Cultivation monitoring method and system for intelligent agricultural orchard

Abstract

The invention relates to the field of intelligent breeding, in particular to a breeding monitoring method and system for an intelligent agricultural orchard, and the method comprises the steps: obtaining poultry breeding data in an orchard range in real time; judging whether abnormal conditions are met or not according to the poultry breeding data; when the poultry breeding data is not abnormal, acquiring environmental data and behavior data of poultry; judging whether the behavior data meets abnormal behaviors or not according to the environment data; when the behavior data meets the abnormal behavior, marking a target poultry corresponding to the abnormal behavior; quantifying the behavior data according to the judgment result, and speculating the reason of the current abnormal behavior in combination with the quantified behavior data and the environment data; and generating a coping strategy according to the reason of the current abnormal behavior based on the speculation result. And the multi-dimensional data fusion capability is realized, and the adaptability of the system to complex conditions is remarkably improved. Misjudgment possibly caused by a single data source is avoided, and the accuracy of an abnormal behavior analysis result is ensured.

Description

Technical Field

[0001] The present application relates to the field of smart breeding technology, and in particular to a breeding monitoring method and system for a smart agricultural orchard. Background Art

[0002] Smart agricultural orchard breeding monitoring refers to the use of modern information technology and Internet of Things technology to monitor and manage poultry breeding in orchards in real time. This monitoring system can collect data information of poultry and help farmers better understand the status and production performance of breeding animals through data analysis, thereby improving breeding efficiency and output.

[0003] In the existing poultry farming technology, it is usually relied on the collection and analysis of video data or sensor data. Fixed parameter thresholds are set to determine whether the behavior of poultry is abnormal. However, the existing technology often tends to ignore the impact of weather conditions on the behavior of poultry. Specifically, poultry will show different behavior patterns under different weather conditions. For example, in hot weather, poultry may reduce their activity, seek shade, or increase their drinking behavior. In cold weather, they may gather together to maintain their body temperature. These behavioral changes are normal responses of poultry to adapt to the environment. Secondly, there are individual differences between poultry. Some poultry are naturally more active, while others are quieter. If fixed parameters are used to judge the behavior of these poultry, these individual differences may be ignored, leading to misjudgment.

[0004] Therefore, the prior art has defects and needs to be improved. Summary of the invention

[0005] In order to solve one or several problems in the prior art, the main purpose of this application is to provide a breeding monitoring method and system for a smart agricultural orchard.

[0006] In order to achieve the above-mentioned invention object, the present application proposes a breeding monitoring method for a smart agricultural orchard, the method comprising:

[0007] Get real-time data on poultry farming within the orchard;

[0008] Determining whether an abnormal condition is met according to the poultry breeding data;

[0009] When the poultry breeding data is abnormal, the label of the abnormal poultry is obtained and sent to the management end;

[0010] When the poultry breeding data is normal, obtaining environmental data and poultry behavior data;

[0011] Determining whether the behavior data satisfies abnormal behavior according to the environmental data;

[0012] When the behavior data meets the abnormal behavior, marking the target poultry corresponding to the abnormal behavior;

[0013] quantify the behavior data according to the judgment result, and infer the cause of the current abnormal behavior by combining the quantified behavior data and the environmental data;

[0014] Based on the inferred results, a response strategy is generated according to the cause of the current abnormal behavior.

[0015] The present application also provides a breeding monitoring system for a smart agricultural orchard, including:

[0016] The first acquisition module is used to obtain poultry breeding data within the orchard in real time;

[0017] A first judgment module, used to judge whether an abnormal condition is met according to the poultry breeding data;

[0018] A sending module, used for obtaining the label of the abnormal poultry and sending it to the management end when the poultry breeding data is abnormal;

[0019] A second acquisition module is used to acquire environmental data and poultry behavior data when the poultry breeding data is normal;

[0020] A second judgment module is used to judge whether the behavior data meets the abnormal behavior according to the environmental data;

[0021] A marking module, used for marking target poultry corresponding to the abnormal behavior when the behavior data meets the abnormal behavior;

[0022] An inference module, used to quantify the behavior data according to the judgment result, and infer the cause of the current abnormal behavior by combining the quantified behavior data and environmental data;

[0023] The generation module is used to generate a response strategy according to the cause of the current abnormal behavior based on the inferred results.

[0024] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0025] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0026] The breeding monitoring method and system of the smart agricultural orchard of the embodiment of the present application collects the behavioral data and environmental data of poultry in the orchard. This real-time performance ensures that the breeders can obtain accurate information at any time, which helps to quickly discover any potential problems. It ensures that poultry health problems can be discovered at the earliest stage, avoiding delays. Continuous high-frequency data collection improves the accuracy of monitoring and helps to accurately judge the behavior and physiological state of poultry. When the behavior or physiological data of poultry deviates from the normal range, abnormal behavior can be automatically judged and marked. This process combines the poultry's own data and environmental factors to efficiently and accurately identify health or environmental problems. Poultry abnormalities can be detected in time to avoid the spread of problems, such as disease transmission or environmental stress. The subjective judgment errors of breeders are reduced, and data-driven automated judgment is more reliable. Combined with environmental data (such as temperature, humidity, light, etc.), a comprehensive analysis is performed to infer the root cause of abnormal behavior. This multi-dimensional data fusion capability significantly improves the system's adaptability to complex situations. It avoids misjudgments that may be caused by a single data source and ensures the accuracy of abnormal behavior analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a method for monitoring breeding in a smart agricultural orchard according to an embodiment of the present application;

[0028] Figure 2 A schematic diagram of a method for monitoring breeding in a smart agricultural orchard according to an embodiment of the present application;

[0029] Figure 3 This is a schematic structural diagram of a breeding monitoring system for a smart agricultural orchard according to an embodiment of the present application;

[0030] Figure 4 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0031] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0033] Reference Figure 1 In an embodiment of the present application, a method for monitoring breeding in a smart agricultural orchard is provided, the method comprising:

[0034] S1. Obtain poultry breeding data within the orchard in real time;

[0035] S2. judging whether abnormal conditions are met according to the poultry breeding data;

[0036] S3. When the poultry breeding data is abnormal, obtain the label of the abnormal poultry and send it to the management end;

[0037] S4. When the poultry breeding data is normal, obtaining environmental data and poultry behavior data;

[0038] S5. judging whether the behavior data satisfies abnormal behavior according to the environment data;

[0039] S6. When the behavior data meets the abnormal behavior requirement, mark the target poultry corresponding to the abnormal behavior;

[0040] S7. quantify the behavior data according to the judgment result, and infer the cause of the current abnormal behavior by combining the quantified behavior data and the environmental data;

[0041] S8. Based on the inferred results, generate a response strategy according to the cause of the current abnormal behavior.

