Sheep growth data monitoring management method and system

Abstract

The invention discloses a sheep growth data monitoring management method and system, and relates to the technical field of livestock breeding management. A sheep growth data monitoring management system comprises a data acquisition module, a data processing module, a clustering analysis module, a model construction module, a time calculation module and a marketing recommendation module. Weighted clustering analysis is carried out on the sheep in the sheep flock through the K-means clustering algorithm, the clustering analysis result is obtained, the sheep in the sheep flock are classified according to the clustering analysis result, the individual difference and growth characteristics of the sheep can be fully considered, more accurate and efficient breeding management is achieved, and the breeding efficiency is improved. According to the sheep growth data monitoring management method and the sheep growth data monitoring management system, each sheep is enabled to be slaughtered in an optimal state, so that the quality and the yield of mutton are improved, the breeding cost is reduced, the economic benefits are increased, the feed utilization efficiency and the resource allocation are optimized, the efficiency and the sustainability of the whole breeding process are improved, and the economic benefits of the sheep growth data monitoring management method and the sheep growth data monitoring management system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of livestock breeding management, and in particular to a sheep growth data monitoring and management method and system. Background Art

[0002] Animal husbandry is a vital component of agriculture, primarily involving the raising and breeding of livestock and poultry to produce products such as meat, milk, eggs, wool, and hides. It plays a crucial role in ensuring human food supply, meeting various domestic and industrial raw material needs, and promoting rural economic development. Sheep, as a common livestock, occupy a prominent position in animal husbandry. Sheep farming not only produces high-quality meat for human consumption but also wool for weaving various clothing and blankets. Furthermore, the milk produced during breeding is nutritious and easily digestible, making it suitable for consumption as a beverage or processed into dairy products. Sheep farming methods vary, from traditional grazing to modern large-scale captive farming, depending on the region, natural conditions, and production needs. Farmers can continuously improve sheep production and economic benefits through scientific husbandry management, appropriate breeding techniques, and effective disease control measures, thereby promoting the sustainable and healthy development of the sheep farming industry.

[0003] Existing sheep growth data monitoring and management methods and systems are generally used to monitor changes in sheep's physiological data so that farmers can understand the recent status of the flock and make corresponding adjustments to the breeding plan. They can also be used to classify sheep in the flock according to their species and establish corresponding slaughter times and slaughter weights. However, this method can only roughly classify the flock, and even sheep of the same breed will have differences. It is difficult to ensure that all sheep in the flock are in the best slaughter condition by determining the slaughter time and slaughter weight only by the species of the sheep, which may lead to low overall economic benefits of the sheep slaughter.

[0004] Based on the above situation, the present invention proposes a sheep growth data monitoring and management method and system with high economic benefits. Summary of the Invention

[0005] In order to overcome the shortcomings of existing sheep growth data monitoring and management methods and systems that can only roughly classify sheep in a flock according to their species and establish corresponding slaughter times and slaughter weights, but do not take into account the differences between sheep of the same breed, making it difficult to ensure that all sheep in the flock are slaughtered in the best slaughter condition, which may lead to low overall economic benefits of sheep slaughter, the present invention proposes a sheep growth data monitoring and management method and system with high economic benefits.

[0006] A method for monitoring and managing sheep growth data comprises the following steps: Acquiring the current growth data and historical monitoring data of each sheep in the flock through monitoring equipment, wherein the historical monitoring data includes historical weight change data, historical body size change data, historical feed intake change data, and historical feeding environment change data; Clean and process the historical monitoring data of each sheep to obtain pre-processed historical monitoring data; Determine the main characteristics based on the current growth data of each sheep and obtain the characteristic weights of each type of data through correlation analysis , based on feature weights Then, a weighted cluster analysis is performed on the sheep in the flock using the K-means clustering algorithm to obtain cluster analysis results, and the sheep in the flock are classified according to the cluster analysis results; A flock growth curve model is constructed based on the optimized Gompertz model, and the flock growth curve model is fitted according to the pre-processed historical monitoring data of various flocks to obtain personalized flock growth curve models for various flocks. Obtain recommended market release time for various sheep flocks based on personalized sheep growth curve model and recommended market weight , at the recommended time of release Obtain market price data in real time and calculate the economic benefits to obtain the latest time for each type of sheep to be marketed ; Based on recommended market time and the latest time of release Constructing recommended time intervals for market release , according to user needs from the recommended time interval Select the appropriate time to market the sheep and market the corresponding type of sheep.

