A dual-model dynamic coupling poultry green intelligent breeding method and system

Abstract

This invention discloses a dual-model dynamically coupled method and system for green and intelligent poultry farming, belonging to the field of ecological farming technology. The method includes: predicting the change curve of environmental parameters in future periods based on environmental data, and constructing an environmental dynamic compliance model with the objective of minimizing the deviation of the change curve from a preset healthy environment range while simultaneously minimizing the weighted sum of energy consumption of the executing equipment, thereby generating an environmental control command sequence; quantitatively analyzing environmental data, sound data, and video data to calculate a disease risk index and environmental risk factors, and constructing a disease risk prediction model; inputting the disease risk index and environmental risk factors into the environmental dynamic compliance model to obtain an updated environmental control command sequence, and dynamically adjusting the feeding management plan in conjunction with the disease risk index to generate manure scheduling commands. This invention solves the defects of the separation and lagging control between environmental and disease management, achieving the goal of healthy, environmentally friendly, and efficient circular farming.

Description

Technical Field

[0001] This invention relates to the field of ecological aquaculture technology, and in particular to a green and intelligent poultry farming method and system with dual-model dynamic coupling. Background Technology

[0002] Currently, green poultry farming relies primarily on separate technical modules for environmental compliance and disease prevention. Environmental control often employs feedback regulation based on fixed thresholds (e.g., setting a temperature threshold to activate fans), while disease prevention depends on regular immunization, medication, and clinical observation. This disconnect between environmental control and disease prevention presents the following problems: (1) Environmental regulation is lagging and crude, and it is impossible to predict and maintain the optimal environment. Parameters such as ammonia, temperature and humidity fluctuate greatly. (2) The disease early warning is passive and cannot be quantitatively warned based on environmental factors before clinical symptoms appear; (3) Environmental and health management are disconnected, and a large amount of environmental data is not used for in-depth health analysis, becoming isolated data.

[0003] Current technical solutions either only disclose environmental data collection and threshold alarms without involving prediction models or disease correlation models, or only focus on the recognition of sick poultry images without combining them with environmental data-driven approaches.

[0004] Therefore, there is an urgent need for a green and intelligent poultry farming method and system with dynamic coupling of two models, which can use environmental factors to conduct collaborative assessment of proactive disease risks. Summary of the Invention

[0005] The purpose of this invention is to provide a green and intelligent poultry farming method and system with dynamic coupling of two models. By constructing and coupling an environmental dynamic compliance model and a disease risk prediction model, it solves the defects of the separation and lagging control of environmental and disease management, and achieves the goal of healthy, environmentally friendly and efficient circular farming.

[0006] To achieve the above objectives, this invention provides a dual-model dynamically coupled green and intelligent poultry farming method, comprising the following steps: Acquire environmental data, as well as sound and video data of birds; Based on environmental data, predict the change curve of environmental parameters in the future period, and construct an environmental dynamic compliance model with the goal of minimizing the deviation of the change curve from the preset healthy environment range and minimizing the weighted sum of energy consumption of the execution equipment, and generate a sequence of environmental control instructions. Quantitative analysis of environmental data, sound data, and video data was conducted to clarify the relationship between environmental data and disease occurrence, and disease risk index and environmental risk factors were calculated to construct a disease risk prediction model. The disease risk index and environmental risk factors are used as correction variables and input into the environmental dynamic compliance model to optimize the environmental control command sequence and obtain an updated environmental control command sequence. Based on the updated environmental control instruction sequence and disease risk index, the feeding management plan is dynamically adjusted, and manure scheduling instructions are generated for manure control.

[0007] Preferably, based on environmental data, the variation curve of environmental parameters in future periods is predicted. With the objective of minimizing the deviation of the variation curve from a preset healthy environment range, and simultaneously minimizing the weighted sum of energy consumption of the executing equipment, a dynamic environmental compliance model is constructed. The specific content of the generated environmental control instruction sequence includes: Feature extraction was performed on the environmental data to obtain ammonia concentration, temperature, and humidity. Inputting ammonia concentration, temperature, and humidity into a time series prediction model, the model predicts the changes in ammonia concentration, temperature, and humidity over the next 1-4 hours. With the objective function of minimizing the deviation between the change curve and the preset healthy environment range, and minimizing the weighted sum of energy consumption of the executing equipment, an optimization algorithm is used to continuously solve for the optimal switching combination and duration command sequence of the fan, wet curtain and heating equipment in the future finite time domain, so as to obtain the environmental dynamic compliance model.