[0042] As described in the above steps S1-S4, sensors can be set on each poultry to collect poultry behavior and environmental data in real time in conjunction with surveillance cameras, Internet of Things devices, etc. These data may include the activity level, position, number, weight change, health status (such as body temperature, respiratory rate, etc.) and physiological performance of poultry. The ability to obtain the latest data at any time ensures the ability to respond in a timely manner. Through real-time collection, the behavior of poultry can be monitored more accurately to avoid misjudgments caused by delays. For example, when poultry in an orchard suddenly stops or reduces their activity, the system will receive this data change in real time and trigger further judgment and analysis. Based on the acquired poultry farming data, the system sets certain "normal" behavior ranges, such as normal activity level, weight fluctuations, food and water intake, etc. If these behaviors or physiological indicators deviate from the set standard values, the system will be judged as "abnormal conditions". It is possible to detect problems and alarm as soon as possible when poultry behavior changes, such as finding that poultry may be sick, injured or stressed. Detecting abnormal conditions in advance helps to avoid the spread of diseases in poultry groups. For example, when the body temperature of poultry suddenly rises, or the activity level decreases sharply, the system will trigger an abnormal condition judgment, indicating that there may be health problems or environmental stress. When there are no abnormalities in the poultry farming data, the system continues to collect environmental data (such as temperature and humidity, light intensity, air quality, etc.) and poultry behavior data (such as activity frequency, group interaction, etc.). The goal of this stage is to conduct continuous monitoring to ensure that the poultry is in the best environment. Even if there are no abnormalities in the poultry data, the system still maintains monitoring of the environment and behavior to capture potential problems at any time. Continuous monitoring helps the system accumulate more behavioral data, so that it can better learn the normal behavior patterns of poultry and improve the accuracy of judgment. Even if the activity level of poultry is within the normal range, the system will still monitor changes in environmental conditions, such as sudden temperature increases or changes in light, which may indirectly affect poultry behavior.

[0043] As described in the above steps S5-S8, the environmental data is combined to determine whether the behavior of poultry is normal. Environmental factors (such as temperature, humidity, etc.) have a great influence on the behavior of poultry. In some cases, the behavioral changes of poultry are not caused by disease or stress, but by changes in the environment. For example, in hot weather, the activity of poultry may naturally decrease, and the system needs to consider environmental factors to reasonably explain the behavior of poultry. By considering environmental factors, misjudgments caused by environmental changes are avoided. For example, in hot weather, poultry naturally reduce their activity, and this behavior should be considered normal, not abnormal. Provide more accurate behavioral analysis for farmers, reducing unnecessary intervention and alarms. In extreme climates (such as high temperatures in summer), poultry may show less activity. By analyzing environmental data, the system can infer that this behavior is a natural adaptation caused by excessive temperature, rather than a health problem. When the behavioral data of poultry meets the abnormal behavior criteria after environmental data analysis, the system will classify these behaviors as "abnormal" and mark the relevant poultry individuals. This step can help farmers quickly identify poultry with problems and conduct further inspections or interventions. The ability to accurately identify specific poultry exhibiting abnormal behavior avoids large-scale, unnecessary interventions. By marking abnormal poultry, the system can provide more personalized management measures, which can help with precise treatment or isolation. For example, when a poultry exhibits obvious inactive behavior and its body temperature is too high, the system will mark the poultry to remind the breeder to check or isolate it. After marking the abnormal poultry, the system will quantify the behavioral data and convert the poultry's behavior into measurable values ​​for more accurate analysis. At the same time, the system will combine environmental data to infer the cause of the abnormal behavior. This stage of analysis combines multidimensional data to help reveal the specific causes of abnormal poultry behavior. By combining quantification and multidimensional data, the system can more accurately determine the root cause of abnormal behavior, such as whether it is caused by environmental changes, disease or other factors. Provide a scientific basis for breeders to ensure that response measures can be adjusted to the actual cause rather than blindly intervene. When poultry exhibit abnormal behavior with decreased activity, the system not only quantifies the degree of reduced activity, but also conducts a comprehensive analysis based on factors such as ambient temperature, humidity, and air quality. It may infer that the abnormal behavior is a stress response caused by sudden temperature changes. Based on the inference of the cause of abnormal poultry behavior, the system automatically generates corresponding response strategies. For example, if the abnormal behavior is caused by excessive temperature, the system may recommend lowering the temperature, increasing ventilation, or providing cooling facilities. If it is caused by disease or other health problems, it may be recommended to isolate sick birds or seek veterinary intervention. The system can generate the most suitable solution based on the specific cause of the abnormality, reducing resource waste and management costs. It can automatically generate response measures without human intervention to improve breeding efficiency.If the system infers that the abnormal behavior of poultry is due to the leakage of harmful gases in the environment (such as high ammonia concentration), the system may automatically adjust the ventilation system or remind farmers to check and deal with the gas leak.

[0044] As mentioned above, behavioral data and environmental data of poultry in the orchard are collected. This real-time nature ensures that farmers can obtain accurate information at any time, which helps to quickly identify any potential problems. It ensures that poultry health problems can be discovered at the earliest stage and avoid delays. Continuous high-frequency data collection improves the accuracy of monitoring and helps to accurately judge the behavior and physiological status of poultry. When the behavior or physiological data of poultry deviates from the normal range, abnormal behavior can be automatically judged and marked. This process combines the poultry's own data and environmental factors to efficiently and accurately identify health or environmental problems. Poultry abnormalities can be detected in time to avoid the spread of problems, such as disease transmission or environmental stress. It reduces the subjective judgment errors of farmers, and data-driven automated judgment is more reliable. Combined with environmental data (such as temperature, humidity, light, etc.) for comprehensive analysis, the root cause of abnormal behavior can be inferred. This multi-dimensional data fusion capability significantly improves the system's adaptability to complex situations. It avoids misjudgments that may be caused by a single data source and ensures the accuracy of abnormal behavior analysis results. For example, natural behavior changes caused by environmental changes are no longer misjudged as health problems. Through comprehensive analysis, the system can self-learn, improve the accuracy of abnormal behavior recognition, and gradually optimize the monitoring model. After confirming the cause of the abnormal behavior, the system can automatically generate targeted response strategies.

