Method for predicting laying rate of laying hens and feed additive

Abstract

This invention relates to the field of agricultural breeding technology, and particularly to a method for predicting and analyzing egg production rate in laying hens and a feed additive. The method includes: extracting heat stress factors and ammonia stress factors based on environmental data within an analysis window, thereby determining environmental stress measures; determining dietary abnormality measures based on cumulative feed intake within a monitoring period; determining production performance deviations based on egg production rate and hen weight within the monitoring period; integrating environmental stress measures, dietary abnormality measures, and production performance deviations to determine a comprehensive stress index, and predicting egg production rate based on the comprehensive stress index; and determining disease risk factors based on disease incidence and immunization records, thereby updating the predicted egg production rate. This invention achieves accurate short-term prediction and early warning of egg production rate in laying hens by quantifying the comprehensive stress index through multi-source data fusion.

Description

Technical Field

[0001] This invention relates to the field of agricultural breeding technology, and in particular to a method for predicting and analyzing the egg production rate of laying hens and a feed additive. Background Technology

[0002] In egg-laying hen farming, egg production rate is a core indicator for measuring production efficiency, but it is affected by a complex interplay of multiple factors, including temperature, humidity, ammonia levels, feed intake, body weight uniformity, and disease. Traditional methods rely on manual experience for judgment, making it difficult to quantitatively analyze the synergistic effects of multiple factors. Often, responses are only made after egg production has already declined significantly, missing the optimal intervention window.

[0003] While existing automated farming systems can collect a large amount of environmental and production data, they lack effective data fusion models and fail to transform multidimensional data into forward-looking early warning information. Therefore, there is an urgent need for a method that can integrate multi-source data, quantify comprehensive stress levels, and predict changes in egg production rates in advance, helping farmers shift from "post-event handling" to "pre-event early warning," thereby improving farming efficiency and animal welfare. Summary of the Invention

[0004] The purpose of this invention is to provide a method for predicting and analyzing the egg production rate of laying hens and a feed additive, so as to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A method for predicting and analyzing egg production rate in egg-laying hen farming environments, comprising:

[0007] Based on the environmental data within the analysis window, heat stress factors and ammonia stress factors are extracted, and then the environmental stress metric is determined.

[0008] The measure of dietary abnormality is determined based on the cumulative food intake during the monitoring period;

[0009] Based on the egg production rate and the weight of laying hens during the monitoring period, the deviation in production performance was determined.

[0010] A comprehensive stress index was determined by integrating environmental stress measurement, dietary abnormality measurement, and production performance deviation, and the egg production rate was predicted based on the comprehensive stress index;

[0011] Disease risk factors are identified based on disease incidence and immunization records, which in turn updates the prediction of egg production rate.

[0012] Furthermore, the average temperature inside the analysis window is calculated and denoted as Tavg, and the maximum and minimum temperatures inside the analysis window are recorded. At the same time, the average relative humidity RHavg and the average ammonia concentration Navg inside the analysis window are calculated.

[0013] The temperature and humidity index (THI) was constructed based on Tavg and RHavg, and THI = 0.8 × Tavg + (RHavg / 100) × (Tavg - 14.4) + 46.4.

[0014] The temperature and humidity index (THI) is compared with the preset comfort threshold (THc), and the heat stress factor (Hs) is calculated: if THI is less than or equal to THc, then Hs = 0; otherwise, Hs = min(1, (THI-THc) / (THImax-THc)); where THImax is the preset extreme heat stress threshold.

[0015] Furthermore, the ammonia stress factor Ns is calculated. When Navg is less than or equal to Nb, Ns = 0. When Navg is greater than Nb and less than or equal to Nm, Ns = (Navg-Nb) / (Nm-Nb). When Navg is greater than Nm, Ns = 1+lg(1+(Navg-Nm) / Nm).

[0016] The environmental stress measure HD was determined by combining the heat stress factor Hs and the ammonia stress factor Ns, where HD = α1 × Hs + α2 × Ns.