[0007] As a preferred aspect of the invention, the current growth data includes the sheep's age, weight, height, oblique length, chest circumference, daily weight gain, total duration of illness and feed intake; the historical body size change data includes the sheep's height change data, oblique length change data and chest circumference change data; the historical feed intake change data includes the sheep's daily feed intake change data and the material ratio change data in the feed; the historical feeding environment change data includes the feeding temperature change data and humidity change data.

[0008] As a preferred aspect of the invention, the feature weight is obtained The steps are: Sheep are classified based on their growth rate differences. Daily weight gain is selected as the primary feature and other types of data as secondary features. The correlation coefficient between each feature and daily weight gain is calculated using the Pearson correlation coefficient calculation formula. ; Correlation coefficient Perform normalization and obtain the feature weights of various types of data .

[0009] As a preferred aspect of the invention, the steps of obtaining the cluster analysis results are: A current growth dataset is constructed based on the current growth data of each sheep, and the data of different dimensions in the current growth dataset are standardized through Z-Score standardization to obtain a standardized current growth dataset; Determine the optimal number of clusters based on the normalized current growth dataset using the elbow rule ; Randomly select the normalized current growth dataset samples as the initial cluster center, based on the feature weights The distance between each sample and the center of each cluster is calculated using the weighted Euclidean distance formula, and the sample is assigned to the nearest cluster. The mean of all samples in each cluster is calculated and used as the new cluster center. The assignment and update process is repeated until the change in the cluster center is less than a certain threshold or the maximum number of iterations is reached, and the cluster analysis results are obtained.

[0010] As a preferred aspect of the invention, the steps of obtaining the personalized flock growth curve model of each type of sheep flock are: The pre-processed historical weight change data of various sheep flocks were obtained. The Gompertz model was optimized based on the significant impact of annual temperature changes on sheep growth, and a sheep flock growth curve model was constructed based on this data. The model formula is: in Sheep in time Weight at is the theoretical maximum weight of a sheep. It is the growth inflection point time, indicating the critical point where the growth rate of sheep changes from fast to slow. is the growth rate constant, is the temperature fluctuation coefficient, which is used to quantify the effect of temperature changes on sheep growth. is the temperature impact factor, which is used to simulate the significant impact of annual periodic changes in temperature on sheep growth by introducing a sine function term; According to prior knowledge or experience, the parameters 、 、 and The initial value is guessed, and the model parameters are fitted using nonlinear regression analysis based on the pre-processed historical weight change data of each type of sheep flock. The parameters are adjusted through iterative optimization algorithm so that the residual sum of squares is Minimize and get the parameters 、 、 and The final estimate of the parameter 、 and The final estimated value is brought into the herd growth curve model to obtain the personalized herd growth curve model of each type of herd, where the residual sum of squares is The calculation formula is: ,in is the number of data points, It is A point in time, The sheep are in the The actual average weight at each time point.

[0011] As a preferred aspect of the invention, the recommended time for marketing of the various types of sheep is obtained. , recommended slaughter weight and the latest time of release The steps are: For each type of sheep flock, select the growth inflection point time As the recommended time for market release, the recommended time for market release will be Bring in personalized flock growth curve model and get recommended slaughter weight , recommended slaughter weight The calculation formula is: ; Get recommended market time The market price of mutton , feed market price , daily feed consumption and other daily farming costs , construct the economic benefit equation and solve it to get the latest time for each type of sheep to be marketed , where the economic benefit equation is: ,in represents the total number of sheep in the flock, and Respectively represent the sheep at time and time Weight at the time.