[0045] Reference Figure 2 In one embodiment, judging whether the behavior data satisfies abnormal behavior based on the environment data includes:

[0046] S41, acquiring the environment data and behavior data, and performing time stamp synchronization processing on the environment data and behavior data;

[0047] S42, based on the processing result, classifying the behavior data, wherein the behavior classification includes activity behavior, interactive behavior and eating behavior;

[0048] S43, constructing a behavior analysis model, inputting the synchronously processed environmental data, behavior data and behavior classification into the behavior analysis model, analyzing the behavior coefficient of the behavior data by combining the behavior classification and environmental data through the behavior analysis model, and outputting the analysis result;

[0049] S44, when the behavior coefficient is within a preset coefficient range, it is determined that the behavior coefficient does not meet the abnormal behavior requirement;

[0050] S45. When the behavior coefficient is not within a preset coefficient range, it is determined that the behavior coefficient satisfies abnormal behavior.

[0051] As described in the above steps, the collection of environmental data and behavioral data is usually completed through different sensors. Environmental data includes temperature and humidity, gas concentration (such as ammonia), light intensity, etc., while behavioral data includes poultry activity status, eating conditions, interactive behavior, etc. Since the collection time of different data sources may be different, it is necessary to align these data through timestamp synchronization processing. This means that the environmental data and behavioral data at each moment need to be accurately matched to ensure that the relationship between poultry behavior and environmental changes is judged at the same time. Assuming that the activity of poultry decreases at a certain moment, only by synchronizing the environmental data at that moment (such as temperature, humidity, gas concentration, etc.) can it be accurately judged whether the reduction in poultry activity is caused by environmental discomfort or other factors (such as disease, hunger, etc.). Ensure that environmental changes and behavioral performance can correspond accurately to avoid misleading caused by time differences between data. Make anomaly detection based on environmental and behavioral data more reasonable and avoid the inability to identify abnormal behavior due to time mismatch. The purpose of behavior classification is to better understand and analyze the daily activities of poultry. By classifying different types of poultry behavior, the normal and abnormal patterns of these behaviors can be analyzed separately, thereby improving the accuracy of anomaly detection. Behavior classification is usually done through machine learning models or rule-based systems. Refers to the behaviors of poultry related to physical activities, such as walking, jumping, and foraging. Refers to the interactions between poultry, such as collisions, fighting, and group interactions when foraging. Refers to the food intake behavior of poultry, including the frequency of eating, the duration of eating, etc. For example, in a group of poultry, most of the poultry suddenly stop eating but still maintain a high level of activity. This may be a behavioral change caused by environmental factors (such as high temperature). Through classification processing, it is possible to distinguish between "abnormal eating behavior" and "normal activity behavior". The behavior of poultry is refined into multiple types, making the analysis of each behavior more specific and accurate. Through classification, different abnormal judgment criteria can be set for different types of behavior to improve the accuracy of abnormality detection. The core of the behavior analysis model is to use machine learning algorithms or statistical models to calculate a "behavior coefficient" by taking the synchronized environmental data, behavior data, and behavior classification as input. This coefficient reflects whether the behavior of poultry conforms to the expected pattern in a specific environment. For example, when the temperature is too high, poultry may show abnormal behaviors such as reduced activity or eating. Through the behavior analysis model, the "abnormality" of this behavior can be quantified and a behavior coefficient can be generated. If the temperature rises at a certain moment, and the activity and food intake of poultry do not change significantly, the behavior analysis model will generate a behavior coefficient that deviates from normal expectations, indicating that the behavior of the poultry does not match the environmental conditions at this time. It can comprehensively consider the factors of the two dimensions of environment and behavior to avoid misjudgment caused by a single dimension. Through the behavior coefficient, the model can quantify the "abnormality" of behavior and provide a basis for subsequent decision-making.The behavior coefficient is considered "normal" within a certain range. When the coefficient falls within the preset range, it means that the match between the behavior of the poultry and the environment is in line with expectations and no abnormal behavior occurs. The preset coefficient range is set through historical data and experience, and is usually obtained based on a large amount of environmental and behavioral data analysis under normal conditions. Assume that under a specific temperature condition, the activity behavior of poultry usually fluctuates within a certain range. Based on a large amount of historical data, a "normal" behavior coefficient range can be set. If the current behavior coefficient is within this range, the behavior of the poultry is considered normal. By setting the expected coefficient range, it is effective to avoid misjudging normal behavior as abnormal behavior. Ensure that the system only alerts for abnormal behavior that exceeds the normal range to avoid frequent and ineffective interference. When the behavior coefficient exceeds the normal preset range, the system will automatically judge it as abnormal behavior. In this case, the system believes that the behavior of the poultry may be affected by environmental changes, disease or other factors, and therefore requires further analysis or intervention. When the ambient temperature is too high, poultry usually show reduced activity and reduced feeding. If poultry remains highly active and eats a lot in high temperatures, this may be due to abnormal behavior caused by disease or other abnormal factors. If the behavior coefficient calculated by the behavior analysis model exceeds the normal range, it will be judged as abnormal by the system. By judging whether the behavior coefficient exceeds the normal range, an alarm can be issued at the early stage of the problem to help farmers take timely intervention measures. Ensure that all possible abnormal behaviors are detected to reduce losses caused by abnormal behaviors that are not discovered in time.

[0052] In one embodiment, after the step of determining whether the behavior coefficient satisfies the abnormal behavior, the method further includes verifying the credibility of the abnormal behavior. The method includes:

[0053] Obtain historical behavior data of poultry;

[0054] Performing a behavior habit analysis on the historical behavior data according to the timestamp, and determining the habit characteristics of the target poultry according to the analysis results;

[0055] Compare the current behavior data and habit features in the same period, and calculate the similarity between the current behavior data and habit features through distance measurement;

[0056] Based on the calculation result, if the similarity is less than a preset similarity threshold, it is determined that the behavior coefficient satisfies the abnormal behavior as a credible result.