[0008] Preferably, the specific content of quantitative analysis of environmental data, sound data, and video data to clarify the relationship between environmental data and disease occurrence, and to calculate the disease risk index and environmental risk factors, and construct a disease risk prediction model includes: Perform spectral analysis on the sound data to extract the frequency characteristics of abnormal coughing / sneezing sounds in birds; Target detection and tracking were performed on video data to extract behavioral characteristics such as the decline rate of poultry group activity and the clustering index; Frequency features and behavioral features are fused with ammonia concentration, temperature and humidity within a continuous time window to obtain a feature vector set. Based on the feature vector set, the disease risk index is calculated using the gradient boosting decision tree algorithm; Based on the gradient boosting decision tree algorithm, the importance of feature vector groups is scored based on environmental data to obtain environmental risk factors, and a disease risk prediction model is constructed.

[0009] Preferably, based on the gradient boosting decision tree algorithm, the importance of the feature vector group is scored according to the environmental data to obtain the specific content of the environmental risk factor, including: Based on the gradient boosting decision tree algorithm, the importance of each feature vector is scored by analyzing the number of times each feature vector in the feature vector group is used to split nodes in each decision tree and the amount of error reduction. The importance scores are sorted in descending order, and the feature vector ranked first is identified as the environmental risk factor.

[0010] Preferably, in the objective function, the weights focus on minimizing the deviation between the change curve corresponding to the environmental risk factor and the preset healthy environment range.

[0011] Preferably, the specific content of dynamically adjusting the feeding management plan and generating manure and wastewater dispatch instructions for manure and wastewater control based on the updated environmental control instruction sequence and disease risk index includes: The feeding and management plan is dynamically adjusted based on the disease risk index. Obtain data on poultry age and feed intake; Based on the updated environmental control command sequence, poultry age and feed intake data, calculate real-time manure production and key component content; Based on the output of manure, the content of key components, the real-time status of each resource utilization unit, and demand order information, manure scheduling instructions are generated to regulate manure and wastewater, with the goal of optimizing system economy and resource utilization efficiency.

[0012] Preferably, the specific content of dynamically adjusting the feeding and management plan based on the disease risk index includes: When the disease risk index exceeds the first threshold, the proportion of vitamin C added to the feed will be automatically increased. When the disease risk index exceeds the second threshold, a predetermined dose of electrolytes is automatically added to the drinking water; The second threshold is greater than the first threshold.

[0013] This invention provides a dual-model dynamically coupled green and intelligent poultry farming system for implementing the aforementioned dual-model dynamically coupled green and intelligent poultry farming method, comprising: The data acquisition module is used to acquire environmental data, as well as the sound and video data of poultry; The first model building module is used to predict the change curve of environmental parameters in the future based on environmental data, and to build a dynamic environmental compliance model with the goal of minimizing the deviation of the change curve from the preset healthy environment range and minimizing the weighted sum of energy consumption of the execution equipment, and to generate a sequence of environmental control instructions. The second model building module is used to perform quantitative analysis on environmental data, sound data, and video data, clarify the relationship between environmental data and disease occurrence, calculate the disease risk index and environmental risk factors, and build a disease risk prediction model. The model coupling module is used to input the disease risk index and environmental risk factors as correction variables into the environmental dynamic compliance model to optimize the environmental control command sequence and obtain an updated environmental control command sequence. The dynamic control module is used to dynamically adjust the feeding management plan based on the updated environmental control instruction sequence and disease risk index, and generate manure scheduling instructions for manure control.

[0014] This invention provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it implements the content of the above-described dual-model dynamic coupling green and intelligent poultry farming method.

[0015] This invention provides a storage medium storing computer-executable instructions. When these computer-executable instructions are loaded and executed by a processor, they realize the above-mentioned dual-model dynamic coupling green and intelligent poultry farming method.

