Efficient feeding method for meat rabbits

Abstract

The invention discloses an efficient feeding method for meat rabbits. The method comprises the following steps that biological characteristics are dynamically monitored, wherein individual weight, body surface temperature, heart rate and motion trail data are obtained in real time through an intelligent necklace; dynamic genetic breeding: screening high-quality breeding rabbits based on the monitoring data; intelligent grouping regulation and control: dynamically adjusting a group structure according to individual behavior characteristics, wherein the grouping period is 72 + / -12 hours; accurate nutrition supply: optimizing a feed formula according to real-time growth data, and improving the digestibility by adopting a steam conditioning technology; intelligent environment regulation and control: a temperature and humidity sensor is linked with a water curtain-fan system; disease early warning prevention and control: integrating biological characteristics and environmental data, and early warning disease outbreak 72 hours in advance. Therefore, by realizing data-driven management of the meat rabbit breeding process, the feed conversion rate and the growth efficiency are effectively improved, the morbidity is reduced, and the comprehensive breeding benefit is improved.

Description

Technical Field

[0001] This application relates to the technical field of meat rabbit breeding, and particularly to an efficient feeding method for meat rabbits. Background Art

[0002] Traditional meat rabbit feeding models mainly rely on manual experience management, and there are the following technical problems:

[0003] Low individual monitoring efficiency: Methods such as manual weighing and observing behaviors cannot obtain dynamic physiological data in real time, resulting in a lag in discovering individuals with abnormal growth;

[0004] Coarse group management: Fixed grouping methods are prone to cause fights between individuals, reducing feed conversion rate and survival rate;

[0005] Imprecise nutrition supply: Feed formulations rely on fixed standards and are not dynamically adjusted in combination with real-time growth data, resulting in nutritional waste or deficiency;

[0006] Passive disease prevention and control: Symptom-based diagnosis methods are difficult to give early warnings, missing the best treatment opportunities;

[0007] Lagging environmental regulation: Temperature and humidity control rely on manual intervention and cannot be dynamically optimized according to group behaviors.

[0008] In related technologies, although some farms have introduced sensor monitoring, the data integration and decision support capabilities are insufficient, and full-process intelligent management has not been achieved, restricting the large-scale and efficient development of meat rabbit breeding. Summary of the Invention

[0009] This application aims to solve at least one of the technical problems in the related technologies to some extent.

[0010] To this end, an object of this application is to provide an efficient feeding method for meat rabbits, which realizes data-driven management of the meat rabbit breeding process through technologies such as intelligent monitoring, precise nutrition regulation, and environmental optimization, effectively improves feed conversion rate and growth efficiency, reduces the incidence of diseases, and improves the comprehensive breeding efficiency.

[0011] To achieve the above object, the first aspect embodiment of this application proposes an efficient feeding method for meat rabbits, including the following steps:

[0012] Dynamic monitoring of biological characteristics: Real-time acquisition of individual body weight, body surface temperature, heart rate, and movement trajectory data through intelligent collars;

[0013] Dynamic genetic selection: Screening high-quality breeding rabbits based on the monitoring data;

[0014] Intelligent group regulation: Dynamically adjusting the group structure according to individual behavior characteristics, and the grouping period is 72 ± 12 hours;

[0015] Precise nutrition supply: Optimize the feed formula according to real-time growth data and adopt steam conditioning technology to improve digestibility;

[0016] Intelligent environment control: The temperature and humidity sensors are linked to the water curtain - fan system;

[0017] Disease early warning and prevention: Integrate biometric and environmental data to predict disease outbreaks 72 hours in advance.

[0018] An efficient feeding method for meat rabbits in an embodiment of the present application realizes data-driven management of the meat rabbit breeding process through technologies such as intelligent monitoring, precise nutrition regulation, and environmental optimization, effectively improving feed conversion rate and growth efficiency, reducing the incidence of diseases, and enhancing the comprehensive breeding benefit.

