A Method and System for Measuring and Feeding Marine Bait Based on the Internet of Things

Abstract

The present invention relates to a method and system for measuring and feeding marine bait based on the Internet of Things, belonging to the technical field of fishery bait feeding. It obtains the breeding biological characteristics of multiple target areas, determines the activity range and breeding density of target aquatic organisms according to the breeding biological characteristics of the multiple target areas; obtains the evaluation result of the nutrient content of the required nutrients in the bait, and combines the evaluation result, activity range and breeding density for estimation to obtain a preliminary feeding measurement value; feeds according to the preliminary feeding measurement value, and analyzes the survival rate of target aquatic organisms to obtain a first measurement correction plan; adjusts the feeding based on the first measurement correction plan, and calculates and analyzes the ammonia nitrogen decomposition rate in the current water body to obtain a second measurement correction plan; determines whether there is a fault in the bait feeding device and performs maintenance. The present invention can perform precise and efficient measurement control on marine bait feeding, improve the breeding quality and reduce feed waste.

Description

Technical Field

[0001] The present invention relates to the technical field of fishery bait feeding, and particularly relates to a shipborne bait feeding metering method and system based on the Internet of Things. Background Art

[0002] In the current fishery aquaculture industry, by introducing advanced aquaculture equipment, fishery aquaculture activities can be made faster, more efficient and more convenient, improving the overall quality of fishery aquaculture; and the most crucial link in fishery aquaculture is the bait feeding of target aquaculture organisms. The accuracy of bait feeding determines the growth quality and survival rate of target aquatic organisms, and can also greatly control the output of feed costs; however, the existing bait feeding equipment does not have an accurate feeding metering method, so that each specific feeding requires manual estimation and proportioning, which is time-consuming and laborious, and there are still large errors in the manually metered and proportioned feeding amounts, resulting in a large amount of waste and increasing the input of feeding costs; and the inaccurately metered and proportioned feeding amounts will lead to nutritional deficiencies and unbalanced health management of target aquatic organisms, reducing the aquaculture survival rate, and excessive bait will remain in the water body and decompose into a large amount of ammonia nitrogen, polluting the aquaculture water body and being unfavorable to high-quality aquaculture activities; at the same time, the errors caused by equipment failures will also lead to inaccurate feeding amounts; therefore, it is necessary to develop a method for accurately and efficiently measuring bait feeding to solve the above problems. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a shipborne bait feeding metering method and system based on the Internet of Things.

[0004] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of the present invention provides a shipborne bait feeding metering method based on the Internet of Things, including the following steps:

[0006] Obtain the aquaculture image data of multiple target areas within a preset time period, introduce the local binary pattern algorithm for feature extraction to obtain the aquaculture organism features of multiple target areas, and determine the activity range and aquaculture density of target aquatic organisms according to the aquaculture organism features of multiple said target areas;

[0007] Obtain the required nutrient components of target aquatic organism individuals, analyze and evaluate the nutrient component content of the required nutrient components in the current bait to obtain an evaluation result, and estimate based on the evaluation result, the activity range and the aquaculture density to obtain a preliminary feeding metering value;

[0008] Feed according to the preliminary feeding measurement value, obtain the survival rate of the target aquatic organism, construct a trained survival rate prediction model for prediction, obtain the survival rate interval with insufficient nutrient content, analyze whether the survival rate of the target aquatic organism is within the survival rate interval, and obtain the first measurement correction plan;

[0009] Based on the first measurement correction plan, adjust the feeding, obtain the actual survival rate after the first correction. If the actual survival rate after the first correction is not within the survival rate interval of water body environmental pollution, calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain the second measurement correction plan;

[0010] Based on the second measurement correction plan, adjust the feeding, obtain the actual survival rate after the second correction. If the actual survival rate after the second correction is not within the survival rate interval of equipment failure, construct a curve graph to analyze whether there is a fault in the bait feeding equipment and perform repair and maintenance.

[0011] Furthermore, in a preferred embodiment of the present invention, obtain the breeding image data of multiple target areas within a preset time period, introduce the local binary pattern algorithm for feature extraction to obtain the breeding organism features of multiple target areas, and determine the activity range and breeding density of the target aquatic organism according to the breeding organism features of multiple target areas, which specifically includes the following steps:

[0012] Based on the Internet of Things technology, control the remote sensing camera on the fishing boat to take images of the target aquatic organism, and obtain the breeding image data of multiple target areas within a preset time period;

[0013] Introduce the local binary pattern algorithm to extract the features of the breeding organisms from the breeding image data of multiple target areas. Cut each breeding image data into several local blocks, compare the pixel points within each local block, and generate several binary coding information;

[0014] Convert the several binary coding information into different local binary patterns, count the frequencies of the different local binary patterns appearing within each local block, draw and output the local binary pattern histogram to obtain the breeding organism features of multiple target areas;

[0015] Calculate the Euclidean distances between the breeding organism features of multiple target areas. At the same time, introduce the hot spot radius algorithm to perform hot spot area planning on the calculated multiple Euclidean distances, construct the first activity hot spot map, and determine the activity range and breeding density of the target aquatic organism according to the first activity hot spot map.

[0016] Further, in a preferred embodiment of the present invention, for obtaining the required nutrient components of the target aquatic organism individual, analyzing the nutrient content of the required nutrient components in the current bait and evaluating it to obtain an evaluation result, and estimating based on the evaluation result, the activity range and the breeding density to obtain a preliminary feeding measurement value, specifically including the following steps:

[0017] Obtain the species information of the target aquatic organism, search for the relevant nutrient information required for the normal growth of the species information of the target aquatic organism based on the big data network to obtain the required nutrient components of the target aquatic organism individual, and at the same time obtain the required intake of each nutrient component;

[0018] Obtain the ingredient information of several kinds of the current bait, construct a knowledge graph, retrieve the nutrient components contained in the ingredient information of several kinds in the knowledge graph to obtain a retrieval result, and screen and mark the ingredient information with the same required nutrient components as the target aquatic organism in the retrieval result to obtain target ingredient information;

[0019] Based on the big data network, obtain the standard nutrient content interval corresponding to the target ingredient, and obtain the ratio quality of the target ingredient. Introduce the fuzzy C-means algorithm to calculate the initial membership degree of the ratio quality and each standard nutrient content in the standard nutrient content interval, construct a clustering center, update the position of the clustering center based on the membership degree until the maximum number of iterations is satisfied, and generate multiple membership degrees;

[0020] Construct an evaluation model, screen out the standard nutrient content corresponding to the maximum membership degree as the result output among multiple membership degrees to obtain the nutrient content of the current bait, and import the nutrient content of the current bait into the evaluation model for evaluation to obtain an evaluation result;

[0021] Calculate the ratio between the required intake of each nutrient component and the nutrient content of the current bait to obtain an individual feeding ratio, and estimate based on the comprehensive individual feeding ratio, the evaluation result, the activity range and the breeding density to obtain a preliminary feeding measurement value.