[0016] In summary, the dual-model dynamic coupling method and system for green and intelligent poultry farming provided by this invention has the following advantages compared with traditional technologies: By constructing an environmental dynamic compliance model and a disease risk prediction model, and through real-time interaction and iterative optimization of the environmental dynamic compliance model and the disease risk prediction model, the defects of the separation and lagging control of environmental and disease management are solved, achieving true intelligent prevention and precise management, and achieving the goal of healthy, environmentally friendly, and efficient circular farming.

[0017] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a dual-model dynamic coupling method for green and intelligent poultry farming in this invention. Figure 2 This is a schematic diagram of a dual-model dynamically coupled green and intelligent poultry farming system according to the present invention. Detailed Implementation

[0019] The technical method of the present invention will be further described below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application.

[0020] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.

[0021] Techniques, systems, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the instruction manual.

[0022] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0023] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0024] This invention provides a green and intelligent poultry farming method with dynamic coupling of two models, such as... Figure 1 As shown, it includes the following steps: S1. Acquire environmental data, including sound and video data of poultry. The environmental data includes: temperature, humidity, wind speed, ammonia concentration, and light intensity.

[0025] S2. Based on environmental data, predict the change curve of environmental parameters in the future period, and construct an environmental dynamic compliance model with the goal of minimizing the deviation of the change curve from the preset healthy environment range and minimizing the weighted sum of energy consumption of the execution equipment, and generate an environmental control instruction sequence.

[0026] Furthermore, step S2 specifically includes the following steps: S201. Extract features from environmental data to obtain ammonia concentration, temperature, and humidity.

[0027] S202. Input ammonia concentration, temperature, and humidity into the time series prediction model to predict the changes in ammonia concentration, temperature, and humidity over the next 1-4 hours. The time series prediction model includes: a long short-term memory network model, gated recurrent units, and a temporal convolutional network.

[0028] S203. Taking minimizing the deviation between the change curve and the preset healthy environment range, while simultaneously minimizing the weighted sum of energy consumption of the executing equipment, as the objective function, an optimization algorithm is used to continuously solve for the optimal switching combination and duration command sequence of the fan, evaporative cooling pad, and heating equipment within a finite future time domain, thus obtaining an environmental dynamic compliance model. The optimization algorithm used is a model predictive control algorithm. This algorithm is implemented through a model predictive controller, which serves as a key technological bridge connecting environmental prediction and disease risk early warning, ultimately achieving intelligent, forward-looking, and collaborative control.

[0029] S3. Conduct quantitative analysis of environmental data, sound data, and video data to clarify the relationship between environmental data and disease occurrence, calculate the disease risk index and environmental risk factors, and construct a disease risk prediction model.

[0030] Furthermore, step S3 specifically includes the following steps: S301. Perform spectral analysis on the sound data to extract the frequency characteristics of abnormal coughing / sneezing sounds in poultry. Specifically, perform Mel-frequency cepstral coefficient transform on the audio signal of the sound data, and use a pre-trained convolutional neural network classifier to identify time segments containing abnormal breathing sounds, and then count their frequency per unit time.

[0031] S302. Perform target detection and tracking on video data, and extract behavioral characteristics such as the decline rate of poultry group activity and the clustering index.

[0032] S303. The frequency features and behavioral features are fused with the ammonia concentration, temperature and humidity within the continuous time window to obtain a feature vector group.

[0033] S304. Based on the feature vector group, calculate the disease risk index according to the gradient boosting decision tree algorithm.

[0034] S305. Based on the gradient boosting decision tree algorithm, the importance of the feature vector group is scored according to environmental data to obtain environmental risk factors, and a disease risk prediction model is constructed. Specifically, the environmental risk factors obtained by scoring the importance of the feature vector group based on environmental data using the gradient boosting decision tree algorithm include: Based on the gradient boosting decision tree algorithm, the importance of each feature vector is scored by analyzing the number of times each feature vector in the feature vector group is used to split nodes in each decision tree and the amount of error reduction.

[0035] The importance scores are sorted in descending order, and the feature vector ranked first is identified as the environmental risk factor.

