A livestock statistics monitoring system
By using time series analysis, Cox proportional hazard model and linear regression model in the animal husbandry statistical monitoring system, the growth, reproduction and feed data abnormalities were identified, and the problems of low information integration efficiency and insufficient risk assessment in the existing system were solved, and the problems of improved Livestock management and operation effects.
Patent Information
- Application Number
- CN202411081557.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-12-31
- Estimated Expiration
- 2044-08-08
AI Technical Summary
The existing animal husbandry statistical monitoring system cannot effectively integrate information, resulting in dispersed data, insufficient real-time analysis, insufficient breeding risk assessment, limited feed supply and demand analysis, lagging response to abnormal situations, insufficient data display and user interaction, which affects the overall animal husbandry industry. Management and operational effectiveness.
A livestock statistical monitoring system including animal husbandry database module, screening statistics module, early warning monitoring module and client module was designed. Livestock growth baseline was established through time series analysis, and reproductive risk was evaluated using the Cox proportional hazard model, and the linear regression model was used to evaluate the reproductive risk. Analyze the relationship between feed consumption and livestock growth, identify abnormal data and issue early warnings, and provide visual display of data.
Real-time data analysis and baseline establishment, systematic risk assessment and abnormal detection have been realized, user interaction efficiency has been improved, the overall management and operational effects of animal husbandry have been optimized, and the efficiency of growth, reproduction and feed management has been improved.
Smart Images
Figure CN118627909B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of animal husbandry statistics monitoring, in particular to an animal husbandry statistics monitoring system. Background Art
[0002] Livestock is an important agricultural sector worldwide, which has a significant impact on economic development, food supply, social stability and environmental protection. Livestock is the main economic pillar in many rural areas, providing income and employment opportunities for local residents and promoting the development of rural economy.
[0003] For example, the announcement number CN108450340B discloses a livestock statistics monitoring system, including a bottom plate, the top of the bottom plate is fixedly connected to a breeding shed body, the top of the bottom plate and one side of the breeding shed body is fixedly connected to a U-shaped pass frame, a rotating shaft is rotatably connected between the two sides of the inner wall of the U-shaped pass frame through a bearing, and the outer surfaces of both ends of the rotating shaft are sleeved with worm sleeves, and the outer surface of the rotating shaft located between the two worm sleeves is sleeved with a first bevel gear, which relates to the field of livestock statistics monitoring technology. This livestock statistics monitoring system greatly facilitates the breeding staff to count the number of cattle and sheep returning to the shed, and well avoids the occurrence of statistical errors. The breeding staff does not need to spend a lot of time to count the cattle and sheep returning to the shed, which reduces the workload of the breeding staff, improves the working efficiency of the breeding staff, and realizes the automatic counting of cattle and sheep returning to the shed that is both fast and accurate.
[0004] For example, announcement number CN109255725B discloses an intelligent management system for animal husbandry production management in the field of animal husbandry management technology, specifically relating to an intelligent management system for animal husbandry production management, including a variety quality management module, a nutrition supply module, a disease prevention and control module, a breeding environment monitoring module and a growth statistics module, the variety quality management module includes purchase channel selection, variety quality screening, qualified standard detection and qualified sample storage; purchase channel selection is used to select different cost-effective purchase channels; variety quality screening is used to select livestock with better varieties in the current purchase channel under different purchase channels; qualified standard detection is used to set the quality of the varieties to be purchased under this management system, and qualified sample storage is used to save qualified varieties and purchase channels for re-purchase; the present invention can effectively overcome the defects of the traditional animal husbandry management system in the prior art that cannot meet daily needs and consumes a lot of human resources.
[0005] In the above-mentioned system, it is mainly used for livestock management decision-making and counting. It is unable to count information and does not provide specific instructions on how to enter livestock information. It faces problems such as data dispersion and management difficulties, insufficient real-time data analysis, insufficient breeding risk assessment, limited analysis of feed supply and demand relationships, delayed response to abnormal situations, and insufficient data display and user interaction. These problems lead to inefficient information integration, untimely problem identification, inaccurate risk assessment, and insufficient resource utilization, affecting the overall management and operation of animal husbandry. Summary of the invention
[0006] In view of the deficiencies of the prior art, the present invention provides a livestock statistics monitoring system, which solves the problems of the above-mentioned background technology.