[0057] As mentioned above, historical behavior data refers to the behavior pattern data of poultry within a certain time range. This data is usually obtained through long-term monitoring and covers the behavior of poultry under various environmental conditions. By collecting historical behavior data of poultry, a reference benchmark can be provided for abnormal judgment of current behavior. This is a very critical step, because without historical data as a comparison, it is difficult to evaluate the rationality of the abnormal current behavior. Suppose that in a farm, the activity of a poultry has been basically stable in the past month, but recently it has suddenly shown extremely low activity. Historical behavior data can help the system determine whether this change is a normal periodic change of poultry or caused by abnormal factors (such as disease or environmental changes). Through historical behavior data, context can be provided for anomaly detection to avoid misjudgment of occasional events. By comparing historical data, the error caused by data isolation can be reduced and the accuracy of current behavior analysis can be improved. Timestamps are an important means to ensure data synchronization. Arranging historical behavior data in chronological order ensures that the periodicity and regularity of poultry behavior can be captured during analysis. Behavioral habit analysis is to identify the regular behavior patterns of poultry in different time periods through methods such as statistical analysis, machine learning or rule analysis. For example, a poultry may be active for a long time every morning, but prefer to rest or eat in the afternoon. Through this analysis, the system can summarize the habit characteristics of poultry (such as peak activity period, frequency of eating, etc.). By analyzing historical data, the system found that a poultry usually has strong activity behavior in the early morning hours and is in a resting state during the noon hours. If the poultry suddenly shows abnormally high activity during the noon hours, this may be a noteworthy anomaly. Habit analysis can accurately identify the common behavioral characteristics of individual poultry. Habit characteristics are not static. As the environment or seasons change, the behavior of poultry will also change. Behavioral habit analysis can help the system dynamically adapt to such changes. The current behavioral data is compared with the habit characteristics to determine whether the behavior of the poultry in the same time period is consistent with its habits. If the current behavioral data does not match the habit characteristics, it may mean that an abnormality has occurred. For example, poultry suddenly increases its activity during its usual rest time, which may be caused by the external environment, health problems or other factors. Suppose poultry usually rests between 8 and 10 p.m. every night, but is unusually active that night, causing activity data for that time period to be significantly higher than normal. By comparing current data with its habitual features, the system can determine the abnormality of this behavior. Comparing current data with habitual features can help the system more clearly determine whether the abnormal behavior is a special case or an emergency for poultry. It can provide a more detailed analysis of abnormal behavior and avoid false alarms for abnormal but harmless behavior. The similarity between current behavior data and historical habitual features is calculated through "distance metrics", including Euclidean distance, cosine similarity, Manhattan distance, etc.This step is to determine whether the current behavior is consistent with the historical behavior of the poultry by quantifying the difference between the current behavior and the habit characteristics. If the similarity between the current behavior and the habit characteristics is low, it can be considered that the behavior may be abnormal, and the abnormal behavior previously judged is credible. If poultry usually has more activities during a certain period of the day, then based on the habit characteristics, the system should expect the amount of activity during this period to be within a certain range. If the similarity between the current behavior data and the habit characteristics is low, it means that the current behavior pattern deviates from the normal range and may represent an abnormality. By calculating the similarity, the difference between the current behavior data and the habit characteristics can be quantified, and a clear basis for abnormal judgment can be given. Avoid judging the behavior abnormality based on a single behavior data. Adding similarity measurement helps reduce false alarms caused by accidental factors. Setting a similarity threshold is to distinguish between normal fluctuations and true abnormalities. If the calculated similarity is less than the set threshold, the system believes that the difference between the current behavior and the historical habit characteristics is too large, and thus determines it as abnormal behavior. The setting of the threshold is usually based on statistical analysis and experience of historical data. A threshold that is too low may lead to excessive alarms, and a threshold that is too high may lead to missed alarms. Assume that historical data shows that the range of activity of poultry at noon is usually within 10%. If the activity changes by more than 30% on a certain day and the result of similarity calculation is lower than the set threshold, the system will identify this as an abnormal behavior. By setting the similarity threshold, the system can more accurately determine whether there is a real abnormal behavior and reduce false alarms caused by non-abnormal reasons such as environmental changes. By adjusting the similarity threshold, the sensitivity of the system can be adjusted according to actual needs to adapt to different breeding environments and management needs. Through similarity calculation, the system finds that the activity of a certain poultry is low and the credibility of this behavior is lower than the set threshold. The inspection results show that the poultry has reduced its activity due to health problems, so this abnormal judgment is credible. Through multi-angle and multi-dimensional data verification, it is possible to more accurately evaluate whether a certain abnormal behavior is credible and avoid false alarms. Through comprehensive analysis of the environment and individual behavior, the system can flexibly respond to different environmental changes and individual differences of poultry.

[0058] In another embodiment, suppose we observe that a certain poultry has low activity at a certain point in time. According to previous monitoring records, the behavior habits of this poultry are relatively quiet, usually less active at night and early morning, and moderately active during the day. In this case, the similarity between the current behavior data and the historical behavior data is very high, indicating that the poultry has no significant behavioral deviation. In other words, the low activity of the poultry during this period is part of its normal behavior pattern. Through long-term monitoring, it is found that the activity pattern of this poultry shows regularity, with less activity at night and early morning, and occasional activity during the day. During the same period of the observation period, the activity of the poultry is low, and there are no other unusual behavioral characteristics (such as rapid breathing, abnormal posture, etc.). Through the similarity calculation of the behavior data, the current behavior is very close to the historical behavior pattern of the poultry, so it does not meet the standard of the "abnormal behavior" pattern. According to the similarity analysis of the behavior, the current behavior is highly consistent with the historical behavior of the poultry, and does not meet the standard of abnormal behavior. Therefore, although the system is initially identified as "abnormally active" or "abnormally inactive", after similarity verification, it can be confirmed that this behavior does not represent an abnormality and should be judged as an unreliable result without further processing.