[0036] S4. The disease risk index and environmental risk factors are input as correction variables into the environmental dynamic compliance model to optimize the environmental control command sequence, resulting in an updated environmental control command sequence. This process establishes an interaction mechanism between the environmental dynamic compliance model and the disease risk prediction model. When optimizing control commands, the environmental dynamic compliance model not only considers energy consumption and comfort but also actively strengthens the suppression of identified environmental risk factors. For example, when the respiratory disease risk index increases, the environmental dynamic compliance model will prioritize reducing the predicted humidity target value and increasing ventilation within the allowable energy consumption range. Simultaneously, the actual effect data after environmental control is used as new samples for the online updating and learning of both the environmental dynamic compliance model and the disease risk prediction model.

[0037] In the objective function of step S203, the weights and sums focus on minimizing the deviation between the change curve corresponding to the environmental risk factor and the preset healthy environment range.

[0038] S5. Based on the updated environmental control instruction sequence and disease risk index, dynamically adjust the feeding management plan and generate manure scheduling instructions for manure control.

[0039] Furthermore, the specific steps of step S5 include: S501. Dynamically adjust the feeding and management plan based on the disease risk index. The specific content of step S501 includes: When the disease risk index exceeds the first threshold, the proportion of vitamin C added to the feed will be automatically increased.

[0040] When the disease risk index exceeds the second threshold, a predetermined dose of electrolytes is automatically added to the drinking water.

[0041] The second threshold is greater than the first threshold.

[0042] S502. Obtain poultry age and feed intake data.

[0043] S503. Calculate the real-time manure production and key component content based on the updated environmental control command sequence, poultry age, and feed intake data.

[0044] S504. Based on the output of manure, the content of key components, the real-time status of each resource utilization unit, and the demand order information, and with the goal of optimizing system economy and resource utilization efficiency, generate manure scheduling instructions for manure control.

[0045] The resource recovery unit includes at least one of a rapid aerobic fermenter, a black soldier fly larvae culture bioreactor, and an anaerobic fermenter. Real-time status information for the rapid aerobic fermenter includes its current fill rate and internal temperature; real-time status information for the black soldier fly larvae culture bioreactor includes its current substrate thickness and larval stage; and real-time status information for the anaerobic fermenter includes its liquid level and pH value.

[0046] An exemplary embodiment of the present invention is implemented using a large-scale quail house: IoT sensors are deployed in the quail houses to continuously collect data on temperature, humidity, ammonia, carbon dioxide, wind speed, and quail sounds. Historical data from at least one breeding batch is accumulated, including environmental data, medication records, and mortality records. Based on this historical data, dynamic environmental compliance models and disease risk prediction models are constructed and trained.

[0047] The environmental dynamic compliance model reads all real-time data every 10 minutes and uses a long short-term memory network model to predict the upward trend of ammonia concentration in the quail house over the next 2 hours. The model predicts that the controller calculation shows that if the side fan is started at low speed for 20 minutes after 30 minutes, the ammonia concentration can be maintained in the optimal range with the lowest energy consumption. Therefore, this instruction is generated and pre-released.

[0048] The disease risk prediction model analyzes the current environmental data for the past 24 hours and combines it with the sound analysis disease risk index - cough index to calculate the current respiratory disease risk index as 0.15 (low risk).

[0049] The following day, a sharp increase in outdoor humidity was detected. Based on the predicted indoor humidity for the next hour provided by the environmental dynamic compliance model, the disease risk prediction model calculated that the respiratory disease risk index surged to 0.72 (high risk), and identified "high humidity" as an environmental risk factor, immediately feeding it back to the environmental dynamic compliance model. During re-optimization, the model predictive controller of the environmental dynamic compliance model increased the target weight of "reducing humidity," thereby generating a more aggressive, slightly more energy-intensive but more effective combination of ventilation and heating commands to proactively suppress the risk.

[0050] Based on the age of the quail flock, combination instructions, and feed intake data, the feed formula and feeding amount are dynamically adjusted, and the increased moisture content of the manure due to cooling and ventilation is accurately calculated. This batch of manure is then directed to the black soldier fly farming module with efficient dehydration function for processing.