[0007] To achieve the above purpose, the present invention is implemented through the following technical solutions: a livestock statistics monitoring system, including the following modules: a livestock database module, a screening statistics module, an early warning monitoring module, and a client module; the livestock database module is used to collect and store livestock information, including a growth information statistics unit, a reproduction information statistics unit, and a feed information statistics unit; the growth information statistics unit is used to collect livestock growth data, analyze the changes of livestock growth data over time through time series, establish a livestock growth baseline, detect abnormal values in livestock growth data, identify livestock with abnormal growth and perform statistics; the reproduction information statistics unit is used to collect livestock reproduction data, establish a maternal livestock reproduction risk model through a Cox proportional risk model, analyze the residual results of the maternal livestock reproduction risk model, detect abnormal data points that deviate from the normal trend, and identify livestock with abnormal reproduction. The feed information statistics unit is used to collect livestock feed data, establish a relationship model between feed consumption and livestock growth through a linear regression model, analyze the residual results of the relationship model, detect the abnormal values of the relationship model, identify livestock with abnormal feed supply and demand and perform statistics; the screening statistics module is used to analyze the growth performance, reproductive performance and feed supply and demand relationship of livestock, screen excellent livestock and perform statistics; the early warning monitoring module is used to monitor the data changes of the growth information statistics unit, the reproduction information statistics unit and the feed information statistics unit, and if abnormal values appear in the livestock growth data, livestock reproduction data and livestock feed data, an early warning message is issued; the client module is used to receive the early warning message sent by the early warning monitoring module, and visualize the data changes of the growth information statistics unit, the reproduction information statistics unit and the feed information statistics unit.
[0008] Furthermore, the specific process of establishing a livestock growth baseline by analyzing the changes in livestock growth data over time through time series is as follows: based on livestock growth data, livestock growth trends, seasonality and residual components in livestock growth data are separated through time series, and the ARIMA time series model is trained and fitted; through the trained and fitted ARIMA time series model, the normal growth range and standard are set to generate a livestock growth baseline.
[0009] Furthermore, the specific process of detecting outliers in livestock growth data, identifying livestock with abnormal growth and conducting statistics is as follows: based on the baseline of livestock growth, upper and lower thresholds are set to define the normal growth range; the livestock growth data are compared with the upper and lower thresholds, the residuals of the livestock growth data are calculated, outliers exceeding the upper limit or falling below the lower limit are detected, and the livestock corresponding to the outliers are identified.
[0010] Furthermore, a maternal reproductive risk model was established through the Cox proportional hazard model. The specific process of analyzing the residual results of the maternal reproductive risk model is as follows: based on livestock reproduction data, features of livestock age, health status, and historical reproduction records were extracted to form feature vectors; the maternal reproductive risk model was established using the Cox proportional hazard model to assess the risk of reproductive failure of maternal livestock from mating to the expected date of delivery, and the risk coefficient of each feature was determined; the residuals between the actual reproduction results and the model prediction results were calculated.
[0011] Furthermore, the specific process of detecting abnormal data points that deviate from the normal trend, identifying livestock with reproductive abnormalities and conducting statistics is as follows: analyzing the residuals calculated by the Cox proportional hazard model, identifying residual data points that significantly deviate from the normal trend; setting a residual threshold, detecting abnormal data points that exceed the threshold, and marking them as outliers; analyzing the characteristic information of the time of occurrence and the magnitude of the abnormal values, and identifying the female livestock corresponding to these abnormal residuals.
[0012] Furthermore, a relationship model between feed consumption and livestock growth was established through a linear regression model. The specific process of analyzing the residual results of the relationship model is as follows: based on livestock feed data, the characteristics of the impact of feed consumption on livestock growth were extracted; a relationship model between feed consumption and livestock growth was established using a linear regression model, the impact of feed on livestock growth was evaluated, and the regression coefficient of each feature was determined; the residual between actual feed consumption and model prediction results was calculated, and the difference between model predictions and actual results was analyzed.
[0013] Furthermore, the specific process of detecting outliers in the relationship model, identifying livestock with abnormal feed supply and demand, and conducting statistics is as follows: analyzing the residuals of the linear regression model, identifying residual data points that significantly deviate from the normal trend; setting residual thresholds, detecting abnormal data points that exceed the thresholds, analyzing the abnormal amplitude of the outliers, determining the abnormality of feed supply and demand, and identifying the livestock corresponding to the abnormal data points.