[0019] In addition, an efficient feeding method for meat rabbits proposed above according to the present application may also have the following additional technical features:

[0020] In an embodiment of the present application, the dynamic biometric monitoring is calculated by the following formula:

[0021] Body weight: W = k·△P + b, where △P is the pressure change value (kPa), k is the sensor sensitivity coefficient, and b is the calibration constant;

[0022] Body surface temperature: T 体表 = T 红外 +ΔT 环境 ΔT 环境 is the environmental temperature correction value;

[0023] Heart rate: T 周期 is the peak interval time of the pulse wave;

[0024] Movement trajectory: Reconstruct the displacement based on GPS positioning (accuracy ±10m) and acceleration integration.

[0025] In an embodiment of the present application, the dynamic monitoring data is used to drive the LSTM neural network to predict the growth trend, and the network includes:

[0026] Input layer: 6-dimensional features (body weight, feed intake, number of exercise steps, etc.) for the past 7 days;

[0027] Bidirectional LSTM hidden layer: 128 memory units, and the state is updated by the following formula:

[0028] f t = σ(W f ·[h t-1 , x t +b f )

[0029] i t= σ(W i · [h t-1 , x t + b i )

[0030]

[0031] h t = o t ⊙ tanh(C t ),

[0032] where σ is the Sigmoid function, and ⊙ is element-wise multiplication.

[0033] In an embodiment of the present application, the intelligent clustering control is based on a fuzzy clustering algorithm and includes the following steps:

[0034] Feature standardization:

[0035] Membership degree calculation: Gaussian function where σ = 0.2 and m = 2;

[0036] Cluster center update:

[0037] Clustering rule base: includes the aggression index formula

[0038] In an embodiment of the present application, the dynamic nutrition optimization adjusts the feed formula based on real-time data and includes the following formulas:

[0039] When the daily weight gain < 30g, the protein supply increases by 10%;

[0040] Add 0.3% astragalus polysaccharide during lactation and supplement 0.5% sulfur-containing amino acids during molting;

[0041] The steam conditioning technology controls the starch gelatinization degree ≥ 85% and the protein denaturation rate ≤ 15%.

[0042] In an embodiment of the present application, the disease warning system is based on an SVM model and integrates the following indicators:

[0043] Abnormal body temperature (> 39.5°C);

[0044] Feed intake decreased by > 20%;

[0045] The number of steps taken decreased by > 30%;

[0046] The prediction accuracy rate ≥ 90% and the response time ≤ 2 hours.

[0047] In an embodiment of the present application, the environmental control system dynamically adjusts parameters through the following formula:

[0048] Summer temperature control: 20±2°C;

[0049] Winter temperature control: 15±2°C;

[0050] When the group lying rate > 60%, the ventilation frequency increases by 5%.

[0051] Compared with the prior art, the beneficial effects of this application are as follows:

[0052] 1. Dynamic monitoring and prediction: Based on the intelligent collar, 6D data such as body weight, body temperature, and heart rate are collected in real time. Combining with the LSTM neural network to predict the growth trend, the prediction accuracy is improved, providing data support for genetic breeding and nutritional regulation.

[0053] 2. Optimization of population structure: The fuzzy clustering algorithm combines the aggression index (AI) to dynamically group the population. The grouping period is shortened, the frequency of group fights is reduced, and the feed conversion rate is improved.

[0054] 3. Precise nutrition supply: The steam conditioning technology makes the starch gelatinization degree ≥85% and the protein denaturation rate ≤15%. Adding astragalus polysaccharide during lactation can increase milk production, and supplementing sulfur-containing amino acids during the molting period can reduce the hair loss rate.

[0055] 4. Active disease prevention and control: The SVM model integrates multi-dimensional indicators such as body temperature, feed intake, and exercise steps, realizes early warning 72 hours in advance, improves the prediction accuracy, and reduces the incidence rate.

[0056] 5. Intelligent environmental control: The temperature and humidity are linked to the water curtain - fan system. The summer temperature fluctuation is controlled within ±2°C. When the winter group lying rate > 60%, the ventilation is automatically increased, reducing the incidence of respiratory diseases.