[0059] In one embodiment, the method of quantifying the behavior data based on the judgment result, combining the quantified behavior data with the environmental data, and inferring the cause of the current abnormal behavior includes:

[0060] Obtaining a behavior classification of the behavior data, and when the behavior is classified as an activity behavior, extracting an activity feature of the activity behavior;

[0061] According to the activity characteristics, the moving distance and moving speed of the target poultry within the preset time are analyzed, and the activity intensity of the target poultry is determined according to the moving distance and moving speed; the activity time and rest time of the target poultry within the preset time are analyzed, and the activity ratio of the activity time to the rest time is calculated;

[0062] Based on the analysis results, the quantified behavioral characteristics are obtained;

[0063] Extracting environmental characteristics of the environmental data, wherein the environmental characteristics include climate characteristics, noise characteristics and site characteristics;

[0064] The quantified behavior characteristics and environmental characteristics are input into a preset inference model, and the inference model is used to analyze and output the reasons why the environmental characteristics affect the behavior characteristics.

[0065] As mentioned above, behavior classification is based on the recording of poultry behavior by sensors or monitoring systems, and all observed behaviors are classified into two categories: "active behavior" and "resting behavior". Active behavior may include walking, foraging, jumping, etc., while resting behavior is usually characterized by being stationary or sleeping. Once a behavior is identified as active behavior, the system will further analyze the characteristics of the active behavior, including the poultry's movement method, speed, direction, etc. Assuming that the system detects that a poultry is walking quickly and for a long time, this behavior will be classified as "active behavior". If the poultry shows a faster pace and a longer travel distance in this behavior, this will affect the subsequent activity intensity assessment. The effect of classification is to enable the system to clearly distinguish different types of behavior, so that subsequent analysis can be more accurate. For example, identifying the activity status of poultry helps to determine whether there is behavioral abnormality caused by changes in the external environment (such as high temperature, the appearance of threats, etc.). Refers to the total distance moved by poultry within a predetermined time. This is an important indicator for evaluating the range of poultry activities. Refers to the movement rate of poultry per unit time when active. A faster speed usually means that the poultry is more active. It is a quantitative representation of poultry activity, which is derived from the combined movement distance and speed. Activity intensity reflects the activity level of poultry. If the activity intensity is low, it may mean that the poultry is in a resting state. Otherwise, it may be overactive, which may indicate interference from some health or environmental factors. For example, if the poultry is slow and moves a short distance in a certain period of time, it may mean that it is in a static state or restricted (such as narrow space, physical discomfort, etc.). On the contrary, if the speed is fast and the movement distance is long, it may mean that the poultry is overexcited, which may be caused by environmental stress (such as high temperature, noise). Through activity feature analysis, the activity intensity of poultry can be accurately assessed, and whether there is an abnormally active or inactive trend in the data can be found. This is crucial to identifying behavioral abnormalities caused by environmental factors or health problems. The ratio of active time to rest time is the ratio of the time that poultry is active to the time that it is resting in a period of time. Under normal circumstances, poultry will have a certain activity and rest cycle. A high or low proportion of activity time may be an abnormal manifestation. A high activity time ratio may indicate that the poultry is disturbed, showing anxiety or overactivity, while a low activity time ratio may indicate that the poultry is in a sick state or lacks sufficient space and resources. If the poultry's activity time ratio is high in the morning, but suddenly drops during the day, and the rest time ratio increases significantly, this may mean that the poultry feels uncomfortable or stressed in the daytime environment. The effect of ratio analysis is that it can effectively reveal the physiological and psychological state of poultry. If there is an abnormal change in the activity-to-rest ratio, the system can better analyze whether further investigation of health or environmental issues is needed. Changes in climate have a direct impact on poultry activity, including factors such as temperature, humidity, and wind speed.For example, high temperatures may cause poultry to become less active, while low temperatures may increase poultry activity to find food or keep warm. Changes in noise in the environment can also affect poultry behavior. Excessive noise may cause poultry to respond to stress, leading to abnormal behavior. It refers to the size of the poultry activity space, the degree of perfection of the facilities, etc. Narrow space or an unsuitable site environment will restrict the normal behavior of poultry. If the temperature rises suddenly, the activity intensity of poultry may decrease. At this time, the monitoring system can correlate and analyze the climate data with the poultry activity data to infer whether the climate factors have caused the reduction in poultry activity. In another case, excessive noise in the environment (such as nearby machinery working or the calls of other animals) may cause poultry to exhibit anxious behavior, such as excessive walking or jumping. The effect of environmental characteristics is that they can help us understand the external driving factors of poultry behavior. By combining environmental data with behavioral data, the system can more accurately infer the environmental causes of abnormal behavior. For example, if poultry suddenly becomes inactive when the temperature rises, the system can infer that the abnormal behavior is caused by climate factors, rather than health problems of the poultry itself. The quantified behavioral characteristics and environmental characteristics are input into the inference model. The model analyzes the impact of environmental changes on behavior based on historical data and known causal relationships, and outputs the possible causes of abnormal behavior. Inference models are usually based on machine learning algorithms, which can infer the driving factors of current behavioral changes based on a large amount of historical behavioral and environmental data. For example, the inference model can analyze the correlation between the current climate (such as rising temperatures and increased humidity) and poultry activity data, and infer whether the decrease or increase in activity is caused by climate change, thereby providing managers with reasonable intervention suggestions. The effect of the inference model is to provide a more scientific explanation for abnormal behavior and guide subsequent treatment measures. Through model analysis, the system can not only identify abnormal behavior, but also explain the potential causes behind this abnormality (such as environmental pressure, health problems, etc.).

[0066] In one embodiment, the method further comprises: quantifying the behavior data according to the judgment result, combining the quantified behavior data with the environmental data, and inferring the cause of the current abnormal behavior.

[0067] Obtaining a behavior classification of the behavior data, and when the behavior is classified as an interactive behavior, extracting an interactive feature of the interactive behavior;

[0068] Based on the interaction characteristics, the spatial density of the interactive behaviors of poultry within a preset time is analyzed, and the concentration of the interactions of poultry in the group is analyzed; the number of times poultry interact with other poultry within a preset time and the duration of each interaction are analyzed;

[0069] Based on the analysis results, the quantified behavioral characteristics are obtained;

[0070] Extracting environmental characteristics of the environmental data, wherein the environmental characteristics include climate characteristics, noise characteristics and site characteristics;

[0071] The quantified behavior characteristics and environmental characteristics are input into a preset inference model, and the inference model is used to analyze and output the reasons why the environmental characteristics affect the behavior characteristics.