[0012] A sheep growth data monitoring and management system, comprising: A data acquisition module is used to obtain the current growth data and historical monitoring data of each sheep in the flock through monitoring equipment; Data processing module, used to clean and process the historical monitoring data of each sheep; Cluster analysis module, used to obtain the feature weights of various types of data in the current growth data through correlation analysis And perform weighted cluster analysis on the sheep in the flock using the K-means clustering algorithm, and classify the sheep according to the cluster analysis results; The model building module is used to build a flock growth curve model and fit the flock growth curve model based on the pre-processed historical monitoring data of various flocks; Time calculation module, used to obtain the recommended time for each type of sheep to be marketed based on the personalized sheep growth curve model and recommended slaughter weight And by calculating the economic benefits, we can get the latest time for each type of sheep to be marketed. ; The market recommendation module is used to build the recommended market time interval , and recommend the time interval for market release based on user needs Choose the appropriate time to market.

[0013] The present invention has the following advantages: 1. The present invention performs weighted cluster analysis on the sheep in a flock through the K-means clustering algorithm to obtain cluster analysis results, and classifies the sheep in the flock according to the cluster analysis results. This not only fully considers the individual differences and growth characteristics of the sheep to achieve more accurate and efficient breeding management, but also ensures that each sheep is marketed in the best condition, thereby improving the quality and yield of mutton, reducing breeding costs and increasing economic benefits, but also helps to optimize feed utilization efficiency and resource allocation, and improve the efficiency and sustainability of the entire breeding process, thereby improving the economic benefits of this sheep growth data monitoring and management method and system.

[0014] The present invention constructs a flock growth curve model based on the optimized Gompertz model, and obtains the recommended time for the release of various flocks based on the personalized flock growth curve model obtained by data fitting. and recommended market weight It not only enables farmers to choose to market the sheep when the growth efficiency is optimal, thereby ensuring the quality of mutton and maximizing economic benefits, but also determines the market release time based on scientific models, which can reduce the uncertainty of farmers' reliance on experience and judgment, and enhance the rationality of production plans and market supply stability. It can also effectively reduce feed waste and excessive resource consumption, thereby reducing breeding costs and improving resource utilization efficiency, and improving the economic benefits of this sheep growth data monitoring and management method and system.

[0015] The present invention proposes the time of slaughtering Obtain market price data in real time and calculate the economic benefits to obtain the latest time for each type of sheep to be marketed It can accurately reflect the actual economic results brought by daily routine breeding activities, so that breeders can have a clear understanding of the breeding economic situation and adjust the breeding strategy in time according to real data. It also determines the latest time of marketing based on the principle of equivalence between economic benefits and costs, and can obtain the key nodes for maximizing breeding benefits and minimizing risks, which helps breeders plan marketing plans in advance to avoid subsequent potential risks and ensure the stable realization of breeding benefits, thereby improving the economic benefits of this sheep growth data monitoring and management method and system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The figure is a flow chart of a sheep growth data monitoring and management method adopted in an embodiment of the present invention.

[0017] Figure 2 This is a schematic structural diagram of a sheep growth data monitoring and management system used in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0019] Example 1, a method for monitoring and managing sheep growth data, such as Figure 1 As shown, the following steps are included: Acquiring the current growth data and historical monitoring data of each sheep in the flock through monitoring equipment, wherein the historical monitoring data includes historical weight change data, historical body size change data, historical feed intake change data, and historical feeding environment change data; Clean and process the historical monitoring data of each sheep to obtain pre-processed historical monitoring data; Determine the main characteristics based on the current growth data of each sheep and obtain the characteristic weights of each type of data through correlation analysis , based on feature weights and perform weighted cluster analysis on the sheep in the flock using the K-means clustering algorithm to obtain cluster analysis results, and classify the sheep in the flock according to the cluster analysis results; A flock growth curve model is constructed based on the optimized Gompertz model, and the flock growth curve model is fitted according to the pre-processed historical monitoring data of various flocks to obtain personalized flock growth curve models for various flocks. Obtain recommended market release time for various sheep flocks based on personalized sheep growth curve model and recommended market weight , recommended time for release Obtain market price data in real time and calculate the economic benefits to obtain the latest time for each type of sheep to be marketed ; Based on recommended market time and the latest time of release Constructing recommended time intervals for market release , according to user needs from the recommended time interval Select the appropriate time to market the sheep and market the corresponding type of sheep.

[0020] The current growth data includes the sheep's age, weight, height, oblique length, chest circumference, daily weight gain, total duration of illness and feed intake; the historical body size change data includes the sheep's height change data, oblique length change data and chest circumference change data; the historical feed intake change data includes the sheep's daily feed intake change data and the material ratio change data in the feed; the historical feeding environment change data includes the feeding temperature change data and the feeding humidity change data.