[0022] Further, in a preferred embodiment of the present invention, for feeding according to the preliminary feeding measurement value, obtaining the survival rate of the target aquatic organism, constructing a trained survival rate prediction model for prediction to obtain a survival rate interval with insufficient nutrient content, and analyzing whether the survival rate of the target aquatic organism is within the survival rate interval to obtain a first measurement correction plan, specifically including the following steps:

[0023] Input the preliminary feeding measurement value of the target area into the bait feeding device for measurement feeding, and reconstruct the heat map after a preset time period to obtain a second activity heat map;

[0024] Obtain all non - hot spots and all feature coincidence points in the target area based on the second activity hot - spot map, define the non - hot spots and the feature coincidence points as the low - activity points of the target aquatic organisms, and calculate the ratio of the low - activity points of all target aquatic organisms to all hot spots in the second activity hot - spot map to obtain the survival rate of the target aquatic organisms;

[0025] Obtain the corresponding survival rates under the influence of different aquaculture condition factors through the big - data network, construct a survival - rate prediction model based on the support vector machine algorithm, and train and verify the corresponding survival rates under the influence of different aquaculture condition factors in the survival - probability prediction model to obtain a trained survival - rate prediction model; wherein, the different aquaculture condition factors include insufficient nutrient content, water - body environmental pollution, and equipment failure;

[0026] Extract the survival - rate interval of insufficient nutrient content based on the trained survival - rate prediction model, and determine whether the survival rate of the target aquatic organisms is within the survival - rate interval of insufficient nutrient content;

[0027] If not, introduce the hash algorithm to calculate the hash value between the lower limit value in the survival - rate interval and the survival rate of the target aquatic organisms, and perform metering regulation on the required feeding amount in the target area according to the hash value to obtain the first metering correction plan.

[0028] Furthermore, in a preferred embodiment of the present invention, perform feeding adjustment based on the first metering correction plan to obtain the actual survival rate after the first correction. If the actual survival rate after the first correction is not within the survival - rate interval of water - body environmental pollution, calculate and analyze the ammonia - nitrogen decomposition rate in the current water body to obtain the second metering correction plan, which specifically includes the following steps:

[0029] Perform metering feeding correction on the bait feeding equipment according to the first metering correction plan, and calculate the survival rate of the target aquatic organisms after correction to obtain the actual survival rate after the first correction;

[0030] Extract the survival - rate interval of water - body environmental pollution in the trained survival - rate prediction model. If the actual survival rate after the first correction is within the survival - rate interval of water - body environmental pollution, extract the aquaculture water - body sample, and detect the aquaculture water - body sample through chemical detection methods to obtain the current ammonia - nitrogen content index;

[0031] Obtain multiple historical ammonia nitrogen content indexes within a preset time period, construct a series of ammonia nitrogen decomposition change models based on the multiple historical ammonia nitrogen content indexes and the current ammonia nitrogen content index, introduce the mean absolute error algorithm to calculate the model error between the series of ammonia nitrogen decomposition change models, obtain multiple discrete error rates, screen out the minimum discrete error rate and define it as the current ammonia nitrogen decomposition rate;

[0032] Obtain the water body ammonia nitrogen pollution standard evaluation system based on the big data network, establish a scoring rule according to the water body ammonia nitrogen pollution standard evaluation system, and score the current ammonia nitrogen decomposition rate through the scoring rule to obtain a score value;

[0033] Judge whether the score value is less than the preset score value. If it is less than, calculate the error between the score value and the preset score value to obtain an error value, match the corresponding ammonia nitrogen decomposition rate in the water body ammonia nitrogen pollution standard evaluation system according to the error value, and define it as the ammonia nitrogen decomposition error rate. Based on the ammonia nitrogen decomposition error rate, perform metering regulation on the first metering correction plan to obtain the second metering correction plan.

[0034] Further, in a preferred embodiment of the present invention, perform feeding adjustment based on the second metering correction plan to obtain the actual survival rate after secondary correction. If the actual survival rate after secondary correction is not within the survival rate interval of equipment failure, construct a curve graph to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance, specifically including the following steps:

[0035] Perform metering feeding correction on the bait feeding equipment according to the second metering correction plan, recalculate the survival rate of the corrected target aquatic organisms to obtain the actual survival rate after secondary correction, and extract the survival rate interval of equipment failure based on the trained survival rate prediction model;

[0036] If the actual survival rate after secondary correction is within the survival rate interval of equipment failure, perform laser coverage scanning on the bait feeding equipment through laser point cloud scanning technology to obtain several groups of point cloud data of the bait feeding equipment, introduce the RANSAC algorithm to perform model fitting on the several groups of point cloud data to obtain a three-dimensional simulation model of the bait feeding equipment;

[0037] Obtain the actual feeding rate of the bait feeding equipment within a preset time period through the Internet of Things technology, divide the preset time period into multiple uniform time nodes, and construct a curve graph based on the multiple uniform time nodes and the actual feeding rate corresponding to each time node to obtain the actual feeding rate - time change curve graph;

[0038] Calculate the feeding amount by analyzing the actual feeding rate - time change curve graph to obtain the actual feeding amount, and at the same time calculate the curvature of the curve to obtain the first curvature;

[0039] Based on multiple of the uniform time nodes, simulate the actual feeding amount in the three-dimensional simulation model of the bait feeding device to obtain the simulated feeding rate corresponding to each time node. Based on the simulated feeding rate corresponding to each time node, construct a simulated feeding rate-time change curve graph, calculate the feeding amount according to the simulated feeding rate-time change curve graph to obtain the simulated feeding amount, and calculate the curvature of the curve to obtain the second curvature;

[0040] Judge whether the actual feeding amount is less than the simulated feeding amount. If it is less, it indicates that there is a fault in the bait feeding device. Calculate the deviation between the first curvature and the second curvature to obtain the curvature deviation value, and repair and maintain the fault of the bait feeding device based on the curvature deviation value.

[0041] The second aspect of the present invention provides a marine bait feeding metering system based on the Internet of Things. The marine bait feeding metering system based on the Internet of Things includes a memory and a processor. A marine bait feeding metering method program is stored in the memory. When the marine bait feeding metering method program is executed by the processor, the following steps are implemented:

[0042] Obtain the aquaculture image data of multiple target areas within a preset time period, and introduce the local binary pattern algorithm for feature extraction to obtain the aquaculture biological characteristics of multiple target areas. Determine the activity range and aquaculture density of the target aquatic organism according to the aquaculture biological characteristics of multiple target areas;

[0043] Obtain the required nutrient components of the target aquatic organism individuals, analyze and evaluate the nutrient component content of the required nutrient components in the current bait to obtain an evaluation result, and estimate by combining the evaluation result, the activity range and the aquaculture density to obtain a preliminary feeding metering value;

[0044] Perform feeding according to the preliminary feeding metering value, obtain the survival rate of the target aquatic organism, construct a trained survival rate prediction model for prediction to obtain the survival rate interval with insufficient nutrient content, and analyze whether the survival rate of the target aquatic organism is within the survival rate interval to obtain the first metering correction plan;

[0045] Based on the first metering correction plan, perform feeding adjustment to obtain the actual survival rate after the first correction. If the actual survival rate after the first correction is not within the survival rate interval of water body environmental pollution, calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain the second metering correction plan;

[0046] Based on the second measurement correction plan, adjust the feeding to obtain the actual survival rate after secondary correction. If the actual survival rate after secondary correction is not within the survival rate range of equipment failure, construct a curve graph to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance.