[0057] The additional aspects and advantages of this application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of this application. Description of the Drawings

[0058] The above and / or additional aspects and advantages of this application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0059] Figure 1 It is a schematic flow chart of an efficient meat rabbit breeding method according to an embodiment of this application. Detailed Embodiments

[0060] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0061] The following describes a method for efficiently raising meat rabbits according to an embodiment of the present application with reference to the accompanying drawings.

[0062] As Figure 1 shown, a method for efficiently raising meat rabbits according to an embodiment of the present application may include the following steps:

[0063] Biometric dynamic monitoring: Real-time acquisition of individual body weight, body surface temperature, heart rate, and movement trajectory data through a smart collar;

[0064] Dynamic genetic selection: Screening of high-quality breeding rabbits based on the monitoring data;

[0065] Intelligent group regulation: Dynamically adjusting the group structure according to individual behavior characteristics, with a grouping cycle of 72 ± 12 hours;

[0066] Precise nutrition supply: Optimizing the feed formula according to real-time growth data and adopting steam conditioning technology to improve digestibility;

[0067] Intelligent environment regulation: Linking the temperature and humidity sensors with the water curtain - fan system;

[0068] Disease early warning and prevention: Integrating biometric and environmental data to early warn of disease outbreaks 72 hours in advance.

[0069] Specifically,

[0070] In an embodiment of the present application, biometric dynamic monitoring is calculated by the following formula:

[0071] Body weight: W = k·ΔP + b, where ΔP is the pressure change value (kPa), k is the sensor sensitivity coefficient, and b is the calibration constant;

[0072] Body surface temperature: T 体表 = T 红外 + ΔT 环境 ΔT 环境 is the environmental temperature correction value;

[0073] Heart rate: T 周期 is the peak interval time of the pulse wave;

[0074] Movement trajectory: Reconstructing displacement based on GPS positioning (accuracy ±10m) and acceleration integration.

[0075] In one embodiment of the present application, the dynamic monitoring data is used to drive an LSTM neural network to predict the growth trend. The network includes:

[0076] Input layer: 6-dimensional features (body weight, feed intake, number of exercise steps, etc.) for the past 7 days;

[0077] Bidirectional LSTM hidden layer: 128 memory units, updating the state through the following formula:

[0078] f t =σ(W f ·[h t-1 ,x t +b f )

[0079] i t =σ(W i ·[h t-1 ,x t +b i )

[0080]

[0081] h t =o t ⊙tanh(C t ),

[0082] where σ is the Sigmoid function, and ⊙ is the element-wise multiplication.

[0083] In one embodiment of the present application, the intelligent grouping control is based on the fuzzy clustering algorithm and includes the following steps:

[0084] Feature standardization:

[0085] Membership degree calculation: Gaussian function where σ = 0.2 and m = 2;

[0086] Cluster center update:

[0087] Grouping rule library: includes the formula for the aggression index

[0088] In one embodiment of the present application, the dynamic nutrition optimization adjusts the feed formula based on real-time data and includes the following formula: when the daily weight gain is less than 30 g, the protein supply is increased by 10%; 0.3% astragalus polysaccharide is added during lactation, and 0.5% sulfur-containing amino acids are supplemented during the molting period; the steam conditioning technology controls the starch gelatinization degree ≥ 85% and the protein denaturation rate ≤ 15%.

[0089] In one embodiment of the present application, the disease early warning system is based on an SVM model and integrates the following indicators: abnormal body temperature (>39.5°C); a decrease in feed intake of more than 20%; a decrease in the number of steps taken of more than 30%; a prediction accuracy rate of ≥90%, and a response time of ≤2 hours.

[0090] In one embodiment of the present application, the environmental control system dynamically adjusts parameters through the following formula: summer temperature control: 20±2°C; winter temperature control: 15±2°C; when the group lying rate > 60%, the ventilation frequency increases by 5%.