[0072] As mentioned above, the classification of behavioral data may include classification by behavior type, action frequency, etc. After the behavior is classified into different categories, the motivation behind each type of behavior can be analyzed more accurately. In this model, interactive behavior refers to direct communication or interaction between poultry, such as foraging, group gathering, etc. The purpose of extracting the characteristics of interactive behavior is to understand the dynamics within the group, including the frequency and intensity of interaction. Characteristics include: the number of interactions, duration and spatial distribution. By analyzing the interactive behavior between poultry, it can help to discover potential anomalies (such as disease transmission or resource shortage). By analyzing the characteristics of interactive behavior, the social structure, group dynamics and possible abnormal behaviors of poultry groups can be quantified. Spatial density analysis refers to the distribution of poultry in a certain area at a specific time. It can help analyze the degree of spatial aggregation of groups, which may indicate whether regional resources are sufficient or the environment is suitable. Concentration analysis involves quantifying the geographical distribution of group interactions to understand the concentration of poultry activities in a region. For example, excessive concentration may lead to behavioral anomalies such as competition and excessive stress. In a closed environment, if a poultry group spends most of its time in a certain area, it may indicate that there is a certain resource (such as water, food or habitat) in the area, but excessive concentration may lead to excessive resource consumption, conflict or stress. This analysis can reveal whether the group is facing spatial pressure or whether there are factors in the environment that can trigger abnormal behavior of poultry, such as overcrowding of the group or inappropriate habitat. Analyze the frequency of interaction between poultry in a specific time period. Frequent interactions may indicate that the poultry is responding to external stimuli or that there is a certain social behavior in the group (such as finding food, socializing, etc.). The duration of each interaction can reveal the closeness of the interaction between poultry. If the interaction time is too long, it may be due to competition for resources or affected by certain external factors (such as disease transmission). Climate characteristics include temperature, humidity, air pressure, etc. Climate factors have a direct impact on the behavior of poultry. For example, too high or too low temperature may lead to reduced activity or abnormal behavior of poultry. In noise characteristics, changes in noise may cause changes in the alertness and reaction behavior of poultry. For example, sudden noise (such as machine operation sound, external animal sound, etc.) may cause poultry to escape. The layout of the site, the size of the habitat, the distribution of food and water sources, etc. directly affect the behavior of poultry. For example, a space that is too small may cause increased stress among poultry, affecting their interactive behavior and health. If the temperature rises suddenly, poultry may gather in the shade or reduce their activities. Too high or too low temperatures may cause poultry to have a stress response and increase tension within the group. If there is sudden noise in the environment (such as construction near the farm), it may cause the poultry group to show restless behavior, frequent movement or gathering. If the site is too crowded, fierce competition may occur between poultry, affecting the health and behavior patterns of the group. Through the analysis of environmental data, it is possible to determine the impact of environmental changes on poultry behavior.For example, high temperatures may cause poultry to reduce activity, frequent noise may cause anxious behavior in the group, and unsuitable sites may cause tension or abnormal behavior among poultry. The purpose of the inference model is to combine quantified behavioral characteristics with environmental characteristics to infer their specific impact on changes in poultry behavior. This inference is usually done through machine learning or statistical models, which train the model based on historical data and infer the cause of abnormal behavior based on current data.

[0073] In one embodiment, the method further comprises:

[0074] Obtain historical behavioral data and historical environmental data of poultry;

[0075] Based on the historical behavior data and the historical environmental data, identifying the change patterns of the behavior data of poultry under different time periods and different environmental data conditions;

[0076] Based on the change pattern of historical behavior data, determine the frequency of obtaining behavior data of poultry under current environmental data and time period.

[0077] As mentioned above, historical behavior data refers to the behavior records of poultry over a period of time in the past. These records usually include the activity status of poultry (such as foraging, resting, socializing, etc.), interaction status, spatial distribution, etc. Historical environmental data can help analyze the relationship between poultry behavior and environment. If the records show that poultry has been foraging in a specific area most of the time every day in the past week, it can be inferred that the area is rich in resources during this period. If the historical data shows that the temperature fluctuated greatly in the past two weeks, it may affect the behavior patterns of poultry, such as reducing activity when the temperature is high. By analyzing historical behavior data and environmental data, the changing patterns of poultry behavior in different time periods and different environmental conditions can be identified. Time period analysis refers to the division of time into different time periods (such as daytime, nighttime or seasonal changes), and the behavior of poultry may be different in each time period. Different environmental conditions (such as temperature and humidity changes) may have different effects on poultry behavior. By identifying these changing patterns, it is possible to infer the behavioral changes of poultry when facing specific environmental conditions. Poultry are active during the day and rest or enter a more static state at night. At this time, the difference in behavior patterns during the day and at night can be identified by analyzing the behavior data. If the temperature is too high (e.g., over 35°C), the activity frequency of poultry may decrease, and they may gather more in the shade. This behavior pattern may show regularity under temperature changes. By identifying the change patterns in historical behavior data, combined with the current environmental data and time period, the behavior patterns of poultry can be inferred and the frequency of data collection can be determined. By analyzing historical behavior and environmental data, the behavior change patterns of poultry in specific environmental changes or time periods can be determined, and these patterns can be used to infer the behavior patterns at the current moment. Based on these patterns, when there are significant environmental changes, the frequency of data collection needs to be increased to ensure that subtle changes in behavior can be captured; when the behavior changes are small, the collection frequency can be reduced to improve efficiency and save storage. If it is found in past data that when the temperature is 40°C, the poultry group will produce a large range of activity changes, and may show escape behavior or aggregation behavior, then when the temperature is close to this value, the frequency of behavior data collection can be increased to monitor subtle changes in group behavior. The behavior data of poultry has different patterns of change during the day and night, so the collection frequency in these time periods can also be different. During the day, poultry is more active, so the frequency of data collection can be reduced; at night, when poultry is stationary, a lower frequency of data collection may be required. By dynamically adjusting the frequency of data collection according to environmental conditions and time periods, data collection efficiency can be improved while ensuring data quality and avoiding invalid data redundancy. It can capture subtle behavioral fluctuations of poultry under environmental changes in a timely manner and avoid missing important behavioral change nodes. For example, if poultry shows drastic behavioral changes under certain environmental conditions (such as reduced activity under high temperatures), the frequency of data collection under these conditions should be increased.By adjusting the frequency, you can increase collection at critical moments to ensure accurate capture of changes in poultry behavior.