[0017] Where α1 is the heat stress weight, α2 is the ammonia stress weight, and α1+α2=1.

[0018] Furthermore, obtain the cumulative feed intake Fd for the current monitoring period, and at the same time, obtain the average cumulative feed intake Fda for the past N monitoring periods;

[0019] Calculate the feeding trend deviation Fde, Fde=(Fd-Fda) / Fda, and then determine the feeding abnormality measure Fdw, Fdw=min(1,max(0,-Fde)).

[0020] Further, calculate the average egg production rate LR during the monitoring period, and combine it with the theoretical egg production rate LRt of the laying hens of that age to calculate the trend deviation of the egg production rate ΔLR, ΔLR=LR-LRt;

[0021] Calculate the average weight of laying hens (BW) and the standard deviation of laying hen weight (BWb) during the monitoring period. Use BWb / BW as the weight uniformity (CVb) of laying hens in the current monitoring period. Compare CVb with the preset uniformity (c0) to determine the uniformity anomaly factor (JY): if CVb is less than or equal to c0, then JY = 0; if CVb is greater than c0, then JY = min(1, (CVb-c0) / Δb); where Δb is the preset rate of change threshold.

[0022] By combining the trend offset of egg production rate ΔLR and the uniformity anomaly factor JY, the production performance deviation PD is determined as PD = w1 × max(0, -ΔLR / LRt) + w2 × JY;

[0023] Where w1 is the egg production offset weight, w2 is the body weight uniformity weight, and w1+w2=1.

[0024] Furthermore, the number of analysis windows m1 in which the environmental emergency measure is greater than the preset environmental stress threshold during the monitoring period is counted. If m1 / M is less than or equal to U, the environmental stress factor HY for the current monitoring period is determined to be 0; otherwise, the environmental stress factor HY is determined to be ln[5×(m1 / MU)+1] / ln6; M is the total number of analysis windows during the monitoring period, and U is the preset abnormality ratio.

[0025] The comprehensive stress index ZH is determined based on environmental stress factor HY, dietary abnormality measure Fdw, and production performance deviation PD. The expression of the comprehensive stress index is: ZH=β1×HY+β2×Fdw+β3×PD.

[0026] Where β1 is the environmental weight, β2 is the dietary weight, β3 is the production weight, and β1+β2+β3=1.

[0027] Furthermore, the comprehensive stress index ZHp of the previous monitoring cycle adjacent to the current monitoring cycle is obtained to determine the stress load CZH, CZH=η×ZH+(1-η)×ZHp;

[0028] Where η is the attenuation factor;

[0029] Based on the stress load CZH, the egg production rate LRy for the next monitoring cycle is predicted, LRy=LR×[1-k×f(CZH)], where k is the maximum stress influence coefficient and f(CZH) is the stress effect function;

[0030] The expression for f(CZH) is as follows: when CZH is less than or equal to a, f(CZH) = 0; when CZH is greater than a and less than b, f(CZH) = tanh[(CZH-a) / (ba)]; when CZH is greater than or equal to b, f(CZH) = 1.

[0031] Where a is the initial threshold of stress influence and b is the saturation threshold of stress influence.

[0032] Furthermore, the maximum value Di of the disease incidence rate within the historical Q monitoring periods is obtained. At the same time, if there is an immunization event within the historical Q monitoring periods, the immunization marker Vf is recorded as 1; otherwise, the immunization marker Vf is recorded as 0.

[0033] Based on Di and Vf, a disease risk factor DF is constructed, where DF = min(1, min(1, Di / Dh) + E × Vf);

[0034] Where Dh is the disease incidence threshold and E is the immune stress coefficient.

[0035] Furthermore, the prediction results of the egg production rate for the next monitoring cycle are updated based on the disease risk factor DF, and the updated prediction results of the egg production rate are set as LRy1, LRy1=LRy×(1-μ×DF);

[0036] Where μ is the disease impact magnitude coefficient.