[0051] This invention presents a dual-model dynamically coupled intelligent poultry farming method, constructing a system farming approach with a two-way dynamic coupling of an environmental dynamic compliance model and a disease risk prediction model as its intelligent engine. It predicts environmental trajectories using a long short-term memory network model and employs model predictive control algorithms for proactive regulation. Simultaneously, it analyzes the correlation between environmental sequences and diseases using interpretable models such as gradient boosting decision trees, outputting a disease risk index and environmental risk factors. More importantly, it uses the disease risk index and environmental risk factors as real-time feedback variables to dynamically adjust the optimization objective of the environmental dynamic compliance model, elevating environmental control from maintaining comfort to actively suppressing disease risk. Combined with real-time status data, it intelligently schedules resource cycles, thereby achieving a synergistic transformation from passive response to proactive prevention and from isolated control to collaborative optimization.

[0052] This invention provides a dual-model dynamically coupled green and intelligent poultry farming system, used to implement the aforementioned dual-model dynamically coupled green and intelligent poultry farming method, such as... Figure 2 As shown, it includes: The data acquisition module is used to acquire environmental data, as well as sound and video data of poultry.

[0053] The first model construction module is used to predict the change curve of environmental parameters in the future based on environmental data, and to construct an environmental dynamic compliance model with the goal of minimizing the deviation of the change curve from the preset healthy environment range and minimizing the weighted sum of energy consumption of the execution equipment, and to generate a sequence of environmental control instructions.

[0054] The second model building module is used to perform quantitative analysis on environmental data, sound data, and video data, clarify the relationship between environmental data and disease occurrence, calculate the disease risk index and environmental risk factors, and build a disease risk prediction model.

[0055] The model coupling module is used to input the disease risk index and environmental risk factors as correction variables into the environmental dynamic compliance model to optimize the environmental control command sequence and obtain an updated environmental control command sequence.

[0056] The dynamic control module is used to dynamically adjust the feeding management plan based on the updated environmental control instruction sequence and disease risk index, and generate manure scheduling instructions for manure control.

[0057] The present invention also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it implements the above-mentioned dual-model dynamic coupling green and intelligent poultry farming method.

[0058] The present invention also provides a storage medium storing computer-executable instructions. When the computer-executable instructions are loaded and executed by a processor, the above-mentioned dual-model dynamic coupling green and intelligent poultry farming method is realized.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A dual-model dynamically coupled green and intelligent poultry farming method, characterized in that, Includes the following steps: Acquire environmental data, as well as sound and video data of birds; Based on environmental data, predict the change curve of environmental parameters in the future period, and construct an environmental dynamic compliance model with the goal of minimizing the deviation of the change curve from the preset healthy environment range and minimizing the weighted sum of energy consumption of the execution equipment, and generate a sequence of environmental control instructions. Quantitative analysis of environmental data, sound data, and video data was conducted to clarify the relationship between environmental data and disease occurrence, and disease risk index and environmental risk factors were calculated to construct a disease risk prediction model. The disease risk index and environmental risk factors are used as correction variables and input into the environmental dynamic compliance model to optimize the environmental control command sequence and obtain an updated environmental control command sequence. Based on the updated environmental control instruction sequence and disease risk index, the feeding management plan is dynamically adjusted, and manure scheduling instructions are generated for manure control.

2. The method for green and intelligent poultry farming with dynamic coupling of dual models according to claim 1, characterized in that, Based on environmental data, the system predicts the change curves of environmental parameters in future periods. With the objective of minimizing the deviation of these change curves from a preset healthy environment range, and simultaneously minimizing the weighted sum of energy consumption of the executing equipment, a dynamic environmental compliance model is constructed. The specific content of the generated environmental control instruction sequence includes: Feature extraction was performed on the environmental data to obtain ammonia concentration, temperature, and humidity. Inputting ammonia concentration, temperature, and humidity into a time series prediction model, the model predicts the changes in ammonia concentration, temperature, and humidity over the next 1-4 hours. With the objective function of minimizing the deviation between the change curve and the preset healthy environment range, and minimizing the weighted sum of energy consumption of the executing equipment, an optimization algorithm is used to continuously solve for the optimal switching combination and duration command sequence of the fan, wet curtain and heating equipment in the future finite time domain, so as to obtain the environmental dynamic compliance model.