[0078] In one embodiment, the method for determining whether an abnormal condition is met according to the poultry breeding data includes:

[0079] Obtaining quantity parameters of the poultry breeding data, and verifying whether the quantity parameters are consistent with a preset quantity;

[0080] When the number of the poultry is consistent with the preset number, obtaining the physical sign parameters of the poultry breeding data, and judging whether abnormal parameters appear according to the physical sign parameters;

[0081] When the physical sign parameters do not show abnormal parameters, it is determined that the poultry breeding data does not show abnormalities.

[0082] As mentioned above, quantity parameters refer to quantity data in poultry farming, such as the total number of poultry, the number of groups, or the number of poultry activities in each time period. The accuracy of the actual data is verified by comparing it with the preset quantity. If the number of poultry is inconsistent with the preset number, it may indicate a data entry error, an abnormal change in the number of poultry, or a change in the number caused by other potential problems (such as escape, death, or disease spread). Suppose there should be 100 poultry in a specific area, but the actual record shows that there are only 95 poultry in the area. By comparing with the preset number, this inconsistency can be immediately discovered, and the subsequent abnormality inspection procedure can be triggered. Vital sign parameters can detect indicators of poultry status, such as weight, body temperature, respiratory rate, heart rate, food intake, etc., which can be obtained through sensors. These parameters can reflect the condition of poultry. If the physical sign parameters are beyond the normal range (for example, abnormal poultry body temperature, loss of appetite, etc.). If the poultry's body temperature rises abnormally (for example, more than 42°C), it may indicate that the poultry is abnormal. At this time, by obtaining and analyzing these physical sign data, the system can determine whether there is a problem. If the weight of poultry drops significantly in a short period of time, it may indicate malnutrition or disease, and abnormal changes in weight loss will trigger the system to automatically alarm. By monitoring vital sign parameters, the health status of poultry can be evaluated in real time and potential health problems can be discovered in time. When there are no abnormalities in the vital sign parameters, it means that the condition of the poultry is fine, and the overall breeding data can be considered to be within the normal range. If the vital sign parameters are within the acceptable range and there are no significant abnormal changes, the system will consider the behavior and condition of the poultry to be normal, and then judge that there are no abnormalities in the breeding data. Assuming that the weight, body temperature and respiratory rate of the poultry are all within the normal range and there are no fluctuations, the system will conclude that no abnormalities have been found.

[0083] In one embodiment, poultry raised in an orchard sometimes need to move in a specific area to prevent them from damaging fruit trees or affecting crop growth. Through the behavior monitoring of poultry, it can be determined whether they have excessive activity (such as running around, destroying fruit trees, improper foraging, etc.), and regional adjustments or optimization of feeding management can be made based on these data. Environmental factors such as climate and humidity in the orchard will also directly affect the behavior of poultry. For example, excessive temperature or humidity may cause poultry to be unwilling to move, or collective behavior abnormalities. The smart agricultural system can detect these environmental data and combine them with the behavior data of poultry to identify potential problems in advance. Assume that the system monitors that the group behavior of poultry in the orchard shows a highly concentrated pattern during a certain period of time. It may be that there are pests or pests in certain fruit tree areas, and poultry activities around this area have increased. At this time, the system can infer and warn, and take corresponding agricultural measures in time, such as using organic or low-toxic pest control methods to reduce the contact between poultry and these areas, so as to achieve sustainable health of the environment. Poultry is a natural pest controller in ecological agriculture, but if they are over-aggregated in certain areas or over-forage, it will affect the healthy growth of fruit trees. The system can analyze the behavior of poultry in the orchard to determine whether it affects the growth of fruit trees, and adjust the poultry activity area when necessary to ensure the coordinated development of orchards and poultry farming.

[0084] Reference Figure 3 In an embodiment of the present application, a breeding monitoring system for a smart agricultural orchard is also provided, including:

[0085] The first acquisition module 1 is used to obtain poultry breeding data within the orchard in real time;

[0086] A first judgment module 2, used to judge whether an abnormal condition is met according to the poultry breeding data;

[0087] The sending module 3 is used to obtain the label of the abnormal poultry and send it to the management end when the poultry breeding data is abnormal;

[0088] A second acquisition module 4 is used to acquire environmental data and poultry behavior data when the poultry breeding data is normal;

[0089] A second judgment module 5 is used to judge whether the behavior data meets the abnormal behavior according to the environmental data;

[0090] A marking module 6, used for marking the target poultry corresponding to the abnormal behavior when the behavior data meets the abnormal behavior;

[0091] Inference module 7, used to quantify the behavior data according to the judgment result, and infer the cause of the current abnormal behavior by combining the quantified behavior data and environmental data;

[0092] The generation module 8 is used to generate a response strategy according to the cause of the current abnormal behavior based on the inference result.

[0093] As described above, it can be understood that the various components of the breeding monitoring system of the smart agricultural orchard proposed in this application can realize the functions of any one of the breeding monitoring methods of the smart agricultural orchard described above, and the specific structure will not be repeated.

[0094] Reference Figure 4 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a breeding monitoring method for a smart agricultural orchard is implemented.

[0095] The above-mentioned processor executes the above-mentioned breeding monitoring method for the smart agricultural orchard, including: acquiring poultry breeding data within the orchard in real time; judging whether abnormal conditions are met based on the poultry breeding data; when the poultry breeding data does not show abnormalities, acquiring environmental data and poultry behavior data; judging whether the behavior data meets abnormal behavior based on the environmental data; when the behavior data meets abnormal behavior, marking the target poultry corresponding to the abnormal behavior; based on the judgment result, quantifying the behavior data, combining the quantified behavior data and environmental data, and inferring the cause of the current abnormal behavior; based on the inferred result, generating a response strategy according to the cause of the current abnormal behavior.

[0096] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a breeding monitoring method for a smart agricultural orchard is implemented, including the following steps: acquiring poultry breeding data within the orchard in real time; judging whether abnormal conditions are met based on the poultry breeding data; when the poultry breeding data does not show abnormalities, acquiring environmental data and poultry behavior data; judging whether the behavior data meets abnormal behavior requirements based on the environmental data; when the behavior data meets abnormal behavior requirements, marking target poultry corresponding to the abnormal behavior; quantifying the behavior data based on the judgment result, and inferring the cause of the current abnormal behavior by combining the quantified behavior data and the environmental data; and generating a response strategy based on the cause of the current abnormal behavior based on the inferred result.