[0037] According to another aspect of the present invention, a feed additive is provided, comprising: 6.5% lysophospholipids, 5% vitamin C, and 88.5% bentonite.

[0038] The beneficial effects of this invention are as follows: This method, through multi-source sensor data fusion, constructs a full-chain stress quantification system encompassing environment, diet, production, and disease risk, achieving short-term accurate prediction and early warning of egg production rate in laying hens. Heterogeneous information such as temperature and humidity, ammonia levels, feed intake, egg production rate, body weight, and disease records are uniformly transformed into comparable stress indicators. The introduction of cumulative effects and piecewise nonlinear mapping makes the prediction model more consistent with biological laws. The system can identify the risk of declining egg production in advance, guiding farmers to optimize environmental control parameters, adjust feed ratios, or initiate disease prevention measures in a timely manner, thereby reducing production losses. Simultaneously, the model parameters can be adaptively adjusted based on historical data, making it suitable for different breeds and chicken house environments, significantly improving the digitalization level and early warning capabilities of livestock management, and providing reliable technical support for precision animal husbandry. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating the method for predicting and analyzing the egg production rate of laying hens in this embodiment.

[0041] Figure 2 This is a flowchart illustrating the egg production rate prediction method in this embodiment.

[0042] Figure 3 This is a flowchart illustrating the egg production rate update method in this embodiment. Detailed Implementation

[0043] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further explains the invention. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0044] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0045] Specifically, this embodiment is applied to a short-term prediction and early warning system for egg production rate in enclosed laying hen houses.

[0046] Please see Figure 1 As shown, this is a flowchart illustrating the egg production rate prediction and analysis method for egg-laying hen farming environments in this embodiment. Before the method is executed, the system synchronously collects data through multi-source sensors deployed in the chicken house environment control unit, feed delivery system, and individual chicken monitoring equipment, including:

[0047] The environmental data, including indoor temperature, relative humidity, and ammonia concentration, is collected through the sensor array built into the chicken house environment controller.

[0048] The cumulative feed intake of all laying hens in the chicken house is collected through the weighing module of the feed delivery system.

[0049] The total number of eggs produced per hour is collected by counters at the ends of egg ribbons distributed on each floor of the chicken house, and the hourly egg production rate is calculated by combining the number of laying hens.

[0050] The weight of laying hens is obtained by using individual weight monitoring devices deployed on the weighing platform (such as weighing sensors installed on the perches);

[0051] The data collection method is obtained from the farm management system, including the age of laying hens, the incidence of diseases in the previous week, and immunization records. This embodiment does not specify the data collection method, and those skilled in the art can set it freely according to their needs.

[0052] The method includes:

[0053] Step S1: Extract heat stress factors and ammonia stress factors based on environmental data within the analysis window, and then determine the environmental stress metric.

[0054] Specifically, calculate the average temperature within the analysis window, denoted as Tavg, and record the maximum and minimum temperatures within the analysis window, Tmax and Tmin. Simultaneously, calculate the average relative humidity within the analysis window, denoted as RHavg, and the average ammonia concentration, Navg.

[0055] The temperature and humidity index (THI) was constructed based on Tavg and RHavg, and THI = 0.8 × Tavg + (RHavg / 100) × (Tavg - 14.4) + 46.4.

[0056] The temperature and humidity index (THI) is compared with the preset comfort threshold (THc), and the heat stress factor (Hs) is calculated: if THI is less than or equal to THc, then Hs = 0; otherwise, Hs = min(1, (THI-THc) / (THImax-THc)); where THImax is the preset extreme heat stress threshold.

[0057] Meanwhile, the ammonia stress factor Ns is calculated. When Navg is less than or equal to Nb, Ns = 0. When Navg is greater than Nb and less than or equal to Nm, Ns = (Navg-Nb) / (Nm-Nb). When Navg is greater than Nm, Ns = 1+lg(1+(Navg-Nm) / Nm).