[0047] The present invention solves the technical defects existing in the background art. The beneficial technical effects of the present invention are as follows:

[0048] Obtain the breeding biological characteristics of multiple target areas, and determine the activity range and breeding density of the target aquatic organisms according to the breeding biological characteristics of the multiple target areas; analyze and evaluate the nutrient content of the required nutrients in the bait to obtain an evaluation result, and estimate in combination with the evaluation result, the activity range and the breeding density to obtain a preliminary feeding measurement value; perform feeding according to the preliminary feeding measurement value, obtain the survival rate of the target aquatic organisms, analyze whether the survival rate of the target aquatic organisms is within the survival rate range of insufficient nutrient content to obtain a first measurement correction plan; based on the first measurement correction plan, adjust the feeding to obtain the actual survival rate after primary correction. If the actual survival rate after primary correction is not within the survival rate range of water body environmental pollution, calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain a second measurement correction plan; based on the second measurement correction plan, adjust the feeding to obtain the actual survival rate after secondary correction. If the actual survival rate after secondary correction is not within the survival rate range of equipment failure, construct a curve graph to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance. The present invention can perform precise and efficient measurement control on marine bait feeding, thereby improving the breeding quality and reducing feed waste. Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0050] Figure 1 Shows a first method flow chart of a marine bait feeding measurement method based on the Internet of Things;

[0051] Figure 2 Shows a second method flow chart of a marine bait feeding measurement method based on the Internet of Things;

[0052] Figure 3 Shows a third method flow chart of a marine bait feeding measurement method based on the Internet of Things;

[0053] Figure 4 Shows the system framework diagram of a shipborne bait feeding metering system based on the Internet of Things. Detailed implementation manners

[0054] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0055] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0056] The first aspect of the present invention provides a shipborne bait feeding metering method based on the Internet of Things, as Figure 1 shown, including the following steps:

[0057] S102: Obtain the aquaculture image data of multiple target areas within a preset time period, and introduce the local binary pattern algorithm for feature extraction to obtain the aquaculture biological characteristics of the multiple target areas, and determine the activity range and aquaculture density of the target aquatic organisms according to the aquaculture biological characteristics of the multiple target areas;

[0058] S104: Obtain the required nutrient components of the target aquatic organism individuals, analyze the nutrient component content of the required nutrient components in the current bait and evaluate it to obtain an evaluation result, and estimate in combination with the evaluation result, the activity range and the aquaculture density to obtain a preliminary feeding metering value;

[0059] S106: Feed according to the preliminary feeding metering value, obtain the survival rate of the target aquatic organisms, construct a trained survival rate prediction model for prediction to obtain the survival rate interval with insufficient nutrient content, and analyze whether the survival rate of the target aquatic organisms is within the survival rate interval to obtain a first metering correction plan;

[0060] S108: Adjust the feeding based on the first metering correction plan, obtain the actual survival rate after the first correction. If the actual survival rate after the first correction is not within the survival rate interval of water body environmental pollution, then calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain a second metering correction plan;

[0061] S110: Adjust the feeding based on the second metering correction plan, obtain the actual survival rate after the second correction. If the actual survival rate after the second correction is not within the survival rate interval of equipment failure, then construct a curve graph to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance.

[0062] Further, in a preferred embodiment of the present invention, the method of obtaining the aquaculture image data of multiple target areas within a preset time period, introducing the local binary pattern algorithm for feature extraction to obtain the aquaculture biological features of multiple target areas, and determining the activity range and aquaculture density of the target aquatic organism based on the aquaculture biological features of multiple said target areas specifically includes the following steps:

[0063] Control the remote sensing camera on the fishing boat based on the Internet of Things technology to capture images of the target aquatic organism, and obtain the aquaculture image data of multiple target areas within a preset time period;

[0064] Introduce the local binary pattern algorithm to extract the features of the aquaculture organisms from the aquaculture image data of multiple said target areas, divide each of the aquaculture image data into several local blocks, and compare the pixel points within each of the local blocks to generate several binary coding information;

[0065] Convert the several binary coding information into different local binary patterns, count the frequencies of the different local binary patterns appearing within each of the local blocks, draw and output the local binary pattern histogram to obtain the aquaculture biological features of multiple target areas;

[0066] Calculate the Euclidean distances between the aquaculture biological features of multiple said target areas, and at the same time introduce the hot spot radius algorithm to perform hot spot area planning on the calculated multiple Euclidean distances, construct the first activity hot spot map, and determine the activity range and aquaculture density of the target aquatic organism according to the first activity hot spot map.

[0067] It should be noted that for the precise measurement of bait feeding, it is first necessary to know the activity range of the aquaculture organisms in the aquaculture area and the aquaculture density of the aquaculture organisms within the activity range. The activity range and aquaculture density are the key indicators for accurately estimating the required feeding amount of all aquaculture organisms in the aquaculture area. Since the activities of the target aquatic organisms in the water are irregular, but the activity range and aquaculture density can remain unchanged, the activity range and aquaculture density of the target aquatic organisms are calculated and analyzed by extracting features from the aquaculture area images. Among them, the local binary pattern algorithm is used for the extraction of image features. This algorithm performs local binarization on the pixels in the image and constructs local binary patterns to represent the texture features of the image. The advantage is that it has good robustness to the influence of light, noise, etc., and the feature calculation efficiency is high. To facilitate the observation of the activity range and aquaculture density of the target aquatic organisms, by introducing the hot spot radius algorithm to construct an activity hot spot map, the distribution position and distribution density of the features of the target aquatic organisms in the aquaculture area image within a preset time period are further analyzed, which can accelerate the analysis rate, reduce redundant calculation steps, and improve the efficiency. The present invention can analyze and determine the activity range and aquaculture density of the target aquatic organisms by the methods of image feature extraction and constructing an activity hot spot map, thereby improving the data analysis and calculation rate and ensuring the accuracy rate of feeding measurement.

[0068] Further, in a preferred embodiment of the present invention, the required nutritional components of the target aquatic organism individuals are obtained, the nutritional component content of the required nutritional components in the current bait is analyzed and evaluated to obtain an evaluation result, and the preliminary feeding measurement value is estimated by combining the evaluation result, the activity range and the aquaculture density, as Figure 2 shown, and specifically includes the following steps:

[0069] S202: Obtain the species information of the target aquatic organisms, search for the relevant nutritional information required for the normal growth of the species information of the target aquatic organisms based on the big data network to obtain the required nutritional components of the target aquatic organism individuals, and at the same time obtain the required intake of each nutritional component;

[0070] S204: Obtain the ingredient information of several kinds of the current bait, construct a knowledge graph, retrieve the nutritional components contained in the ingredient information of several kinds in the knowledge graph to obtain a retrieval result, and screen and mark the ingredient information that is the same as the required nutritional components of the target aquatic organisms in the retrieval result to obtain the target ingredient information;

[0071] S206: Obtain the standard nutrient content range corresponding to the target ingredient based on the big data network, and obtain the proportion mass of the target ingredient. Introduce the fuzzy C-means algorithm to calculate the initial membership degrees of the proportion mass and each standard nutrient content in the standard nutrient content range, construct the cluster centers, update the positions of the cluster centers based on the membership degrees until the maximum number of iterations is satisfied, and generate multiple membership degrees;

[0072] S208: Construct an evaluation model, screen out the standard nutrient content corresponding to the maximum membership degree among the multiple membership degrees as the result output to obtain the nutrient content of the current bait, and import the nutrient content of the current bait into the evaluation model for evaluation to obtain the evaluation result;

[0073] S210: Calculate the ratio between the required intake of each nutrient and the nutrient content of the current bait to obtain the individual feeding ratio. Estimate based on the comprehensive individual feeding ratio, the evaluation result, the activity range, and the breeding density to obtain the preliminary feeding measurement value.

