers for receiving target marine products; And a high-speed Internet connection network 403 connecting each network storage device. The network storage devices classified as the first, second, third, and fourth may be determined according to the number of practitioners included, the number of users, and the number of storage devices.

According to an embodiment, the first network storage device 410 may include primary providers of target marine products, and primary providers of target marine products may be one company or more. The number of first network storage devices 410 may be determined according to the number of storage devices used by each company. The first network storage device 410 may check transportation information and supply amount change information of the provided marine products, and may process orders entered through an automatic order signal in the blockchain network.

According to one embodiment, the second network storage 420 may include manufacturers that manufacture a water tank for transportation. The second network storage device 420 is a network device including manufacturers that manufacture transport tanks, and the number may be determined according to the number of manufacturers and the number of storage devices. The second network storage device 420 can check in real time whether or not the tanks for transportation manufactured by them are real-time, and can manually learn and correct the convolutional neural network learned based on information transmitted from the tanks for transportation.

According to one embodiment, the third network storage 430 may include transporters that transport the targeted seafood to a secondary provider. The third network storage device 430 may include people who operate an actual transportation tank, and may include a practical user of the method for controlling the transportation of aquatic products. Accordingly, the third network storage device 430 may be a storage device located in the embedded computer of the corresponding transport tank, and thus may perform functions other than the storage device.

According to an embodiment, the fourth network storage 440 may include secondary providers that receive targeted marine products. Users of the fourth network storage device 440 can manually or automatically generate an order signal, and check the transportation information and the change in the amount of purchase of marine products ordered through the connection of the blockchain network.

The high-speed Internet connection network 403 according to an embodiment generally refers to an Internet connection network having a speed of 10 Mb / s or more, and includes a local area network (LAN), a wireless LAN (Wireless) as a connection network including wired, wireless, and optical cable technologies. Local Area Network (WAN), Wide Area Network (WAN), Personal Area Network (PAN), and the like.

5 is a diagram for describing a convolutional neural network according to an embodiment.

Blocks according to an embodiment may include a pre-trained convolutional neural network 510 and a database 520, a first input signal 501 as an input, and a first output signal 502 as an output. , Learning through the learning signal 503.

According to an embodiment, the first input signal 501 that is the input of the convolutional neural network 510 may store the same-time photographic data, anomaly detection result data, water quality data, and vehicle operation information in the form of a data sheet.

According to one embodiment, the first output signal 502, which is the output of the convolutional neural network 510, is ideal for the type, size, number, and anomalies of the marine products, the size, number, quality of the marine products, and vehicle operation information. It may include correction information for salinity, oxygen saturation and temperature of water based on a comparison of water quality and vehicle operating conditions.

According to an embodiment, the learning signal 503 for learning of the convolutional neural network 510 may be generated based on the abnormal seafood detection result data stored in the remarks of the data sheet. The learning signal 503 is composed of a data sheet having the same configuration as the first input signal 501, and only the recording of the result data of abnormal seafood detection can be used as the input value.

The learning signal 503 according to an embodiment is made based on an error between a correct answer and an output value. In some cases, an SGD using a delta, a batch method, or a method using a back propagation algorithm may be used. According to the learning signal, the convolutional neural network 510 performs learning by modifying an existing weight, and may use momentum in some cases. The cost function can be used to calculate the error, and the cross entropy function can be used as the cost function.

According to an embodiment, the convolutional neural network 510 may learn to modify a data sheet of aquatic product average information and ideal water quality state and vehicle operation state in the database 520 based on the learning signal 503. The pre-trained convolutional neural network 510 has three or more hidden layers, and each hidden layer may have 50 or more hidden nodes. ReLU function, sigmoid function and tanh function can be used as the active function of each hidden node, but is not limited thereto. As a function of the output node, a softmax function using one-hot encoding can be used. The output selects only one classification according to the one-hot encoding technique, and can execute commands from the selected classification.

According to one embodiment, the database 520 may store information as big data, and may be continuously updated through a high-speed Internet connection network connected to a blockchain network.