[0021] The specific steps of cleaning and processing the historical monitoring data of each sheep to obtain the pre-processed historical monitoring data are as follows: Duplicate data processing: Through data comparison algorithms, duplicate historical monitoring data can be found and deleted. For example, when the intelligent weighing system records the weight data of the same sheep at the same time multiple times, duplicate records can be removed to retain the only accurate data. Missing data processing: handle the null or missing values ​​in the historical monitoring data, use linear interpolation or polynomial interpolation to fill the missing values, or directly use the mean or median of the monitoring data to fill the missing values ​​to ensure the integrity of the data and the stability of the model. For example, if the sheep physiological behavior monitoring capsule occasionally loses data due to signal interruption, the missing physiological parameter values ​​can be estimated based on the data change trend before and after the moment by using linear interpolation or nonlinear interpolation methods; Abnormal data processing: using the Z-Score method or the IQR method to identify outliers in historical monitoring data that do not conform to the expected pattern, and then deleting outliers and replacing them with the mean or median of such monitoring data or using interpolation methods to repair outliers, so as to avoid these outliers from having a negative impact on the fitting of the herd growth curve model; The data format is unified, and data from different sources and formats are converted into a unified format. The starting base time point of all historical monitoring data is unified, and the monitoring frequency of all historical monitoring data is unified. The missing values ​​of monitoring data with low monitoring frequency at the new time point are filled by interpolation methods such as linear interpolation or polynomial interpolation to ensure that all historical monitoring data have values ​​at the same time point. For example, weight data is unified into kilograms (kg), and the time of behavioral monitoring data is unified into a 24-hour system, etc., to facilitate subsequent analysis and processing.

[0022] The main characteristics are determined based on the current growth data of each sheep and the characteristic weights of various types of data are obtained through correlation analysis. The specific steps are: classify the sheep based on their growth rate differences, select daily weight gain as the main feature, and other types of data as secondary features, and calculate the correlation coefficient between each feature and daily weight gain using the Pearson correlation coefficient calculation formula. , where the correlation coefficient The general calculation formula is: ,in Indicates the The actual value of a sheep under a certain feature, represents the mean value of all sheep under this feature, Indicates the The daily weight gain of sheep, represents the average daily weight gain of all sheep, Indicates the number of sheep; Correlation coefficient Normalize the rows and get the feature weights of each type of data , where the feature weight The specific calculation formula is: ,in Indicates the The normalized weight of the features, Indicates the The correlation coefficient between each characteristic and daily weight gain, Indicates the number of feature types.

[0023] The feature weight-based The K-means clustering algorithm is used to perform weighted cluster analysis on the sheep in the flock. The specific steps to obtain the cluster analysis results are as follows: Data processing: Based on the current growth data of each sheep, a current growth data set is constructed. The data of different dimensions in the current growth data set are standardized through Z-Score standardization to obtain the standardized current growth data set. The calculation formula of Z-Score standardization is: ,in Represents the original data value, Represents the average value of the corresponding dimension data in the current growth data set, Shows the standard deviation of the corresponding dimension data in the current growth data set, Represents the standardized data value; Determine the number of clusters and use the elbow rule to determine the optimal number of clusters based on the normalized current growth dataset ; Cluster analysis, randomly select the normalized current growth data set samples as the initial cluster center, based on the feature weights The weighted Euclidean distance formula is used to calculate the distance between each sample and the center of each cluster, and the sample is assigned to the nearest cluster. The mean of all samples in each cluster is calculated and the mean is used as the new cluster center. The assignment and update process is repeated until the change in the cluster center is less than a certain threshold or the maximum number of iterations is reached, and the cluster analysis result is obtained. The weighted Euclidean distance formula is as follows: ,in and are the values ​​of the two samples on each type of data.

[0024] The above steps use the K-means clustering algorithm to perform weighted cluster analysis on the sheep in the flock, obtain cluster analysis results, and classify the sheep in the flock according to the cluster analysis results. This not only fully considers the individual differences and growth characteristics of the sheep to achieve more accurate and efficient breeding management, and ensures that each sheep is marketed in the best condition, thereby improving the quality and yield of mutton, reducing breeding costs and increasing economic benefits, but also helps to optimize feed utilization efficiency and resource allocation, and improve the efficiency and sustainability of the entire breeding process, thereby improving the economic benefits of this sheep growth data monitoring and management method and system.