[0074] It should be noted that the required nutrients of the target aquatic organism individual include protein, carbohydrates, fat, vitamins, and minerals; one of the key indicators determining the precise measurement of bait feeding is to analyze the proportion of bait ingredients and the nutrient content, so as to calculate the specific bait feeding measurement that can meet the required bait nutrient content of the target aquatic organism object. If the bait is directly fed without preliminary analysis and evaluation of the proportion of bait ingredients and the nutrient content, it may result in insufficient nutrient content of the bait, leading to nutritional deficiency in the feeding of the target aquatic organism, and the survival rate will drop linearly over time, which is not conducive to high-quality breeding; for the analysis of the proportion of bait ingredients and the nutrient content, it is to screen out the target ingredient information related to the required nutrients of the target aquatic organism individual. Since the nutrient content of the target ingredient is not a fixed value and there is a certain value range, it is necessary to obtain the standard nutrient content range corresponding to the target ingredient, and then introduce the fuzzy C-means to calculate the membership degrees of the proportion mass of the target ingredient and each nutrient content in the standard nutrient content range, and determine the nutrient content of the bait according to the membership degrees, improve the precise matching rate of the nutrient content, and reduce the occurrence of errors; the individual feeding ratio is the feeding amount ratio of nutrients calculated based on the demand of the target individual for nutrients and the nutrient content of the bait. The present invention can analyze the specific feeding measurement of the bait according to the required bait nutrient content of the target aquatic organism object, ensure the balanced feeding nutrition of the cultured organisms, and improve the quality of feeding health management.

[0075] It should be noted that the input data of the fuzzy C-means algorithm is the sample of the proportion mass coefficient of the target ingredient and the standard nutritional content characteristic coefficients of the target ingredients (such as protein and fat content). The specific calculation process for the initial membership degree is as follows: Set the coefficient sample set , where each sample represents a different proportion mass, and set the characteristic coefficient interval of the standard nutritional content , each characteristic coefficient represents the central value of a standard nutritional content, and set the number C (clustering number) of standard nutritional content categories. Then, use the number of standard nutritional content categories to perform matrix calculation on the membership degrees of the coefficient sample set and the characteristic coefficient interval. The specific expression is:

[0076]

[0077] where represents the membership degree of the coefficient sample point belonging to the j-th nutritional standard category.

[0078] Exemplarily, taking protein and fat content as an example, assume that the proportion mass data contains 3 samples, each sample has 2 standard nutritional content characteristics, and it is desired to be divided into 2 categories (C = 2). Then, a partial example table of the input data is as follows:

[0079]

[0080] Then the initial membership degree is:

[0081]

[0082] where U represents the initial membership degrees of each proportion mass coefficient sample for the two categories.

[0083] It should be noted that for the construction of the evaluation model, the specific steps are as follows: First, obtain the key indicators for bait nutrition evaluation and their historical evaluation coefficients for the current bait through the big data network. The historical evaluation coefficients are in the form of input data. Then, split these historical evaluation coefficients into an 80% training set and a 20% test set and perform denoising operations such as missing value processing, deduplication, and outlier detection to reduce the impact of redundant noise in data training on the evaluation result. Subsequently, use the model architecture of linear regression to fit and train the historical evaluation coefficients of the 80% test set. During the training process, continuously adjust the hyperparameters of the model architecture to ensure training stability and accuracy. After training, a preliminary evaluation model that can evaluate the standard nutrient content of bait based on key indicators and is in the test stage will be formed. At this time, perform a regularization evaluation test on the trained preliminary evaluation model through the remaining 20% test set to avoid overfitting or underfitting of the evaluation model. Adjust the learning rate of the model according to the test results. After the test is completed, the evaluation model will output a series of nutrient evaluation regression coefficients for the key indicators of bait nutrition evaluation, and this series of nutrient evaluation regression coefficients is an accurate linear expression of the final evaluation result of the standard nutrient content of the current bait.

[0084] Furthermore, in a preferred embodiment of the present invention, feeding is performed according to the preliminary feeding measurement value to obtain the survival rate of the target aquatic organism, a trained survival rate prediction model is constructed for prediction to obtain the survival rate interval with insufficient nutrient content, and it is analyzed whether the survival rate of the target aquatic organism is within the survival rate interval to obtain the first measurement correction plan, which specifically includes the following steps:

[0085] Input the preliminary feeding measurement value of the target area into the bait feeding device for metered feeding, and reconstruct the heat map after a preset time period to obtain the second activity heat map;

[0086] Based on the second activity heat map, obtain all non - hot spots and all feature coincidence points in the target area, define the non - hot spots and the feature coincidence points as the low - activity points of the target aquatic organism, and calculate the ratio of all low - activity points of the target aquatic organism to all hot spots in the second activity heat map to obtain the survival rate of the target aquatic organism;

[0087] Obtain the corresponding survival rates under the influence of different aquaculture condition factors through the big data network, construct a survival rate prediction model based on the support vector machine algorithm, and train and verify the corresponding survival rates under the influence of different aquaculture condition factors in the survival probability prediction model to obtain a trained survival rate prediction model; wherein, the different aquaculture condition factors include insufficient nutrient content, water body environmental pollution, and equipment failure;

[0088] Extract the survival rate interval with insufficient nutrient content based on the trained survival rate prediction model, and determine whether the survival rate of the target aquatic organism is within the survival rate interval with insufficient nutrient content;

[0089] If not, introduce the hash algorithm to calculate the hash value between the lower limit value in the survival rate interval and the survival rate of the target aquatic organism, and perform measurement and control on the required feeding amount in the target area according to the hash value to obtain the first measurement correction plan.

[0090] It should be noted that the calculated preliminary feeding measurement value is accurately measured and fed in the bait feeding equipment. However, since the preliminary calculated feeding measurement value is a preliminary estimate and there is a risk of error, the measurement of bait feeding is inaccurate, which may lead to phenomena such as the survival rate of the target aquatic organism in the breeding area not being improved or the growth rate of the survival rate being small. If such phenomena occur, the preliminary feeding measurement value needs to be corrected in a timely manner to reduce the measurement error; after feeding with the preliminary feeding dose value for a preset time period, construct the second activity hot spot map of the target aquatic organism again. When the target aquatic organism dies or has low activity in the breeding area, the characteristics shown in the image will not change significantly. Therefore, the characteristics of death or low activity can be represented by non-hot spots in the activity hot spot map, and the survival rate of the target aquatic organism after feeding can be calculated; since there is no comparison data, it is impossible to know what causes the survival rate to occur. Therefore, the survival rate corresponding to the target aquatic organism under the influence of different breeding condition factors can be predicted by constructing a prediction model; although the preliminary feeding measurement value has been evaluated for the nutrient content, there may still be a phenomenon of insufficient nutrition caused by measurement error. Therefore, when the survival rate of the target aquatic organism after feeding belongs to the survival rate interval with insufficient nutrition, it means that the main reason for the survival rate is insufficient nutrition. Thus, an accurate correction value is calculated to correct and adjust the preliminary feeding measurement value, thereby improving the accuracy of measurement and feeding. The lower limit value in the survival rate interval is the lowest survival rate value in the survival rate interval with insufficient nutrient content. The present invention can accurately analyze the reasons for the survival rate of the target aquatic organism after the preliminary feeding measurement value, so as to correct the preliminary feeding measurement value and improve the quality of feeding measurement.

[0091] It should be noted that for the construction of the survival rate prediction model, this method first collects and collates historical influencing factor data under different breeding conditions through a big data network and several aquatic biological feeding cases, such as water temperature parameters with insufficient nutrient content, dissolved oxygen parameters, pH values, and feed type parameters, etc., and obtains the corresponding historical survival rate labels of each historical influencing factor as input data. Then, perform denoising processing on the collected input data, such as removing missing values, outliers, data standardization or normalization, to improve the convergence speed and stability of the model. Next, divide the input data set into a training set, a test set, and a validation set according to the ratio of 7:2:1. At this time, introduce the support vector machine algorithm to further select a suitable support vector machine kernel function to adapt to different data feature distributions, and adjust the penalty coefficient and kernel function parameters in the support vector machine algorithm according to the selected support vector machine kernel function, so as to form a survival rate prediction model with a support vector machine model architecture. Then, use the historical influencing factor data and its historical survival rate labels in the training set to continuously train and learn the survival rate prediction model with the support vector machine model architecture, so that it can adaptively predict the relationship between the breeding conditions and the survival rate. Set the evaluation mean square error threshold, evaluate the trained survival rate prediction model on the validation set, and output the current evaluation mean square error. If the current evaluation mean square error exceeds the evaluation mean square error threshold, it means that there is an error in the prediction accuracy of the trained model. During the training process, adjust the feature extraction of the support vector machine model architecture and optimize the penalty coefficient and kernel function parameters to improve the generalization ability of the model prediction. Finally, use the test set data to evaluate the finally trained survival rate prediction model to ensure its good performance on unseen data. Applying the trained survival rate prediction model to the actual breeding environment can provide a prediction reference for the survival rate under different breeding conditions.