[0091] Specifically, the efficient meat rabbit breeding method provided by the present application realizes full-process data-driven management through intelligent monitoring, precise regulation, and environmental optimization technologies. The specific implementation steps are as follows:

[0092] Deployment of biometric dynamic monitoring hardware: Wear an intelligent collar integrated with a pressure sensor, an infrared temperature measurement module, an accelerometer, and a GPS for each meat rabbit to collect weight, body surface temperature, heart rate, and movement trajectory data in real time.

[0093] Data calculation: The weight is calculated by a formula, where the pressure change value is obtained by the collar pressure sensor, and k and b are determined through laboratory calibration. The body surface temperature is compensated by combining the infrared temperature measurement value with the environmental temperature correction value to eliminate environmental interference. The heart rate is calculated by the peak interval time of the pulse wave, and the movement trajectory is reconstructed by fusing GPS positioning (accuracy ±10m) and acceleration integration to record the daily activity range and the number of steps.

[0094] Integration of dynamic genetic breeding data: Input the monitoring data (such as weight gain rate, feed intake, disease resistance, etc.) into an LSTM neural network to predict the individual growth potential. Model training: The network input is the 6-dimensional features (weight, feed intake, number of steps taken, etc.) of the past 7 days, and the sequential features are learned through a bidirectional LSTM layer (128 memory units).

[0095] Breeding criteria: Select individuals with fast daily weight gain and high feed conversion rate as breeding rabbits according to the prediction results, and eliminate low-performance individuals.

[0096] Feature extraction for intelligent group regulation: Calculate the aggression index based on behavioral data such as movement trajectory and heart rate changes.

[0097] Fuzzy clustering: Standardize the feature data to eliminate the influence of dimension, calculate the individual membership probability using a Gaussian membership function, and iteratively update the clustering center.

[0098] Group execution: Adjust the group structure every 72±12 hours according to the clustering results, separate the individuals with strong aggression into separate groups, and reduce the frequency of fights.

[0099] Dynamic optimization of precise nutrition supply formula: when the daily weight gain < 30g, the protein supply is increased by 10%, 0.3% astragalus polysaccharide is added during lactation, 0.5% sulfur-containing amino acids are supplemented during the molting period, and the steam conditioning technology is used to control the starch gelatinization degree ≥ 85% and the protein denaturation rate ≤ 15% to improve the feed digestibility.

[0100] Feeding method: quantitatively feed according to individual needs through an intelligent feeding system, record the feed intake daily and feedback it to the nutrition model.

[0101] Intelligent environmental control of temperature and humidity: in summer, the temperature is maintained at 20 ± 2°C through the water curtain - fan system, and in winter, it is controlled at 15 ± 2°C through the floor heating system. When the group lying rate > 60%, the ventilation frequency is automatically increased by 5% to prevent respiratory diseases.

[0102] Data linkage: The temperature and humidity sensors upload data to the central control system in real time to trigger the linkage of environmental equipment.

[0103] Disease early warning and prevention with multi-source data fusion: Integrate indicators such as body temperature > 39.5°C, feed intake decrease > 20%, and movement steps decrease > 30%, and input them into the SVM model to predict disease risks.

[0104] Response mechanism: When the prediction accuracy rate ≥ 90%, the system gives an early warning 72 hours in advance and pushes it to the breeding personnel. Isolation treatment is initiated within 2 hours after diagnosis to reduce the risk of disease transmission.

[0105] Specifically, this method realizes the intelligent breeding of meat rabbits through the "monitoring - analysis - decision - execution" closed loop:

[0106] Data collection: The intelligent collar collects the physiological and behavioral data of meat rabbits in real time, and the environmental sensors monitor parameters such as temperature and humidity.

[0107] Model-driven: The LSTM network predicts the growth trend, fuzzy clustering optimizes the grouping, the SVM model warns of diseases, and dynamically adjusts the nutrition and environmental parameters.

[0108] Precise regulation: Automatically optimize the feed formula, grouping structure, and operation of environmental equipment according to the model output to form a real-time feedback system of "data - decision - execution".