[0025] It should be noted that after obtaining the cluster analysis results, clustering results need to be verified, that is, first calculate the weighted average distance between samples within the cluster and the weighted average distance between clusters to obtain the silhouette coefficient of all samples, and then take the average of the silhouette coefficients of all samples to obtain the overall clustering effect evaluation, where the silhouette coefficient The specific calculation formula is: ,in The value range is ,and The larger the value of is, the better the clustering effect is. Indicates the The weighted average distance from a sample to other samples in the same cluster, Indicates the The minimum weighted average distance from a sample to samples in other clusters.

[0026] The optimal number of clusters is determined based on the standardized current growth data set and the elbow rule The specific steps are: Calculate the sum of squared errors within clusters under different cluster numbers , the calculation formula is: ,in is the number of clusters, It is clusters, It is The center of the cluster, It is a sample To cluster center The weighted Euclidean distance of ; Plot the within-cluster sum of squared errors With the number of clusters Variation of the elbow plot, selecting the elbow point as the optimal number of clusters .

[0027] The specific steps of constructing a flock growth curve model based on the optimized Gompertz model and fitting the flock growth curve model according to the pre-processed historical monitoring data of various flocks to obtain personalized flock growth curve models for various flocks are as follows: The pre-processed historical weight change data of various sheep flocks were obtained. The Gompertz model was optimized based on the significant impact of annual temperature changes on sheep growth, and a sheep flock growth curve model was constructed based on this data. The specific model formula is: ,in Sheep in time Weight at is the theoretical maximum weight of a sheep. It is the growth inflection point time, indicating the critical point where the growth rate of sheep changes from fast to slow. is the growth rate constant, is the temperature fluctuation coefficient, which is used to quantify the effect of temperature changes on sheep growth. is the temperature impact factor, which is used to simulate the significant impact of annual periodic changes in temperature on sheep growth by introducing a sine function term; According to prior knowledge or experience, the parameters 、 、 and The initial value is guessed, and the model parameters are fitted using nonlinear regression analysis based on the pre-processed historical weight change data of each type of sheep flock. The parameters are adjusted through iterative optimization algorithms (such as Newton iteration method and Levenberg-Marquardt algorithm) so that the residual sum of squares is Minimize and get the parameters 、 、 and The final estimate of the parameter 、 、 and The final estimated value is brought into the herd growth curve model to obtain the personalized herd growth curve model of each type of herd, where the residual sum of squares is The specific calculation formula is: ,in is the number of data points, It is A point in time, The flock is in the first Actual average weight at the time point.

[0028] The above steps construct a flock growth curve model based on the optimized Gompertz model, and obtain the recommended time for the release of various flocks based on the personalized flock growth curve model obtained by data fitting. and recommended market weight It not only enables farmers to choose to market the sheep when the growth efficiency is optimal, thereby ensuring the quality of mutton and maximizing economic benefits, but also determines the market release time based on scientific models, which can reduce the uncertainty of farmers' reliance on experience and judgment, and enhance the rationality of production plans and market supply stability. It can also effectively reduce feed waste and excessive resource consumption, thereby reducing breeding costs and improving resource utilization efficiency, and improving the economic benefits of this sheep growth data monitoring and management method and system.

[0029] The recommended time for marketing of various types of sheep is obtained based on the personalized sheep growth curve model and recommended market weight , at the recommended time of release Obtain market price data in real time and calculate the economic benefits to obtain the latest time for each type of sheep to be marketed The specific steps are: For each type of sheep flock, select the growth inflection point time As the recommended time for market release, the recommended time for market release will be Bring in personalized flock growth curve model and get recommended slaughter weight , recommended slaughter weight The calculation formula is: ; Get recommended market time The market price of mutton , feed market price , daily feed consumption and other daily farming costs , construct the economic benefit equation and solve it to get the latest time for each type of sheep to be marketed , the economic benefit equation is: ,in represents the total number of sheep in the flock, and Respectively represent the sheep at time and time Weight at the time.