[0092] Further, in a preferred embodiment of the present invention, the feeding adjustment is performed based on the first measurement correction scheme to obtain the actually corrected survival rate. If the actually corrected survival rate is not within the survival rate range of water body environmental pollution, then calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain the second measurement correction scheme, as Figure 3 shown, specifically including the following steps:

[0093] S302: Perform measurement feeding correction on the bait feeding device according to the first measurement correction scheme, and calculate the survival rate of the corrected target aquatic organism to obtain the actually corrected survival rate;

[0094] S304: Extract the survival rate range of water body environmental pollution in the trained survival rate prediction model. If the actually corrected survival rate is within the survival rate range of water body environmental pollution, then extract a breeding water body sample, and detect the breeding water body sample by a chemical detection method to obtain the current ammonia nitrogen content index;

[0095] S306: Obtain multiple historical ammonia nitrogen content indexes within a preset time period, construct a series of ammonia nitrogen decomposition change models based on the multiple historical ammonia nitrogen content indexes and the current ammonia nitrogen content index, introduce the mean absolute error algorithm to calculate the model error between the series of ammonia nitrogen decomposition change models, obtain multiple discrete error rates, screen out the minimum discrete error rate and define it as the current ammonia nitrogen decomposition rate;

[0096] S308: Obtain the water body ammonia nitrogen pollution standard evaluation system based on the big data network, establish a scoring rule according to the water body ammonia nitrogen pollution standard evaluation system, and score the current ammonia nitrogen decomposition rate through the scoring rule to obtain a score value;

[0097] S310: Determine whether the score value is less than a preset score value. If it is less than, calculate the error between the score value and the preset score value to obtain an error value, match the corresponding ammonia nitrogen decomposition rate in the water body ammonia nitrogen pollution standard evaluation system according to the error value, and define it as the ammonia nitrogen decomposition error rate. Based on the ammonia nitrogen decomposition error rate, perform metering regulation on the first metering correction plan to obtain a second metering correction plan.

[0098] It should be noted that after correcting the problem of insufficient nutrition in the feeding metering, a second activity hot spot map is constructed again to calculate the survival rate of the target aquatic organisms in the breeding area. If the survival rate still fails to meet the standard, it means that the first metering correction plan for metering regulation still needs to be further corrected. However, the problem this time is no longer insufficient nutrition. It may be that a large amount of ammonia nitrogen pollution in the water environment has led to a decline in the breeding quality of the target aquatic organisms, resulting in a low survival rate. And the ammonia nitrogen content in the water is related to the decomposition rate. Therefore, the current ammonia nitrogen decomposition rate can be further evaluated by analysis and calculation, so as to know whether the current water environment quality is the reason for the low survival rate of the target aquatic organisms caused by the regulation of the first metering correction plan; regarding the method of obtaining the current ammonia nitrogen decomposition rate, relevant ammonia nitrogen decomposition change models can be constructed through the process of gradually reaching the current ammonia nitrogen content index from multiple historical ammonia nitrogen content indexes at different time nodes. By calculating the discrete error of the model, the decomposition rate of ammonia nitrogen in the process can be analyzed. Compared with the traditional method of gradually calculating the ammonia nitrogen decomposition rate, the analysis speed is faster, the analysis result is more accurate, and the result output with a lower error rate can be realized; finally, score the ammonia nitrogen decomposition rate result. Through the score value, it can be known whether the low survival rate of the current target aquatic organisms is affected by the current ammonia nitrogen pollution in the water body. Therefore, a secondary correction adjustment is made to the first metering correction plan according to the pollution situation of the ammonia nitrogen content. On the one hand, it ensures that the target aquatic organisms can further obtain sufficient nutritional supplements, avoiding the problem of nutrient deficiency caused by water environment pollution to the target aquatic organisms. On the other hand, it reduces the increase in the ammonia nitrogen content in the water body caused by bait residues, thereby improving the survival rate.

[0099] It should be noted that for the construction of the ammonia nitrogen decomposition change model, the specific steps are as follows: First, extract multiple historical ammonia nitrogen content indices at different time nodes in the aquaculture water body within a preset time period from the aquaculture log. Then, perform normalization processing on the multiple historical ammonia nitrogen content indices and the current ammonia nitrogen content index. Subsequently, determine whether the time series fluctuation index presented by the historical ammonia nitrogen content index and the current ammonia nitrogen content index is greater than the preset threshold. If it is greater, it indicates that the ammonia nitrogen decomposition from the historical ammonia nitrogen content index to the current ammonia nitrogen content index is unstable. Therefore, perform stationary differencing calculation on the historical ammonia nitrogen content index and the current ammonia nitrogen content index to generate a differencing order. Next, introduce the decomposition spectra of the autocorrelation and partial autocorrelation of the ammonia nitrogen in the water body, and jointly calculate the autocorrelation function and partial autocorrelation function of the ammonia nitrogen gradually decomposing from each historical ammonia nitrogen content index to the current ammonia nitrogen content index through the two spectra. At this time, an autoregressive order and a moving average order are obtained to describe the variability of the time series decomposition of the input data. Use the output differencing order, autoregressive order, and moving average order to perform time series calculation fitting on the autoregressive integrated moving average of the ammonia nitrogen gradually decomposing from each historical ammonia nitrogen content index to the current ammonia nitrogen content index. Finally, a series of models formed by fitting are the concrete expressions of the time series decomposition and change of ammonia nitrogen in the aquaculture water body.

[0100] It should be noted that the water body ammonia nitrogen pollution standard evaluation system refers to an evaluation reference system for evaluating the water quality of fishery aquaculture based on national or international environmental quality standards, including but not limited to the "Fishery Water Quality Standard" (GB 11607-1989), the OECD eutrophication evaluation standard, and the "Pollutant Discharge Standard for Municipal Wastewater Treatment Plants" (GB 18918-2002), etc., all of which can be obtained through querying the big data network. After querying the available water body ammonia nitrogen pollution standard evaluation system, construct a water quality evaluation decision matrix based on the ammonia nitrogen decomposition rate evaluation grades and evaluation indicators recorded in the water body ammonia nitrogen pollution standard evaluation system. The specific form of the water quality evaluation decision matrix is:

[0101]

[0102] Among them, represents the value of the ammonia nitrogen decomposition rate evaluation grade on the evaluation indicator.