[0058] The environmental stress measure HD was determined by combining the heat stress factor Hs and the ammonia stress factor Ns, where HD = α1 × Hs + α2 × Ns.

[0059] Where α1 is the heat stress weight, α2 is the ammonia stress weight, and α1+α2=1.

[0060] It should be noted that the temperature Tavg and relative humidity RHavg in this formula are calculated by simply substituting the values, and there is no need to consider unit conversion. The temperature unit is degrees Celsius, and the relative humidity unit is percentage.

[0061] Specifically, in this embodiment, the preset comfort threshold is 70, the preset extreme heat stress threshold is 85, the healthy baseline for ammonia concentration is 5 ppm, the preset warning line for ammonia concentration is 20 ppm, the heat stress weight is 0.6, and the ammonia stress weight is 0.4.

[0062] Specifically, by constructing temperature and humidity indices and ammonia stress factors, environmental parameters are transformed into quantifiable heat stress and ammonia stress indicators, which are then integrated into an environmental stress metric. This allows for a comprehensive capture of the combined effects of environmental factors on laying hens. This step extracts micro-features using basic data windows as units, laying the foundation for subsequent statistical analysis of outlier window proportions. This ensures that the assessment of environmental stress is both sensitive and stable, avoiding misjudgments caused by single fluctuations, and thus accurately reflecting whether the chicken house environment is within a suitable range.

[0063] Please continue reading. Figure 1As shown, the method for predicting and analyzing egg production rate in egg-laying hen farming environments also includes:

[0064] Step S2: Determine the measure of dietary abnormality based on the cumulative food intake during the monitoring period.

[0065] Specifically, obtain the cumulative feed intake Fd for the current monitoring period, and at the same time, obtain the average cumulative feed intake Fda for the past N monitoring periods;

[0066] Calculate the feeding trend deviation Fde, Fde=(Fd-Fda) / Fda, and then determine the feeding abnormality measure Fdw, Fdw=min(1,max(0,-Fde)), the value range of Fdw is [0,1], and it is taken as 1 when the feed intake decreases by more than 100%.

[0067] Specifically, in this embodiment, the value of N is 5.

[0068] Specifically, based on historical trend analysis of feed intake, focusing only on the direction of decline in feed intake, a measure of abnormal feeding can be constructed to promptly detect early abnormal signals such as decreased appetite in laying hens. This indicator eliminates the interference of normal fluctuations in feed intake and directly reflects changes in the feeding behavior of laying hens under stress, providing production managers with quantitative data on dietary health and helping to identify potential problems such as feed quality, water supply, or disease in advance.

[0069] Please continue reading. Figure 1 As shown, the method for predicting and analyzing egg production rate in egg-laying hen farming environments also includes:

[0070] Step S3: Determine the production performance deviation based on the egg production rate and the weight of laying hens during the monitoring period.

[0071] Specifically, calculate the average egg production rate LR during the monitoring period, and combine it with the theoretical egg production rate LRt of the laying hens of that age to calculate the trend deviation of the egg production rate ΔLR, where ΔLR = LR - LRt;

[0072] Calculate the average weight of laying hens (BW) and the standard deviation of laying hen weight (BWb) during the monitoring period. Use BWb / BW as the weight uniformity (CVb) of laying hens in the current monitoring period. Compare CVb with the preset uniformity (c0) to determine the uniformity anomaly factor (JY): if CVb is less than or equal to c0, then JY = 0; if CVb is greater than c0, then JY = min(1, (CVb-c0) / Δb); where Δb is the preset rate of change threshold.

[0073] By combining the trend offset of egg production rate ΔLR and the uniformity anomaly factor JY, the production performance deviation PD is determined as PD = w1 × max(0, -ΔLR / LRt) + w2 × JY;

[0074] Where w1 is the egg production offset weight, w2 is the body weight uniformity weight, and w1+w2=1.