3. The method for green and intelligent poultry farming with dynamic coupling of dual models according to claim 2, characterized in that, The specific content of quantitative analysis of environmental, audio, and video data to clarify the relationship between environmental data and disease occurrence, and to calculate disease risk indices and environmental risk factors, and construct disease risk prediction models includes: Perform spectral analysis on the sound data to extract the frequency characteristics of abnormal coughing / sneezing sounds in birds; Target detection and tracking were performed on video data to extract behavioral characteristics such as the decline rate of poultry group activity and the clustering index; Frequency features and behavioral features are fused with ammonia concentration, temperature and humidity within a continuous time window to obtain a feature vector set. Based on the feature vector set, the disease risk index is calculated using the gradient boosting decision tree algorithm; Based on the gradient boosting decision tree algorithm, the importance of feature vector groups is scored based on environmental data to obtain environmental risk factors, and a disease risk prediction model is constructed.

4. The method for green and intelligent poultry farming with dynamic coupling of dual models according to claim 3, characterized in that, Based on the gradient boosting decision tree algorithm, the importance of feature vector groups is scored based on environmental data, resulting in the following specific contents of environmental risk factors: Based on the gradient boosting decision tree algorithm, the importance of each feature vector is scored by analyzing the number of times each feature vector in the feature vector group is used to split nodes in each decision tree and the amount of error reduction. The importance scores are sorted in descending order, and the feature vector ranked first is identified as the environmental risk factor.

5. The method for green and intelligent poultry farming with dynamic coupling of dual models according to claim 4, characterized in that, In the objective function, the weights focus on minimizing the deviation between the change curve corresponding to the environmental risk factor and the preset healthy environment range.

6. The method for green and intelligent poultry farming with dynamic coupling of dual models according to claim 3, characterized in that, Based on the updated environmental control instruction sequence and disease risk index, the feeding management plan is dynamically adjusted, and manure and wastewater dispatch instructions are generated for manure and wastewater control. Specific details of this manure and wastewater control include: The feeding and management plan is dynamically adjusted based on the disease risk index. Obtain data on poultry age and feed intake; Based on the updated environmental control command sequence, poultry age and feed intake data, calculate real-time manure production and key component content; Based on the output of manure, the content of key components, the real-time status of each resource utilization unit, and demand order information, manure scheduling instructions are generated to regulate manure and wastewater, with the goal of optimizing system economy and resource utilization efficiency.

7. The method for green and intelligent poultry farming with dynamic coupling of dual models according to claim 6, characterized in that, The specific details of dynamically adjusting the feeding and management plan based on the disease risk index include: When the disease risk index exceeds the first threshold, the proportion of vitamin C added to the feed will be automatically increased. When the disease risk index exceeds the second threshold, a predetermined dose of electrolytes is automatically added to the drinking water; The second threshold is greater than the first threshold.

8. A dual-model dynamically coupled green intelligent poultry farming system, characterized in that, A method for implementing a dual-model dynamically coupled green and intelligent poultry farming method as described in any one of claims 1-7 includes: The data acquisition module is used to acquire environmental data, as well as the sound and video data of poultry; The first model building module is used to predict the change curve of environmental parameters in the future based on environmental data, and to build a dynamic environmental compliance model with the goal of minimizing the deviation of the change curve from the preset healthy environment range and minimizing the weighted sum of energy consumption of the execution equipment, and to generate a sequence of environmental control instructions. The second model building module is used to perform quantitative analysis on environmental data, sound data, and video data, clarify the relationship between environmental data and disease occurrence, calculate the disease risk index and environmental risk factors, and build a disease risk prediction model. The model coupling module is used to input the disease risk index and environmental risk factors as correction variables into the environmental dynamic compliance model to optimize the environmental control command sequence and obtain an updated environmental control command sequence. The dynamic control module is used to dynamically adjust the feeding management plan based on the updated environmental control instruction sequence and disease risk index, and generate manure scheduling instructions for manure control.

9. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor, when calling the computer program in the memory, implements the content of the dual-model dynamic coupling green intelligent poultry farming method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores computer-executable instructions, which, when loaded and executed by a processor, implement the content of a dual-model dynamic coupling green and intelligent poultry farming method as described in any one of claims 1 to 7.

Images