[0103] Since each evaluation indicator may have different importance, at this time, an indicator weight vector needs to be set, and this indicator weight vector satisfies the normalization requirement of the following formula:

[0104]

[0105] Next, based on the weighted normalization matrix of the index weight vector, a weighted normalized water quality evaluation decision matrix is obtained. Using the weighted normalized water quality evaluation decision matrix, the positive ideal evaluation solution and negative ideal evaluation solution of the evaluation index for the ammonia nitrogen decomposition rate are calculated. The positive ideal evaluation solution and negative ideal evaluation solution are the value range intervals for evaluating the ammonia nitrogen decomposition rate in the water quality evaluation decision matrix. Since the scoring of ammonia nitrogen decomposition is based on the reference assignment of the ammonia nitrogen decomposition rate evaluation level, it is necessary to calculate the distances between each ammonia nitrogen decomposition rate evaluation level and the positive and negative ideal evaluation solutions. This distance is the basis for measuring the scoring strength of the ammonia nitrogen decomposition rate. Finally, the above steps of calculation are repeatedly executed for different ammonia nitrogen decomposition rates, so as to form a complete scoring rule for different ammonia nitrogen decomposition rates, and then accurately score the current ammonia nitrogen decomposition rate under the constraint of the water body ammonia nitrogen pollution standard evaluation system.

[0106] Exemplarily, the scoring rule is as follows in the table:

[0107]

[0108] Among them, 100 in 100 - 80 is the positive ideal evaluation solution, and 80 is the negative ideal evaluation solution.

[0109] Further, in a preferred embodiment of the present invention, based on the second measurement correction scheme, feeding adjustment is performed to obtain the actually corrected survival rate. If the actually corrected survival rate after the second correction is not within the survival rate interval of equipment failure, a curve graph is constructed to analyze whether there is a failure in the bait feeding equipment and repair and maintenance are carried out. The specific steps are as follows:

[0110] According to the second measurement correction scheme, metering feeding correction is performed on the bait feeding equipment, and the survival rate of the target aquatic organisms after correction is recalculated to obtain the actually corrected survival rate after the second correction, and the survival rate interval of equipment failure is extracted based on the trained survival rate prediction model;

[0111] If the actually corrected survival rate after the second correction is within the survival rate interval of equipment failure, laser coverage scanning is performed on the bait feeding equipment through laser point cloud scanning technology to obtain several groups of point cloud data of the bait feeding equipment, and the RANSAC algorithm is introduced to perform model fitting on the several groups of point cloud data to obtain a three - dimensional simulation model of the bait feeding equipment;

[0112] The actual feeding rate of the bait feeding equipment within a preset time period is obtained through the Internet of Things technology. The preset time period is divided into multiple uniform time nodes, and a curve graph is constructed based on the multiple uniform time nodes and the actual feeding rate corresponding to each time node to obtain an actual feeding rate - time change curve graph;

[0113] Calculate the feeding amount by analyzing the actual feeding rate-time change curve diagram to obtain the actual feeding amount, and at the same time calculate the curvature of the curve to obtain the first curvature;

[0114] Based on multiple uniform time nodes, simulate the actual feeding amount in the three-dimensional simulation model of the bait feeding device to obtain the simulated feeding rate corresponding to each time node. Based on the simulated feeding rate corresponding to each time node, construct a simulated feeding rate-time change curve diagram, calculate the feeding amount according to the simulated feeding rate-time change curve diagram to obtain the simulated feeding amount, and calculate the curvature of the curve to obtain the second curvature;

[0115] Judge whether the actual feeding amount is less than the simulated feeding amount. If it is less, it means that there is a fault in the bait feeding device. Calculate the deviation between the first curvature and the second curvature to obtain the curvature deviation value, and repair and maintain the fault of the bait feeding device based on the curvature deviation value.

[0116] It should be noted that the fault of the bait feeding device is also one of the key factors affecting the survival rate of the target aquatic organisms. When the bait feeding device fails, it may cause large errors in the measurement output rate, output amount and data monitoring of the bait, so that the bait feeding device cannot accurately measure and feed according to the second measurement correction scheme, and then the nutrition of the target aquatic organisms will decline. Therefore, it is necessary to determine and repair the fault of the bait feeding device; for judging whether there is a fault in the bait feeding device, the error between the simulated feeding behavior and the historical actual feeding behavior can be determined by means of simulated feeding, so that it can be judged whether there is a fault in the device based on the error, saving the steps of manual repeated on-site operations, improving the speed and accuracy of data acquisition and comparison, and reducing the generation of judgment errors; among them, the method of simulated feeding is realized by constructing a three-dimensional simulation model of the bait feeding device, with low cost and convenient operation; the first curvature represents the change trend of the actual feeding rate, and the second curvature represents the change trend of the simulated feeding rate. By analyzing the change trends of the two, the fault error degree of the device can be known, so as to facilitate the accurate and rapid repair of the faulty device by the maintenance personnel and improve the measurement quality.

[0117] In addition, the above-mentioned method for measuring and feeding marine bait based on the Internet of Things further includes the following steps:

[0118] Obtain the fault time node of the bait feeding device, judge whether the fault time node is within the preset working time interval. If it is, obtain the remaining bait feeding measurement tasks of the current faulty bait feeding device;

[0119] A preset distance threshold, obtain the distance values between the current ship and all other ships in the aquaculture area through satellite positioning technology. If the distance value is less than the distance threshold, extract the distance values less than the distance threshold, and screen out the ship corresponding to the minimum distance value among the extracted distance values. Define the ship corresponding to the minimum distance value as the nearest ship;

[0120] Obtain the remaining bait feeding measurement tasks and the traveling speed of the nearest ship, and calculate by combining the remaining bait feeding measurement tasks and the traveling speed of each nearest ship to obtain the time for the nearest ship to complete the remaining bait feeding measurement tasks;

[0121] Based on the remaining required bait feeding measurement tasks of the current faulty bait feeding device and the traveling speed, calculate the time required for the nearest ship to complete the remaining bait feeding measurement tasks of the current faulty bait feeding device;

[0122] Add the time required for the nearest ship to complete the remaining bait feeding measurement tasks of the current faulty bait feeding device to the time for the nearest ship to complete the remaining bait feeding measurement tasks to obtain the total feeding time, and judge whether the total feeding time is less than the preset total working time;

[0123] If it is less, send a distress signal to the nearest ship through the Internet of Things technology, and upload the remaining required bait feeding measurement tasks of the current faulty bait feeding device to the control terminal of the bait feeding device on the nearest ship to continue to complete the task.

[0124] It should be noted that when the ship is feeding bait to the target aquaculture area, if the bait feeding device fails during the feeding process, it will cause the remaining feeding tasks to be unable to be completed, resulting in the target aquatic organisms being unable to ingest the accurately measured bait nutrients, greatly affecting the breeding growth quality, reducing the survival rate, and being unfavorable for the high-quality breeding of the target aquatic organisms; when the ship is performing bait feeding operations in aquaculture areas such as the sea, rivers, and lakes, there are usually multiple standby ships or multiple ships working together at the same time. On the one hand, it reduces the problem of low feeding efficiency of a single ship, and on the other hand, it can prevent the problem of abnormal breeding work caused by ship failures or bait feeding device failures. Therefore, when the bait feeding device on a certain ship fails, a distress signal can be sent to the ship closest to the current faulty ship, and the remaining uncompleted feeding tasks of the current ship can be handed over to the nearest ship to continue to complete. The present invention can hand over the remaining feeding tasks to the nearest ship to continue to complete when the bait feeding device of the ship fails during the feeding process, thereby solving the problem of the mid-course failure of the bait feeding device, improving the feeding efficiency, ensuring the breeding growth quality, and reducing the breeding feeding measurement error.