[0014] Furthermore, the specific process of analyzing the growth performance, reproductive performance and feed supply and demand relationship of livestock, screening excellent livestock and conducting statistics is as follows: Based on the livestock growth baseline, the maternal livestock reproduction risk model and the relationship model between feed consumption and livestock growth, the growth performance, reproductive performance and feed supply and demand relationship are comprehensively analyzed, and the livestock excellence coefficient is obtained through weighted average, and excellent livestock is screened out based on the livestock excellence coefficient.
[0015] The present invention has the following beneficial effects:
[0016] (1) This livestock statistics monitoring system establishes a livestock growth baseline through time series analysis, effectively tracking and predicting livestock growth trends. By detecting outliers in growth data, it is possible to promptly identify and handle livestock with abnormal growth, thereby optimizing livestock breeding strategies and improving livestock growth effects and production efficiency. By analyzing the reproductive risk of female livestock through the Cox proportional hazard model, it is possible to systematically assess the risk of reproductive failure, and detect outliers in reproductive data through residual analysis. Identifying livestock with reproductive abnormalities improves the accuracy of reproductive management, reduces the risk of reproductive failure, and improves overall reproductive efficiency.
[0017] (2) This animal husbandry statistical monitoring system uses a linear regression model to establish a relationship model between feed consumption and livestock growth, and effectively analyzes feed supply and demand. By detecting outliers in the relationship model, it is possible to accurately identify abnormalities in feed supply and demand, thereby optimizing feed management, ensuring that the nutritional needs of livestock are met, and improving breeding efficiency. By comprehensively analyzing the growth performance, reproductive performance, and feed supply and demand relationship of livestock, it is possible to screen out livestock with excellent performance and conduct statistics. This improves the efficiency of livestock selection, helps to improve the overall livestock production level and management effect, and achieves optimal allocation of resources.
[0018] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 The present invention is a flow chart of a livestock statistics monitoring system. DETAILED DESCRIPTION
[0020] The embodiment of the present application uses a livestock statistics monitoring system to centrally manage livestock growth, reproduction and feed data, realize real-time data analysis and baseline establishment, provide systematic risk assessment and anomaly detection, and improve user interaction efficiency through visual display, effectively solving the problems of data dispersion, analysis lag, insufficient risk assessment, slow response to abnormal situations and non-intuitive data display in traditional systems, thereby optimizing the overall management and operation effects of animal husbandry.
[0021] The overall idea of the problem in the embodiment of this application is as follows:
[0022] Collect livestock growth data, analyze the changes in livestock growth data over time through time series, establish a livestock growth baseline, detect outliers in livestock growth data, identify livestock with abnormal growth and conduct statistics.
[0023] Collect livestock reproduction data, establish a maternal livestock reproduction risk model through the Cox proportional risk model, analyze the residual results of the maternal livestock reproduction risk model, detect abnormal data points that deviate from the normal trend, identify livestock with abnormal reproduction and conduct statistics.
[0024] Collect livestock feed data, establish a relationship model between feed consumption and livestock growth through a linear regression model, analyze the residual results of the relationship model, detect outliers in the relationship model, identify livestock with abnormal feed supply and demand, and conduct statistics.
[0025] Analyze livestock growth performance, reproductive performance and feed supply and demand, screen excellent livestock and conduct statistics.
[0026] Monitor the data changes of growth information statistical units, reproduction information statistical units, and feed information statistical units. If abnormal values appear in livestock growth data, livestock reproduction data, and livestock feed data, issue an early warning.
[0027] The data changes of growth information statistical unit, reproduction information statistical unit and feed information statistical unit are displayed visually.