[0075] Specifically, in this embodiment, the theoretical egg production rate of laying hens can be obtained from the standard egg production curve or breeding manual based on the age of the laying hens. The preset uniformity threshold is 0.1, the preset rate of change threshold is 0.2, the egg production offset weight is 0.7, and the weight uniformity weight is 0.3.

[0076] Specifically, by combining the deviation of egg production rate from theoretical values ​​with changes in body weight uniformity, a production performance deviation is constructed to comprehensively assess the current production level and flock consistency of laying hens. This step focuses on both core economic indicators and flock health status, enabling timely detection of stress-induced declines in egg production and individual differentiation, providing a direct basis for precise control, thereby maintaining high and stable flock production.

[0077] Please continue reading. Figure 1 As shown, the method for predicting and analyzing egg production rate in egg-laying hen farming environments also includes:

[0078] Step S4: Integrate environmental stress measurement, dietary abnormality measurement, and production performance deviation to determine the comprehensive stress index, and predict the egg production rate based on the comprehensive stress index.

[0079] Please see Figure 2 As shown, the egg production rate prediction method includes:

[0080] Step S41: Integrate environmental stress measurement, dietary abnormality measurement, and production performance deviation to determine the comprehensive stress index.

[0081] Specifically, the number of analysis windows m1 in which the environmental emergency measure is greater than the preset environmental stress threshold during the monitoring period is counted. If m1 / M is less than or equal to U, the environmental stress factor HY for the current monitoring period is determined to be 0; otherwise, the environmental stress factor HY is determined to be ln[5×(m1 / MU)+1] / ln6; M is the total number of analysis windows in the monitoring period, and U is the preset abnormality ratio.

[0082] The comprehensive stress index ZH is determined based on environmental stress factor HY, dietary abnormality measure Fdw, and production performance deviation PD. The expression of the comprehensive stress index is: ZH=β1×HY+β2×Fdw+β3×PD.

[0083] Where β1 is the environmental weight, β2 is the dietary weight, β3 is the production weight, and β1+β2+β3=1.

[0084] Specifically, in this embodiment, the preset abnormality ratio is 0.1, the environmental weight is 0.4, the dietary weight is 0.3, the production weight is 0.3, and the preset environmental stress threshold is 0.5.

[0085] Specifically, stress measures from three dimensions—environment, diet, and production—are integrated. An environmental stress factor is constructed by statistically analyzing the proportion of outlier windows and applying logarithmic transformation. This factor is then weighted and combined with dietary anomaly measures and production performance deviations to form a single comprehensive stress index. This step normalizes and integrates multi-source heterogeneous data, comprehensively quantifying the overall stress level of laying hens, eliminating the potential bias of a single indicator, and providing a unified and comparable core input for subsequent predictions, making stress assessment more scientific and objective.

[0086] Please continue reading. Figure 2 As shown, the egg production rate prediction method further includes:

[0087] Step S42: Predict the egg production rate based on the comprehensive stress index.

[0088] Specifically, the comprehensive stress index ZHp of the previous monitoring cycle adjacent to the current monitoring cycle is obtained to determine the stress load CZH, CZH=η×ZH+(1-η)×ZHp;

[0089] Where η is the attenuation factor;

[0090] Based on the stress load CZH, the egg production rate LRy for the next monitoring cycle is predicted, LRy=LR×[1-k×f(CZH)], where k is the maximum stress influence coefficient and f(CZH) is the stress effect function;

[0091] The expression for f(CZH) is as follows: when CZH is less than or equal to a, f(CZH) = 0; when CZH is greater than a and less than b, f(CZH) = tanh[(CZH-a) / (ba)]; when CZH is greater than or equal to b, f(CZH) = 1.

[0092] Where a is the initial threshold of stress influence and b is the saturation threshold of stress influence.