[0125] In addition, the above-mentioned method for measuring and feeding marine bait based on the Internet of Things further includes the following steps:

[0126] Match bait varieties in the big data network based on the required nutritional components of the target aquatic organism to obtain associated bait varieties, and at the same time obtain the purchase costs corresponding to each bait variety;

[0127] If the purchase cost is greater than the preset purchase cost, extract the bait varieties corresponding to the purchase cost greater than the preset purchase cost to obtain the bait varieties after the first screening;

[0128] Based on the big data network, obtain the nutritional value of each bait variety in the bait varieties after the first screening, and eliminate the bait varieties after the first screening corresponding to the nutritional value lower than the preset nutritional value to obtain the bait varieties after the second screening;

[0129] Construct a sorting table, and import the purchase costs corresponding to the bait varieties after the second screening into the sorting table for sorting from large to small;

[0130] After the sorting is completed, extract the bait variety corresponding to the maximum purchase cost among the bait varieties after the second screening as the best feeding bait for output.

[0131] It should be noted that when selecting and purchasing bait, multiple factors should be fully considered. Among them, the two most important factors for breeders are nutritional value and purchase cost. When selecting bait for the target aquatic organism, first, it should be considered whether the nutritional value of the bait variety can achieve the expected breeding effect, and bait varieties with higher nutritional value and suitable for the breeding of the target aquatic organism should be selected; second, there are various bait varieties, and the prices of each are different. From the perspective of consumers, it is most appropriate to select bait varieties with lower purchase costs, which can not only ensure achieving the expected breeding goal but also ensure controlling the lowest purchase cost output, and better improve the feeding experience of breeders. The present invention can conduct a preliminary screening based on the nutritional value of bait varieties to ensure that the feeding and breeding performance meets the expected effect, and then conduct a second screening of bait varieties according to the purchase cost, which can reduce the purchase cost output of breeders, has a high cost performance, and has a further improved effect on the measurement of bait feeding.

[0132] In the second aspect of the present invention, a system for measuring and feeding marine bait based on the Internet of Things is provided. The system for measuring and feeding marine bait based on the Internet of Things includes a memory 41 and a processor 42. A program for the method for measuring and feeding marine bait based on the Internet of Things is stored in the memory 41. When the program for the method for measuring and feeding marine bait based on the Internet of Things is executed by the processor 42, as Figure 4 shown, the following steps are implemented:

[0133] Obtain the aquaculture image data of multiple target areas within a preset time period, introduce the local binary pattern algorithm for feature extraction to obtain the aquaculture biological characteristics of the multiple target areas, and determine the activity range and aquaculture density of the target aquatic organism according to the aquaculture biological characteristics of the multiple target areas;

[0134] Obtain the required nutrient components of the target aquatic organism individuals, analyze and evaluate the nutrient content of the required nutrient components in the current bait to obtain an evaluation result, and estimate based on the evaluation result, the activity range and the aquaculture density to obtain a preliminary feeding measurement value;

[0135] Perform feeding according to the preliminary feeding measurement value, obtain the survival rate of the target aquatic organism, construct a trained survival rate prediction model for prediction to obtain the survival rate interval with insufficient nutrient content, and analyze whether the survival rate of the target aquatic organism is within the survival rate interval to obtain a first measurement correction plan;

[0136] Based on the first measurement correction plan, perform feeding adjustment to obtain the actual survival rate after the first correction. If the actual survival rate after the first correction is not within the survival rate interval of water body environmental pollution, calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain a second measurement correction plan;

[0137] Based on the second measurement correction plan, perform feeding adjustment to obtain the actual survival rate after the second correction. If the actual survival rate after the second correction is not within the survival rate interval of equipment failure, construct a curve graph to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance.

[0138] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for measuring the feeding amount of marine bait based on the Internet of Things, characterized in that, It includes the following steps: Obtain the aquaculture image data of multiple target areas within a preset time period, introduce the local binary pattern algorithm for feature extraction to obtain the aquaculture biological characteristics of the multiple target areas, and determine the activity range and aquaculture density of the target aquatic organisms according to the aquaculture biological characteristics of the multiple target areas; Obtain the required nutrients of the target aquatic organism individuals, analyze and evaluate the nutrient content of the required nutrients in the current bait to obtain an evaluation result, and estimate based on the evaluation result, the activity range and the aquaculture density to obtain a preliminary feeding measurement value; Perform feeding according to the preliminary feeding measurement value, obtain the survival rate of the target aquatic organisms, predict according to the constructed and trained survival rate prediction model to obtain the survival rate interval with insufficient nutrient content, and analyze whether the survival rate of the target aquatic organisms is within the survival rate interval to obtain a first measurement correction plan; Based on the first measurement correction plan, perform feeding adjustment to obtain the actual survival rate after the first correction. If the actual survival rate after the first correction is not within the survival rate interval of water body environmental pollution, calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain a second measurement correction plan; Based on the second measurement correction plan, perform feeding adjustment to obtain the actual survival rate after the second correction. If the actual survival rate after the second correction is not within the survival rate interval of equipment failure, construct a curve graph to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance.

2. The marine bait feeding metering method based on the Internet of Things according to claim 1, characterized in that The step of obtaining the aquaculture image data of multiple target areas within a preset time period, introducing the local binary pattern algorithm for feature extraction to obtain the aquaculture biological characteristics of the multiple target areas, and determining the activity range and aquaculture density of the target aquatic organisms according to the aquaculture biological characteristics of the multiple target areas specifically includes the following steps: Based on the Internet of Things technology, control the remote sensing camera on the fishing boat to capture images of the target aquatic organisms, and obtain the aquaculture image data of multiple target areas within a preset time period; Introduce the local binary pattern algorithm to extract the characteristics of the aquaculture organisms from the aquaculture image data of the multiple target areas, divide each aquaculture image data into several local blocks, and compare the pixel points within each local block to generate several binary coding information; Convert the several binary coding information into different local binary patterns, count the frequencies of the different local binary patterns appearing within each local block, draw and output a local binary pattern histogram to obtain the aquaculture biological characteristics of the multiple target areas; Calculate the Euclidean distances between the aquaculture biological characteristics of the multiple target areas, and at the same time introduce the hotspot radius algorithm to perform hotspot area planning on the calculated multiple Euclidean distances, construct a first activity hotspot map, and determine the activity range and aquaculture density of the target aquatic organisms according to the first activity hotspot map.

3. The method for measuring the amount of bait feeding for ships based on the Internet of Things according to claim 1, wherein Obtain the required nutrient components of the target aquatic organism, analyze the nutrient content of the required nutrient components in the current bait and evaluate it to obtain an evaluation result, and estimate based on the evaluation result, the activity range and the breeding density to obtain a preliminary feeding measurement value, which specifically includes the following steps: Obtain the species information of the target aquatic organism, search for the relevant nutrient information required for the normal growth of the species information of the target aquatic organism based on the big data network to obtain the required nutrient components of the target aquatic organism individual, and at the same time obtain the required intake of each nutrient component; Obtain the ingredient information of several kinds of current bait, construct a knowledge graph, retrieve the nutrient components contained in the ingredient information of several kinds in the knowledge graph to obtain a retrieval result, and screen and mark the ingredient information with the same required nutrient components as the target aquatic organism in the retrieval result to obtain target ingredient information; Based on the big data network, obtain the standard nutrient content range corresponding to the target ingredient, and obtain the proportion quality of the target ingredient. Introduce the fuzzy C-means algorithm to calculate the initial membership degree of the proportion quality and each standard nutrient content in the standard nutrient content range, construct a clustering center, and update the position of the clustering center based on the membership degree until the maximum number of iterations is satisfied, and generate multiple membership degrees; Construct an evaluation model, screen out the standard nutrient content corresponding to the maximum membership degree in multiple membership degrees as the result output to obtain the nutrient content of the current bait, and import the nutrient content of the current bait into the evaluation model for evaluation to obtain an evaluation result; Calculate the ratio between the required intake of each nutrient component and the nutrient content of the current bait to obtain an individual feeding ratio, and estimate comprehensively based on the individual feeding ratio, the evaluation result, the activity range and the breeding density to obtain a preliminary feeding measurement value.