[0109] Benefit improvement: Through the intelligent management of the whole process, the cost of manual intervention is reduced, the feed conversion rate and survival rate are improved, and finally the comprehensive breeding benefit is increased.

[0110] In summary, an efficient feeding method for meat rabbits in the embodiments of this application realizes data-driven management of the meat rabbit breeding process through technologies such as intelligent monitoring, precise nutrition regulation, and environmental optimization, effectively improving the feed conversion rate and growth efficiency, reducing the incidence rate, and increasing the comprehensive breeding benefit.

[0111] In the description of this specification, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of this application, "a plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0112] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "examples", "specific examples" or "some examples", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0113] Although the embodiments of this application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting this application. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for efficiently raising meat rabbits, characterized in that, It includes the following steps: Biometric dynamic monitoring: Real-time obtain data on an individual's body weight, body surface temperature, heart rate, and movement trajectory through an intelligent collar; Dynamic genetic breeding: Screen high-quality breeding rabbits based on the monitored data; Intelligent group regulation: Dynamically adjust the group structure according to individual behavior characteristics, with a grouping cycle of 72 ± 12 hours; Precise nutrition supply: Optimize the feed formula according to real-time growth data and use steam conditioning technology to improve digestibility; Intelligent environment regulation: The temperature and humidity sensors are linked to the water curtain - fan system; Disease early warning and prevention: Integrate biometric and environmental data to give an early warning of disease outbreaks 72 hours in advance.

2. The efficient feeding method for meat rabbits according to claim 1, characterized in that The biometric dynamic monitoring is calculated by the following formula: Body weight: W = k·△P + b, where △P is the pressure change value (kPa), k is the sensor sensitivity coefficient, and b is the calibration constant; Body surface temperature: T 体表 = T 红外 + ΔT 环境 , ΔT 环境 is the environmental temperature correction value; Heart rate: T 周期 is the peak interval time of the pulse wave; Movement trajectory: Reconstruct the displacement based on GPS positioning (accuracy ±10m) and acceleration integration.

3. The efficient feeding method for meat rabbits according to claim 1, characterized in that, The dynamic monitoring data is used to drive the LSTM neural network to predict the growth trend. The network includes: Input layer: 6-dimensional features (body weight, feed intake, movement steps, etc.) for the past 7 days; Bidirectional LSTM hidden layer: 128 memory units, and the state is updated by the following formula: f t = σ(W f ·[h t-1 , x t + b f ) i t = σ(W i · [h t-1 , x t + b i ) h t = o t ☉tanh(C t ) where σ is the Sigmoid function and ⊙ is the element-wise multiplication.

4. The efficient feeding method for meat rabbits according to claim 1, wherein The intelligent group regulation is based on the fuzzy clustering algorithm and includes the following steps: Feature standardization: Membership degree calculation: Gaussian function where σ = 0.2 and m = 2; Cluster center update: Clustering rule library: includes the formula for the aggression index 5. A method for efficiently raising meat rabbits according to claim 1, characterized in that The dynamic nutrition optimization adjusts the feed formula based on real-time data and includes the following formula: When the daily weight gain < 30g, the protein supply is increased by 10%; Add 0.3% astragalus polysaccharide during lactation and supplement 0.5% sulfur-containing amino acids during the molting period; The steam conditioning technology controls the starch gelatinization degree ≥ 85% and the protein denaturation rate ≤ 15%.

6. A high-efficiency feeding method for meat rabbits according to claim 1, characterized in that, The disease early warning system is based on the SVM model and integrates the following indicators: Abnormal body temperature (> 39.5°C); Feed intake decrease > 20%; Movement steps decrease > 30%; The prediction accuracy rate ≥ 90% and the response time ≤ 2 hours.

7. A method for efficiently raising meat rabbits according to claim 1, characterized in that, The environment regulation system dynamically adjusts the parameters by the following formula: Summer temperature control: 20 ± 2°C; Winter temperature control: 15 ± 2°C; When the group lying rate > 60%, the ventilation frequency is increased by 5%.

Images