[0093] Specifically, in this embodiment, the attenuation factor is 0.7, the maximum stress influence coefficient is 0.2, the initial stress influence threshold is 0.3, and the stress influence saturation threshold is 0.8.

[0094] Specifically, based on the comprehensive stress index, an exponential smoothing method is introduced to calculate the cumulative stress load, accurately reflecting the continuous cumulative effect and lagged impact of stress on laying hens. A piecewise linear function is used to construct a stress effect mapping, converting the cumulative stress load into the percentage decrease in egg production rate, thereby predicting the egg production rate in future cycles. This step transforms the qualitative stress state into a quantitative prediction of egg production rate changes, enabling managers to grasp production trends in advance, providing a clear time window and quantitative basis for formulating intervention measures, and significantly improving the timeliness and practicality of the prediction.

[0095] Please continue reading. Figure 1 As shown, the method for predicting and analyzing egg production rate in egg-laying hen farming environments also includes:

[0096] Step S5: Based on the disease incidence rate and immunization records, disease risk factors are determined, and the prediction results of egg production rate are updated.

[0097] Please see Figure 3 As shown, the method for updating the egg production rate includes:

[0098] Step S51: Determine disease risk factors based on disease incidence and immunization records.

[0099] Specifically, the maximum value Di of the disease incidence rate within the historical Q monitoring periods is obtained. The disease incidence rate is the proportion of the number of sick chickens to the total number of chickens in stock within the monitoring period. At the same time, if there is an immunization event within the historical Q monitoring periods, the immunization marker Vf is recorded as 1; otherwise, the immunization marker Vf is recorded as 0.

[0100] Based on Di and Vf, a disease risk factor DF is constructed, where DF = min(1,(min(1,Di / Dh)+E×Vf));

[0101] Where Dh is the disease incidence threshold and E is the immune stress coefficient.

[0102] Specifically, in this embodiment, Q is 10, the disease incidence threshold is 0.1, the immune stress coefficient is 0.05, and the disease impact magnitude coefficient is 0.1.

[0103] Specifically, in this embodiment, the analysis window is 10 minutes and the monitoring cycle is 1 day.

[0104] Specifically, disease risk factors are constructed using disease incidence and immunization information recorded in the farm management system, and health events are incorporated into the predictive model. This step fully explores the health risks hidden in the existing data, quantifies the additional stress of disease outbreaks and immunization procedures on the flock, enables the model to respond to sudden health events, avoids prediction bias caused by health factors, and enhances the model's robustness and adaptability.

[0105] Please continue reading. Figure 1 As shown, the method for updating the egg production rate further includes:

[0106] Step S52: Update the prediction results of egg production rate based on disease risk factors.

[0107] Specifically, the prediction results of the egg production rate for the next monitoring cycle are updated based on the disease risk factor DF, and the updated prediction results of the egg production rate are set as LRy1, LRy1=LRy×(1-μ×DF);

[0108] Where μ is the disease impact magnitude coefficient.

[0109] Specifically, disease risk factors are used as a correction term to perform a secondary adjustment on the egg production rate prediction results based on the comprehensive stress index, resulting in a final prediction value that more closely reflects the actual risk. This step organically integrates health factors and stress factors, enabling the prediction model to dynamically reflect the combined effects of disease and immunity on egg production rate. This effectively improves the prediction accuracy during periods of high disease incidence or intensive immunization, providing more reliable decision support for farms to formulate disease prevention and health management strategies.

[0110] To effectively mitigate the negative impacts of environmental stress, abnormal diet, and disease risk on the production performance of chicken flocks, this application also provides an auxiliary intervention method suitable for this scenario: a feed additive, by weight percentage, comprising 6.5% lysophospholipids, 5% vitamin C, and 88.5% bentonite, wherein the montmorillonite content of the bentonite is not less than 80%. In this additive, lysophospholipids can promote fat absorption to compensate for energy consumption, vitamin C can scavenge free radicals to alleviate oxidative stress, and the high montmorillonite content of the bentonite can adsorb intestinal toxins and maintain intestinal health; the synergistic effect of these three components can assist chicken flocks in maintaining or restoring egg production performance during stress.