4. A method for measuring the feeding amount of marine bait based on the Internet of Things according to claim 1, characterized in that, Feed according to the preliminary feeding measurement value, obtain the survival rate of the target aquatic organism, construct a trained survival rate prediction model for prediction to obtain the survival rate interval with insufficient nutrient content, and analyze whether the survival rate of the target aquatic organism is within the survival rate interval to obtain a first measurement correction plan, which specifically includes the following steps: Input the preliminary feeding measurement value of the target area into the bait feeding device for measurement feeding, and reconstruct the heat map after a preset time period to obtain a second activity heat map; Based on the second activity heat map, obtain all non-hot spots and all feature coincidence points in the target area, define the non-hot spots and the feature coincidence points as the low-activity points of the target aquatic organism, and calculate the ratio of all low-activity points of the target aquatic organism to all hot spots in the second activity heat map to obtain the survival rate of the target aquatic organism; Obtain the corresponding survival rates under the influence of different aquaculture condition factors through a big data network, construct a survival rate prediction model based on the support vector machine algorithm, train and verify the survival rates corresponding to the different aquaculture condition factors in the survival rate prediction model to obtain a trained survival rate prediction model; wherein, the different aquaculture condition factors include insufficient nutrient content, water body environmental pollution, and equipment failure; Extract the survival rate interval of insufficient nutrient content based on the trained survival rate prediction model, and determine whether the survival rate of the target aquatic organism is within the survival rate interval of insufficient nutrient content; If not, introduce the hash algorithm to calculate the hash value between the lower limit value in the survival rate interval and the survival rate of the target aquatic organism, and perform metering regulation on the required feeding amount in the target area according to the hash value to obtain the first metering correction plan.

5. The marine bait feeding metering method based on the Internet of Things according to claim 1, wherein, Perform feeding adjustment based on the first metering correction plan to obtain the actually corrected survival rate after the first correction. If the actually corrected survival rate after the first correction is not within the survival rate interval of water body environmental pollution, calculate and analyze the ammonia nitrogen decomposition rate in the current water body to obtain the second metering correction plan, which specifically includes the following steps: Perform metering feeding correction on the bait feeding equipment according to the first metering correction plan, and calculate the corrected survival rate of the target aquatic organism to obtain the actually corrected survival rate after the first correction; Extract the survival rate interval of water body environmental pollution in the trained survival rate prediction model. If the actually corrected survival rate after the first correction is within the survival rate interval of water body environmental pollution, extract the aquaculture water body sample, and detect the aquaculture water body sample through chemical detection methods to obtain the current ammonia nitrogen content index; Obtain multiple historical ammonia nitrogen content indexes within a preset time period, construct a series of ammonia nitrogen decomposition change models based on the multiple historical ammonia nitrogen content indexes and the current ammonia nitrogen content index, introduce the mean absolute error algorithm to calculate the model error between the series of ammonia nitrogen decomposition change models to obtain multiple discrete error rates, and select the smallest discrete error rate and define it as the current ammonia nitrogen decomposition rate; Obtain the water body ammonia nitrogen pollution standard evaluation system based on the big data network, establish a scoring rule according to the water body ammonia nitrogen pollution standard evaluation system, and score the current ammonia nitrogen decomposition rate through the scoring rule to obtain a score value; Judge whether the score value is less than the preset score value. If it is less than, calculate the error between the score value and the preset score value to obtain an error value, match the corresponding ammonia nitrogen decomposition rate in the water body ammonia nitrogen pollution standard evaluation system according to the error value, and define it as the ammonia nitrogen decomposition error rate. Perform metering regulation on the first metering correction plan based on the ammonia nitrogen decomposition error rate to obtain the second metering correction plan.

6. The method for measuring and feeding marine bait based on the Internet of Things according to claim 1, wherein, Perform feeding adjustment based on the second metering correction plan to obtain the actually corrected survival rate after the second correction. If the actually corrected survival rate after the second correction is not within the survival rate interval of equipment failure, construct a curve graph to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance, which specifically includes the following steps: Perform metering feeding correction on the bait feeding device according to the second metering correction plan, recalculate the survival rate of the target aquatic organisms after correction, obtain the actual survival rate after secondary correction, and extract the survival rate interval of equipment failure based on the trained survival rate prediction model; If the actual survival rate after secondary correction is within the survival rate interval of equipment failure, perform laser coverage scanning on the bait feeding device through laser point cloud scanning technology to obtain several groups of point cloud data of the bait feeding device, and introduce the RANSAC algorithm to perform model fitting on the several groups of point cloud data to obtain a three-dimensional simulation model of the bait feeding device; Obtain the actual feeding rate of the bait feeding device within a preset time period through the Internet of Things technology, divide the preset time period into multiple uniform time nodes, and construct a curve graph based on the multiple uniform time nodes and the actual feeding rate corresponding to each time node to obtain an actual feeding rate-time change curve graph; Calculate the feeding amount by analyzing the actual feeding rate-time change curve graph to obtain the actual feeding amount, and at the same time calculate the curvature of the curve to obtain the first curvature; Perform simulated feeding of the actual feeding amount in the three-dimensional simulation model of the bait feeding device based on the multiple uniform time nodes to obtain the simulated feeding rate corresponding to each time node, construct a simulated feeding rate-time change curve graph based on the simulated feeding rate corresponding to each time node, calculate the feeding amount according to the simulated feeding rate-time change curve graph to obtain the simulated feeding amount, and calculate the curvature of the curve to obtain the second curvature; Judge whether the actual feeding amount is less than the simulated feeding amount. If it is less, it means that there is a fault in the bait feeding device. Calculate the deviation between the first curvature and the second curvature to obtain the curvature deviation value, and repair and maintain the fault of the bait feeding device based on the curvature deviation value.

7. A marine bait feeding metering system based on the Internet of Things, characterized in that, The marine bait feeding metering system based on the Internet of Things includes a memory and a processor. A marine bait feeding metering method program based on the Internet of Things is stored in the memory. When the marine bait feeding metering method program based on the Internet of Things is executed by the processor, the following steps are implemented: Obtain the aquaculture image data of multiple target areas within a preset time period, and introduce the local binary pattern algorithm for feature extraction to obtain the aquaculture biological characteristics of the multiple target areas, and determine the activity range and aquaculture density of the target aquatic organisms according to the aquaculture biological characteristics of the multiple target areas; Obtain the required nutrient components of the target aquatic organism individuals, analyze and evaluate the nutrient component content of the required nutrient components in the current bait to obtain an evaluation result, and estimate in combination with the evaluation result, the activity range and the aquaculture density to obtain a preliminary feeding metering value; Perform feeding according to the preliminary feeding metering value, obtain the survival rate of the target aquatic organisms, predict according to the constructed and trained survival rate prediction model to obtain the survival rate interval of insufficient nutrient content, and analyze whether the survival rate of the target aquatic organisms is within the survival rate interval to obtain the first metering correction plan; Based on the first measurement correction plan, feeding adjustment is carried out to obtain the actually corrected survival rate for the first time. If the actually corrected survival rate for the first time is not within the survival rate range of water body environmental pollution, the ammonia nitrogen decomposition rate in the current water body is calculated and analyzed to obtain the second measurement correction plan; Based on the second measurement correction plan, feeding adjustment is carried out to obtain the actually corrected survival rate for the second time. If the actually corrected survival rate for the second time is not within the survival rate range of equipment failure, a curve graph is constructed to analyze whether there is a failure in the bait feeding equipment and perform repair and maintenance.

Images