[0028] See also Figure 1The embodiment of the present invention provides a technical solution: a livestock statistics monitoring system, comprising the following modules: a livestock database module, a screening statistics module, an early warning monitoring module, and a client module; the livestock database module is used to collect and store livestock information, including a growth information statistics unit, a reproduction information statistics unit, and a feed information statistics unit; the growth information statistics unit is used to collect livestock growth data, analyze the changes of livestock growth data over time through time series, establish a livestock growth baseline, detect abnormal values in livestock growth data, identify livestock with abnormal growth and perform statistics; the reproduction information statistics unit is used to collect livestock reproduction data, establish a maternal reproduction risk model through a Cox proportional risk model, analyze the residual results of the maternal reproduction risk model, detect abnormal data points that deviate from the normal trend, identify livestock with abnormal reproduction and perform statistics The feed information statistics unit is used to collect livestock feed data, establish a relationship model between feed consumption and livestock growth through a linear regression model, analyze the residual results of the relationship model, detect outliers in the relationship model, identify livestock with abnormal feed supply and demand and conduct statistics; the screening statistics module is used to analyze the growth performance, reproductive performance and feed supply and demand relationship of livestock, screen excellent livestock and conduct statistics; the early warning monitoring module is used to monitor the data changes of the growth information statistics unit, the reproduction information statistics unit and the feed information statistics unit. If abnormal values appear in the livestock growth data, livestock reproduction data and livestock feed data, an early warning message is issued; the client module is used to receive the early warning message sent by the early warning monitoring module, and visualize the data changes of the growth information statistics unit, the reproduction information statistics unit and the feed information statistics unit.
[0029] In this embodiment, time series analysis is used to track changes in livestock growth data over time and help establish a growth baseline to identify growth anomalies. The baseline is used to assess whether livestock growth data is within the expected range and detect outliers. The Cox proportional hazard model is a statistical model used for survival analysis to evaluate variables that affect the risk of an event. It assumes that the risk ratio is constant at different time points. In the system, the Cox model is used to establish a reproductive risk model for female livestock, assess the risk of reproductive failure, and analyze model residuals. The linear regression model is used to model the linear relationship between two or more variables. It predicts the value of one variable (dependent variable) based on another variable (independent variable) by fitting a straight line. In the system, the linear regression model is used to establish the relationship between feed consumption and livestock growth and analyze abnormalities in feed supply and demand. Residual analysis is an analysis of the difference between the model predicted value and the actual observed value. The residual is the gap between the actual value and the predicted value. In the system, abnormal data points that deviate from the expected trend are identified by analyzing the model residuals to help detect data anomalies.
[0030] Specifically, the specific process of establishing a livestock growth baseline by analyzing the changes in livestock growth data over time through time series is as follows: based on livestock growth data, livestock growth trends, seasonality and residual components in livestock growth data are separated through time series, and the ARIMA time series model is trained and fitted; through the trained and fitted ARIMA time series model, the normal growth range and standard are set to generate a livestock growth baseline.
[0031] In this embodiment, the time series data is decomposed into trend component, seasonal component and residual component, wherein the trend component represents the long-term change trend in the data, the overall upward or downward trend of livestock growth. The seasonal component represents the seasonal periodic fluctuation in livestock growth. The residual component represents the random noise or abnormal fluctuation left after removing the trend and seasonality.
[0032] ARIMA time series model stands for Autoregressive Integrated Moving Average model and is a statistical model used for time series forecasting. It models the dynamics of data through autoregressive, differencing, and moving average components. Autoregressive means using past values to predict current values. Differencing means converting the data series into a stationary series for ease of modeling. Moving average means modeling random noise in the data. Through training, the ARIMA model can capture trends and seasonal patterns in the data and adjust the model parameters to optimize the forecast accuracy. Establish a reference standard line for evaluating whether future data is normal. Set upper and lower limits of the baseline to monitor whether the data deviates from the expected range.
[0033] Specifically, the specific process of detecting outliers in livestock growth data, identifying livestock with abnormal growth and conducting statistics is as follows: based on the baseline of livestock growth, upper and lower thresholds are set to define the normal growth range; the livestock growth data are compared with the upper and lower thresholds, the residuals of the livestock growth data are calculated, outliers exceeding the upper limit or falling below the lower limit are detected, and the livestock corresponding to the outliers are identified.
[0034] In this embodiment, the upper and lower thresholds represent preset ranges of baseline data, which are used to define normal growth intervals. The setting of thresholds generally takes into account the natural fluctuations of growth data and the statistically reasonable range. Defining a normal growth range means a growth range determined according to the upper and lower thresholds, including the baseline and the safety interval above and below it, and data beyond this range is considered abnormal. Comparing growth data with thresholds means comparing the actual livestock growth data with the set upper and lower thresholds. By comparison, it is possible to check whether the actual data falls within the normal range. If the data exceeds the set range, it indicates that there may be an abnormality. Calculate the difference between the actual growth data and the baseline, i.e., the residual. The residual reflects the degree of deviation of the actual data from the baseline. Large residuals may indicate abnormal growth. Identify those data points that exceed the upper and lower thresholds and mark them as outliers. By identifying livestock that are beyond the normal range, further inspections and treatments can be carried out on these livestock, such as adjusting feeding strategies or conducting health checks.