[0097] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0098] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0099] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for monitoring breeding in a smart agricultural orchard, characterized in that: The method comprises: Get real-time data on poultry farming within the orchard; Determining whether an abnormal condition is met according to the poultry breeding data; When the poultry breeding data is abnormal, the label of the abnormal poultry is obtained and sent to the management end; When the poultry breeding data is normal, obtaining environmental data and poultry behavior data; Determining whether the behavior data satisfies abnormal behavior according to the environmental data; When the behavior data meets the abnormal behavior, marking the target poultry corresponding to the abnormal behavior; quantify the behavior data according to the judgment result, and infer the cause of the current abnormal behavior by combining the quantified behavior data and the environmental data; Based on the inferred results, a response strategy is generated according to the cause of the current abnormal behavior.

2. The method for monitoring the cultivation of a smart agricultural orchard according to claim 1, characterized in that: The method of judging whether the behavior data satisfies abnormal behavior according to the environment data includes: Acquire the environment data and behavior data, and perform time stamp synchronization processing on the environment data and behavior data; Based on the processing result, the behavior data is classified into behavior categories, wherein the behavior categories include activity behavior, interactive behavior and eating behavior; Constructing a behavior analysis model, inputting the synchronously processed environmental data, behavior data and behavior classification into the behavior analysis model, analyzing the behavior coefficient of the behavior data by combining the behavior classification and environmental data through the behavior analysis model, and outputting the analysis result; When the behavior coefficient is within a preset coefficient range, it is determined that the behavior coefficient does not meet the abnormal behavior; When the behavior coefficient is not within a preset coefficient range, it is determined that the behavior coefficient satisfies abnormal behavior.

3. The breeding monitoring method of the smart agricultural orchard according to claim 2 is characterized in that: After the step of determining whether the behavior coefficient satisfies the abnormal behavior, the method further includes verifying the credibility of the abnormal behavior. The method includes: Obtain historical behavior data of poultry; Performing a behavior habit analysis on the historical behavior data according to the timestamp, and determining the habit characteristics of the target poultry according to the analysis results; Compare the current behavior data and habit features in the same period, and calculate the similarity between the current behavior data and habit features through distance measurement; Based on the calculation result, if the similarity is less than a preset similarity threshold, it is determined that the behavior coefficient satisfies the abnormal behavior as a credible result.

4. The breeding monitoring method of the smart agricultural orchard according to claim 2 is characterized in that: According to the judgment result, the behavior data is quantified, and the cause of the current abnormal behavior is inferred by combining the quantified behavior data and environmental data. The method includes: Obtaining a behavior classification of the behavior data, and when the behavior is classified as an activity behavior, extracting an activity feature of the activity behavior; According to the activity characteristics, the moving distance and moving speed of the target poultry within the preset time are analyzed, and the activity intensity of the target poultry is determined according to the moving distance and moving speed; the activity time and rest time of the target poultry within the preset time are analyzed, and the activity ratio of the activity time to the rest time is calculated; Based on the analysis results, the quantified behavioral characteristics are obtained; Extracting environmental characteristics of the environmental data, wherein the environmental characteristics include climate characteristics, noise characteristics and site characteristics; The quantified behavior characteristics and environmental characteristics are input into a preset inference model, and the inference model is used to analyze and output the reasons why the environmental characteristics affect the behavior characteristics.

5. The method for monitoring the cultivation of a smart agricultural orchard according to claim 4, characterized in that: According to the result of the judgment, the behavior data is quantified, and the cause of the current abnormal behavior is inferred by combining the quantified behavior data and the environmental data. The method also includes: Obtaining a behavior classification of the behavior data, and when the behavior is classified as an interactive behavior, extracting an interactive feature of the interactive behavior; Based on the interaction characteristics, the spatial density of the interactive behaviors of poultry within a preset time is analyzed, and the concentration of the interactions of poultry in the group is analyzed; the number of times poultry interact with other poultry within a preset time and the duration of each interaction are analyzed; Based on the analysis results, the quantified behavioral characteristics are obtained; Extracting environmental characteristics of the environmental data, wherein the environmental characteristics include climate characteristics, noise characteristics and site characteristics; The quantified behavior characteristics and environmental characteristics are input into a preset inference model, and the inference model is used to analyze and output the reasons why the environmental characteristics affect the behavior characteristics.

6. The method for monitoring the cultivation of a smart agricultural orchard according to claim 1, characterized in that: The method further comprises: Obtain historical behavioral data and historical environmental data of poultry; Based on the historical behavior data and the historical environmental data, identifying the change patterns of the behavior data of poultry under different time periods and different environmental data conditions; Based on the change pattern of historical behavior data, determine the frequency of obtaining behavior data of poultry under current environmental data and time period.

7. The method for monitoring breeding in a smart agricultural orchard according to claim 1, characterized in that: The method of judging whether an abnormal condition is met according to the poultry breeding data comprises: Obtaining quantity parameters of the poultry breeding data, and verifying whether the quantity parameters are consistent with a preset quantity; When the number of the poultry is consistent with the preset number, obtaining the physical sign parameters of the poultry breeding data, and judging whether abnormal parameters appear according to the physical sign parameters; When the physical sign parameters do not show abnormal parameters, it is determined that the poultry breeding data does not show abnormalities.

8. A breeding monitoring system for a smart agricultural orchard, characterized in that: include: The first acquisition module is used to obtain poultry breeding data within the orchard in real time; A first judgment module, used to judge whether an abnormal condition is met according to the poultry breeding data; A sending module, used for obtaining the label of the abnormal poultry and sending it to the management end when the poultry breeding data is abnormal; A second acquisition module is used to acquire environmental data and poultry behavior data when the poultry breeding data is normal; A second judgment module is used to judge whether the behavior data meets the abnormal behavior according to the environmental data; A marking module, used for marking target poultry corresponding to the abnormal behavior when the behavior data meets the abnormal behavior; An inference module, used to quantify the behavior data according to the judgment result, and infer the cause of the current abnormal behavior by combining the quantified behavior data and environmental data; The generation module is used to generate a response strategy according to the cause of the current abnormal behavior based on the inferred results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images