The method for controlling the transportation of aquatic products according to an embodiment may make information big data through a blockchain network and use enhanced security.

6 is an exemplary view of a configuration of an apparatus according to an embodiment.

The device 1201 according to an embodiment includes a processor 1202 and a memory 1203. The device 1201 according to an embodiment may be the above-described server or terminal. The processor may include at least one of the devices described above with reference to FIGS. 1 to 5, or may perform the at least one method described with reference to FIGS. 1 to 5. The memory 1203 may store information related to the above-described method or a program implemented with the above-described method. The memory 1203 may be volatile memory or nonvolatile memory.

According to an embodiment, the processor 1202 may execute a program and control the device 1201. The code of the program executed by the processor 1202 may be stored in the memory 1203. The device 1201 is connected to an external device (for example, a personal computer or a network) through an input / output device (not shown), and can exchange data.

The embodiments described above may be implemented with hardware components, software components, and / or combinations of hardware components and software components. For example, the devices, methods, and components described in the embodiments include, for example, a processor, controller, arithmetic logic unit (ALU), digital signal processor (micro signal processor), microcomputer, field programmable gate (FPGA). It can be implemented using one or more general purpose computers or special purpose computers, such as arrays, programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. The processing device may run an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

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, or the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiments or may be known and usable by 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, DVDs, and magnetic media such as floptical disks. -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 code that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and / or data may be interpreted by a processing device, or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodied in the transmitted signal wave. The software may be distributed on networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

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

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

Claims (5)

A method of controlling a transportation environment for aquatic products based on artificial intelligence, the method comprising: capturing images of each segment for 2 minutes by marine product detection image cameras in a transportation tank;
Obtaining a water quality state data by the water quality management sensor, wherein the water quality state data includes an amount of water, salinity, oxygen saturation, temperature, and pollution level;
Obtaining, by the embedded computer of the transport tank, vehicle operation information, wherein the vehicle operation information includes an average vehicle speed, an instantaneous speed, a planned transportation distance, and a remaining transportation distance;
Generating, by the embedded computer, a first input signal based on the image photographing result, the result of acquiring the water quality status data, and the result of acquiring the automatic manipulation information;
Inputting the first input signal to the convolutional neural network of a blockchain network including the embedded computer by the embedded computer;
Acquiring a first output signal from the convolutional neural network by the embedded computer;
Based on the first output signal, the embedded computer controlling a liquid oxygen regulator and a water quality controller;
Re-acquiring the image for each segment, the water quality data, and the vehicle operation information at 2-minute intervals based on the control result;
Updating, by the embedded computer, the first input signal based on the re-acquisition result;
Generating, by the embedded computer, a first learning signal based on the result of detecting the abnormal seafood in the first input signal; And
Based on the result of generating the first learning signal, the embedded computer learning by applying the first learning signal to a convolutional neural network.
Containing
How to control the marine environment.
According to claim 1,
The step of generating the first input signal by the embedded computer is
Obtaining the photographing result of the cameras as a picture at 60 frames per second;
Classifying the same time frames of the respective cameras into same time picture data of the first input signal;
Generating the result of detecting the abnormal aquatic product for a target aquatic product having no motion through frame-by-frame comparison of the same-time photo data;
Recording the water quality state data and the vehicle operation information at 60 standardized values per second; And
Generating a data sheet combining the same-time photographic data, the abnormal seafood detection result data, the water quality condition data, and the vehicle operation information in 60 unit units per second.
Containing
How to control the marine environment.
According to claim 2,
The step of generating the abnormal seafood detection result data
Identifying target marine products from the same-time photographic data;
Identifying a marine product having no change of 300 pixels or more during 1800 frames among the target marine products through frame-by-frame comparison of the same-time photo data;
Classifying the unchanged marine product as an abnormal marine product and storing additional picture information in the remarks of the data sheet, and recording the number; And
Correcting the abnormal seafood detection result data based on the first output for the vehicle manipulation information and the photographic data at the same time, when the marine product without the change shows a change of 300 pixels or more afterwards.
Containing
How to control the marine environment.


delete delete

Images