[0035] Specifically, a maternal reproductive risk model was established through the Cox proportional hazard model. The specific process of analyzing the residual results of the maternal reproductive risk model is as follows: based on livestock reproduction data, features of livestock age, health status, and historical reproduction records were extracted to form feature vectors; the maternal reproductive risk model was established using the Cox proportional hazard model to assess the risk of reproductive failure of maternal livestock from mating to the expected date of delivery, and the risk coefficient of each feature was determined; the residuals between the actual reproduction results and the model prediction results were calculated.
[0036] In this embodiment, the characteristics that affect the reproductive risk are extracted from the livestock reproduction data, including the age, health status and historical reproduction records of the female livestock. The historical reproduction records indicate the historical reproduction success or failure records, which can help predict the future reproductive risk. These characteristics are converted into input variables in the mathematical model to establish the risk model. The Cox proportional hazard model is a semi-parametric regression model used to assess the risk of reproductive failure. The Cox proportional hazard model formula is as follows ; In the formula, represents the risk function given feature X at time t. represents the instantaneous risk of an event occurring at time t. Denotes the benchmark risk function. This is the risk function without any feature influence, which represents the basic risk based on time t. The exponential form of the risk ratio represents the impact of feature X on risk. It is a feature The regression coefficient describes the characteristics The risk ratio is , indicating the characteristics The multiple of risk per unit change. , then the risk ratio is , indicating that when the characteristic increases by one unit, the risk increases by approximately 6596.
[0037] Specifically, the specific process of detecting abnormal data points that deviate from the normal trend, identifying livestock with reproductive abnormalities and conducting statistics is as follows: analyzing the residuals calculated by the Cox proportional hazard model, identifying residual data points that significantly deviate from the normal trend; setting a residual threshold, detecting abnormal data points that exceed the threshold, and marking them as outliers; analyzing the characteristic information of the time of occurrence and the magnitude of the abnormal values, and identifying the female livestock corresponding to these abnormal residuals.
[0038] In this embodiment, the reproductive risk residuals of each female livestock are calculated according to the Cox proportional hazard model. These residuals reflect the difference between the actual reproductive results and the model prediction results. The residuals of all female livestock are statistically analyzed, and the mean and standard deviation of the residuals are calculated to identify residual data points that deviate significantly from the normal trend. According to the statistical distribution of the residual data, a threshold is set to distinguish normal data points from abnormal data points. The residuals of each female livestock are compared with the set threshold. Any residuals that exceed the threshold range are marked as outliers. This indicates that the reproductive performance of these female livestock deviates significantly from the normal level predicted by the model. The detected abnormal data points are marked as outliers, and the relevant characteristic information is recorded. By analyzing the characteristic information of these abnormal residuals, the potential causes of reproductive abnormalities are identified.
[0039] Specifically, a relationship model between feed consumption and livestock growth was established through a linear regression model, and the specific process of analyzing the residual results of the relationship model was as follows: based on livestock feed data, the characteristics of the impact of feed consumption on livestock growth were extracted; a linear regression model was used to establish a relationship model between feed consumption and livestock growth, the impact of feed on livestock growth was evaluated, and the regression coefficient of each feature was determined; the residual between actual feed consumption and model prediction results was calculated, and the difference between model predictions and actual results was analyzed.
[0040] In this implementation, relevant features that affect livestock growth are extracted from livestock feed data. Including feed consumption, feed type, feeding frequency, and features closely related to livestock growth are selected to ensure that the linear regression model can accurately reflect the impact of feed consumption on livestock growth. The linear regression model establishment process is as follows: Use a linear regression model to establish the relationship between feed consumption and livestock growth. The basic form of the linear regression model is: ; Among them, Y represents the growth index of livestock, are feed-related characteristics that affect livestock growth, is the intercept, Represents the regression coefficient of each feature, indicating the degree of influence of the feature on livestock growth, is the error term. Through model training, the regression coefficients of each feature are evaluated. These coefficients reflect the specific impact of each feature on livestock growth. The actual feed consumption data are predicted using the established linear regression model to obtain the predicted livestock growth value , calculate the actual growth value and predicted growth value The residual between .