[0030] The above steps are carried out by recommending the time of market release. Obtain market price data in real time and calculate the economic benefits to obtain the latest time for each type of sheep to be marketed It can accurately reflect the actual economic results brought by daily routine breeding activities, so that breeders can have a clear understanding of the breeding economic situation and adjust the breeding strategy in time according to real data. It also determines the latest time of marketing based on the principle of equivalence between economic benefits and costs, and can obtain the key nodes for maximizing breeding benefits and minimizing risks, which helps breeders plan marketing plans in advance to avoid subsequent potential risks and ensure the stable realization of breeding benefits, thereby improving the economic benefits of this sheep growth data monitoring and management method and system.

[0031] Example 2, a sheep growth data monitoring and management system, such as Figure 2 As shown, it includes a data acquisition module, a data processing module, a cluster analysis module, a model building module, a time calculation module and a market recommendation module. The data acquisition module is used to obtain the current growth data and historical monitoring data of each sheep in the flock through monitoring equipment. The historical monitoring data includes historical weight change data, historical body size change data, historical feed intake change data and historical feeding environment change data; Data processing module: used to clean and process the historical monitoring data of each sheep to obtain pre-processed historical monitoring data; Cluster analysis module: used to determine the main characteristics based on the current growth data of each sheep and obtain the characteristic weights of various types of data through correlation analysis , based on feature weights Then, a weighted cluster analysis is performed on the sheep in the flock using the K-means clustering algorithm to obtain cluster analysis results, and the sheep in the flock are classified according to the cluster analysis results; Model construction module: used to construct a flock growth curve model based on the optimized Gompertz model, and fit the flock growth curve model according to the pre-processed historical monitoring data of various flocks to obtain personalized flock growth curve models for various flocks; Time calculation module: used to obtain the recommended time for each type of sheep to be marketed based on the personalized sheep growth curve model and recommended market weight , at the recommended time of release Obtain market price data in real time and calculate the economic benefits to obtain the latest time for each type of sheep to be marketed ; Slaughter recommendation module: used to recommend the time of slaughter and the latest time of release Constructing recommended time intervals for market release Select the appropriate time to market the sheep and market the corresponding type of sheep.

[0032] It should be understood that those skilled in the art may make improvements or modifications based on the above description, and all such improvements and modifications shall fall within the scope of protection of the appended claims. Any portion of this specification not described in detail is prior art known to those skilled in the art.

Claims

1. A method for monitoring and managing sheep growth data, characterized in that: The following steps are involved: Acquiring the current growth data and historical monitoring data of each sheep in the flock through monitoring equipment, wherein the historical monitoring data includes historical weight change data, historical body size change data, historical feed intake change data, and historical feeding environment change data; Clean and process the historical monitoring data of each sheep to obtain pre-processed historical monitoring data; Determine the main characteristics based on the current growth data of each sheep and obtain the characteristic weights of each type of data through correlation analysis , based on feature weights Then, a weighted cluster analysis is performed on the sheep in the flock using the K-means clustering algorithm to obtain cluster analysis results, and the sheep in the flock are classified according to the cluster analysis results; A flock growth curve model is constructed based on the optimized Gompertz model, and the flock growth curve model is fitted according to the pre-processed historical monitoring data of various flocks to obtain personalized flock growth curve models for various flocks. Obtain recommended market release time for various sheep flocks based on personalized sheep growth curve model Recommended slaughter weight , at the recommended time of release Obtain market price data in real time and calculate the economic benefits to obtain the latest time for each type of sheep to be marketed ; Based on recommended market time and the latest time of release Constructing recommended time intervals for market release , according to user needs from the recommended time interval Select the appropriate time to market the sheep and market the corresponding type of sheep.

2. The sheep growth data monitoring and management method according to claim 1, characterized in that: The current growth data includes the sheep's age, weight, height, oblique length, chest circumference, daily weight gain, total duration of illness and feed intake; the historical body size change data includes the sheep's height change data, oblique length change data and chest circumference change data; the historical feed intake change data includes the sheep's daily feed intake change data and the material ratio change data in the feed; the historical feeding environment change data includes the feeding temperature change data and humidity change data.