[0041] Specifically, the specific process of detecting outliers in the relationship model, identifying livestock with abnormal feed supply and demand, and conducting statistics is as follows: analyzing the residuals of the linear regression model, identifying residual data points that significantly deviate from the normal trend; setting residual thresholds, detecting abnormal data points that exceed the thresholds, analyzing the abnormal amplitude of the outliers, determining the abnormal feed supply and demand, and identifying the livestock corresponding to the abnormal data points.
[0042] In this embodiment, in the relational model, the residual of each data point is obtained by calculating the difference between the actual growth value and the model predicted growth value; the residuals of all data points are statistically analyzed to understand their distribution. Under normal circumstances, the residuals should be distributed around the zero value, and most of the residuals should be concentrated in a smaller range. Based on the statistical characteristics of the residuals (such as the mean and standard deviation), a threshold range is set to distinguish normal residuals from abnormal residuals. Identify data points whose residual values exceed the threshold. These data points are considered to be outliers that deviate significantly from the normal trend. For the detected abnormal data points, the amplitude of their residuals is calculated to determine the degree of their deviation from the normal trend. Analyze the abnormal amplitude to assess the severity of the abnormality in feed supply and demand. Large abnormal residuals indicate a serious imbalance in feed supply and demand. Match the detected abnormal data points with specific livestock data to identify the specific livestock corresponding to these abnormal residuals.
[0043] Specifically, the specific process of analyzing livestock growth performance, reproductive performance and feed supply and demand, screening excellent livestock and conducting statistics is as follows: Based on the livestock growth baseline, the maternal livestock reproduction risk model and the relationship model between feed consumption and livestock growth, the growth performance, reproductive performance and feed supply and demand are comprehensively analyzed, and the livestock excellence coefficient is obtained through weighted average, and excellent livestock is screened out based on the livestock excellence coefficient.
[0044] In this implementation plan, livestock information is integrated based on the following three data, and growth performance is measured based on the deviation of livestock growth data from the baseline. Reproductive performance is evaluated by the residuals of the maternal reproductive risk model. Feed supply and demand are evaluated by analyzing the impact of feed consumption on livestock growth through a linear regression model. The growth performance, reproductive performance and feed supply and demand of each livestock are quantified into specific values. Assume that each performance is assigned a score, for example, growth performance score: based on the deviation from the baseline, the smaller the deviation below the baseline, the higher the score; reproductive performance score: based on the absolute value of the Cox model residual, the smaller the residual, the higher the score; feed supply and demand score: based on the residual of the linear regression model, the closer the residual is to zero, the higher the score. Assign a weight to each performance to reflect its importance in the comprehensive evaluation. The formula for synthesizing these scores into a comprehensive excellence coefficient using the weighted average method is as follows: ;in, It represents the livestock quality coefficient, is the growth performance score, is the reproductive performance score, is the feed supply and demand fraction, represents the growth performance score weight, represents the reproductive performance score weight, Represents the feed supply and demand score weight.
[0045] In summary, this application has at least the following effects:
[0046] A livestock statistics monitoring system optimizes the statistical monitoring of livestock by setting up a livestock database module, a screening statistics module, an early warning monitoring module, and a client module. A baseline is established through time series analysis to identify growth anomalies in real time, thereby optimizing growth strategies and improving production efficiency. The Cox proportional risk model is used to assess reproductive risk, detect anomalies in reproductive data, and reduce the risk of reproductive failure. At the same time, a linear regression model is used to analyze the relationship between feed consumption and livestock growth, identify feed supply and demand anomalies, and optimize feed management to meet the nutritional needs of livestock. Comprehensive analysis of growth, reproduction, and feed data is performed to screen out excellent livestock, and data changes are monitored in real time to quickly respond to potential problems. It also provides a visual display of data, which enhances data understanding and management and improves decision-making efficiency.
[0047] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0048] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0049] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0051] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0052] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A livestock statistics monitoring system, characterized in that: It includes the following modules: livestock database module, screening statistics module, early warning monitoring module, and client module; The livestock database module is used to collect and store livestock information, including a growth information statistics unit, a reproduction information statistics unit, and a feed information statistics unit; The growth information statistics unit is used to collect livestock growth data, analyze the changes of livestock growth data over time through time series, establish livestock growth baselines, detect abnormal values in livestock growth data, identify livestock with abnormal growth and conduct statistics; The reproduction information statistics unit is used to collect livestock reproduction data, establish a maternal reproduction risk model through a Cox proportional risk model, analyze the residual results of the maternal reproduction risk model, detect abnormal data points that deviate from the normal trend, identify livestock with abnormal reproduction and perform statistics; The feed information statistics unit is used to collect livestock feed data, establish a relationship model between feed consumption and livestock growth through a linear regression model, analyze the residual results of the relationship model, detect abnormal values of the relationship model, identify livestock with abnormal feed supply and demand, and perform statistics; The screening and statistics module is used to analyze the growth performance, reproductive performance and feed supply and demand relationship of livestock, screen excellent livestock and conduct statistics; The early warning monitoring module is used to monitor the data changes of the growth information statistical unit, the reproduction information statistical unit, and the feed information statistical unit. If abnormal values appear in the livestock growth data, livestock reproduction data, and livestock feed data, an early warning message is issued; The client module is used to receive the early warning information sent by the early warning monitoring module, and to visualize the data changes of the growth information statistical unit, the reproduction information statistical unit, and the feed information statistical unit; The specific process of establishing a livestock growth baseline by analyzing the change of livestock growth data over time through time series is as follows: Based on livestock growth data, the livestock growth trend, seasonality and residual components in the livestock growth data are separated through time series, and the ARIMA time series model is trained and fitted; By training the fitted ARIMA time series model, the normal growth range and standard are set to generate a baseline for livestock growth; The specific process of detecting abnormal values in livestock growth data, identifying livestock with abnormal growth and performing statistics is as follows: Based on the baseline of livestock growth, set upper and lower thresholds to define the normal growth range; Compare livestock growth data with upper and lower thresholds, calculate the residual of livestock growth data, detect outliers that exceed the upper limit or fall below the lower limit, and identify the livestock corresponding to the outliers; The specific process of establishing the maternal reproductive risk model through the Cox proportional hazard model and analyzing the residual results of the maternal reproductive risk model is as follows: Based on livestock reproduction data, feature extraction is performed on the age, health status, and historical reproduction records of livestock to form feature vectors; The Cox proportional hazard model was used to establish a reproductive risk model for female livestock, assess the risk of reproductive failure in female livestock from mating to the expected date of delivery, and determine the risk coefficient for each characteristic; Calculate the residuals between actual reproductive outcomes and those predicted by the model; The specific process of detecting abnormal data points that deviate from the normal trend, identifying livestock with abnormal reproduction and conducting statistics is as follows: Analyze the residuals calculated from the Cox proportional hazards model and identify residual data points that deviate significantly from the normal trend; Set the residual threshold, detect abnormal data points that exceed the threshold, and mark them as outliers; Analyze the characteristic information of the time and magnitude of abnormal values, and identify the female animals corresponding to these abnormal residuals; The specific process of establishing the relationship model between feed consumption and livestock growth through a linear regression model and analyzing the residual results of the relationship model is as follows: Based on livestock feed data, extract characteristics of the impact of feed consumption on livestock growth; Use linear regression models to model the relationship between feed consumption and livestock growth, assess the effect of feed on livestock growth, and determine the regression coefficient for each characteristic; Calculate the residual between actual feed consumption and model prediction results, and analyze the difference between model prediction and actual results; The specific process of detecting the abnormal values of the relationship model, identifying livestock with abnormal feed supply and demand, and conducting statistics is as follows: Analyze linear regression model residuals and identify residual data points that deviate significantly from the normal trend; Set residual thresholds, detect abnormal data points that exceed the threshold, analyze the magnitude of abnormality of the outliers, determine the anomaly in feed supply and demand, and identify the livestock corresponding to the abnormal data points; The specific process of analyzing the growth performance, reproductive performance and feed supply and demand relationship of livestock, selecting excellent livestock and conducting statistics is as follows: Based on the livestock growth baseline, the maternal livestock reproduction risk model and the relationship model between feed consumption and livestock growth, a comprehensive analysis of growth performance, reproductive performance and feed supply and demand is conducted, and the livestock quality coefficient is obtained through weighted average. Excellent livestock is screened out based on the livestock quality coefficient.