3. The sheep growth data monitoring and management method according to claim 2, characterized in that: Get the feature weight The steps are: classify the sheep based on their growth rate differences, select daily weight gain as the main feature, and other types of data as secondary features, and calculate the correlation coefficient between each feature and daily weight gain using the Pearson correlation coefficient calculation formula. ; Correlation coefficient Perform normalization and obtain the feature weights of various types of data .

4. The sheep growth data monitoring and management method according to claim 3, characterized in that: The steps of obtaining the cluster analysis results are: A current growth dataset is constructed based on the current growth data of each sheep, and the data of different dimensions in the current growth dataset are standardized through Z-Score standardization to obtain a standardized current growth dataset; Determine the optimal number of clusters based on the normalized current growth dataset using the elbow rule ; Randomly select the normalized current growth dataset samples as the initial cluster center, based on the feature weights The distance between each sample and the center of each cluster is calculated using the weighted Euclidean distance formula, and the sample is assigned to the nearest cluster. The mean of all samples in each cluster is calculated and used as the new cluster center. The assignment and update process is repeated until the change in the cluster center is less than a certain threshold or the maximum number of iterations is reached, and the cluster analysis results are obtained.

5. The sheep growth data monitoring and management method according to claim 4, characterized in that: The steps of obtaining the personalized flock growth curve model for each type of sheep flock are as follows: obtaining pre-processed historical weight change data of each type of sheep flock, optimizing the Gompertz model based on the significant impact of annual periodic temperature changes on sheep growth, and constructing a flock growth curve model based on the data. The model formula is: ,in Sheep in time Weight at is the theoretical maximum weight of a sheep. It is the growth inflection point time, indicating the critical point where the growth rate of sheep changes from fast to slow. is the growth rate constant, is the temperature fluctuation coefficient, which is used to quantify the effect of temperature changes on sheep growth. is the temperature impact factor, which is used to simulate the significant impact of annual periodic changes in temperature on sheep growth by introducing a sine function term; According to prior knowledge or experience, the parameters 、 、 and The initial value is guessed, and the model parameters are fitted using nonlinear regression analysis based on the pre-processed historical weight change data of each type of sheep flock. The parameters are adjusted through iterative optimization algorithm so that the residual sum of squares is Minimize and get the parameters 、 、 and The final estimate of the parameter 、 、 and The final estimated value is brought into the herd growth curve model to obtain the personalized herd growth curve model of each type of herd, where the residual sum of squares is The calculation formula is: ,in is the number of data points, It is A point in time, The flock is in the The actual average weight at each time point.

6. The sheep growth data monitoring and management method according to claim 5, characterized in that: Get the recommended time to market each type of sheep , recommended slaughter weight and the latest time of release The steps are: For each type of sheep flock, select the growth inflection point time As the recommended time for market release, the recommended time for market release will be Bring in personalized flock growth curve model and get recommended slaughter weight , recommended slaughter weight The calculation formula is: ; Get recommended market time The market price of mutton , feed market price , daily feed consumption and other daily farming costs , construct the economic benefit equation and solve it to get the latest time for each type of sheep to be marketed , the economic benefit equation is: ,in represents the total number of sheep in the flock, and Respectively represent the sheep at time and time Weight at the time.

7. A sheep growth data monitoring and management system, applied to a sheep growth data monitoring and management method according to any one of claims 1 to 6, characterized in that: include: A data acquisition module is used to obtain the current growth data and historical monitoring data of each sheep in the flock through monitoring equipment; Data processing module, used to clean and process the historical monitoring data of each sheep; Cluster analysis module, used to obtain the characteristic weights of various types of data in the current growth data through correlation analysis , perform weighted cluster analysis on the sheep in the flock using the K-means clustering algorithm, and classify the sheep according to the cluster analysis results; The model building module is used to build a flock growth curve model and fit the flock growth curve model based on the pre-processed historical monitoring data of various flocks; Time calculation module, used to obtain the recommended time for each type of sheep to be marketed based on the personalized sheep growth curve model and recommended market weight And by calculating the economic benefits, we can get the latest time for each type of sheep to be marketed. ; The market recommendation module is used to build the recommended market time interval , and recommend the time interval for market release based on user needs Choose the appropriate time to market.

Images