[0111] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all the implementation methods here. All obvious variations or modifications derived from the technical solutions of the present invention are still within the protection scope of the present invention.

Claims

1. A method for predicting and analyzing egg production rate in egg-laying hen farming environments, characterized in that, include: Based on the environmental data within the analysis window, heat stress factors and ammonia stress factors are extracted, and then the environmental stress metric is determined. The measure of dietary abnormality is determined based on the cumulative food intake during the monitoring period. Based on the egg production rate and the weight of laying hens during the monitoring period, the deviation in production performance was determined. A comprehensive stress index was determined by integrating environmental stress measurement, dietary abnormality measurement, and production performance deviation, and the egg production rate was predicted based on the comprehensive stress index. Disease risk factors are identified based on disease incidence and immunization records, which in turn updates the prediction of egg production rate.

2. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 1, characterized in that, Calculate the average temperature inside the analysis window, denoted as Tavg, and record the maximum and minimum temperatures inside the analysis window, Tmax and Tmin. At the same time, calculate the average relative humidity RHavg and the average ammonia concentration Navg inside the analysis window. The temperature and humidity index (THI) was constructed based on Tavg and RHavg, and THI = 0.8 × Tavg + (RHavg / 100) × (Tavg - 14.4) + 46.

4. The temperature and humidity index (THI) is compared with the preset comfort threshold (THc), and the heat stress factor (Hs) is calculated: if THI is less than or equal to THc, then Hs = 0; otherwise, Hs = min(1, (THI-THc) / (THImax-THc)); where THImax is the preset extreme heat stress threshold.

3. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 2, characterized in that, Calculate the ammonia stress factor Ns. When Navg is less than or equal to Nb, Ns = 0. When Navg is greater than Nb and less than or equal to Nm, Ns = (Navg-Nb) / (Nm-Nb). When Navg is greater than Nm, Ns = 1 + lg(1 + (Navg-Nm) / Nm). The environmental stress measure HD was determined by combining the heat stress factor Hs and the ammonia stress factor Ns, where HD = α1 × Hs + α2 × Ns. Where α1 is the heat stress weight, α2 is the ammonia stress weight, and α1+α2=1.

4. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 3, characterized in that, Obtain the cumulative feed intake Fd for the current monitoring period, and at the same time, obtain the average cumulative feed intake Fda for the past N monitoring periods; Calculate the feeding trend deviation Fde, Fde=(Fd-Fda) / Fda, and then determine the feeding abnormality measure Fdw, Fdw=min(1,max(0,-Fde)).

5. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 4, characterized in that, Calculate the average egg production rate LR during the monitoring period, and combine it with the theoretical egg production rate LRt of the laying hens of that age to calculate the trend deviation of the egg production rate ΔLR, ΔLR=LR-LRt; Calculate the average weight of laying hens (BW) and the standard deviation of laying hen weight (BWb) during the monitoring period. Use BWb / BW as the weight uniformity (CVb) of laying hens in the current monitoring period. Compare CVb with the preset uniformity (c0) to determine the uniformity anomaly factor (JY): if CVb is less than or equal to c0, then JY = 0; if CVb is greater than c0, then JY = min(1, (CVb-c0) / Δb); where Δb is the preset rate of change threshold. By combining the trend offset of egg production rate ΔLR and the uniformity anomaly factor JY, the production performance deviation PD is determined as PD = w1 × max(0, -ΔLR / LRt) + w2 × JY; Where w1 is the egg production offset weight, w2 is the body weight uniformity weight, and w1+w2=1.

6. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 5, characterized in that, The number of analysis windows m1 in which the environmental emergency measure is greater than the preset environmental stress threshold during the monitoring period is calculated. If m1 / M is less than or equal to U, the environmental stress factor HY for the current monitoring period is determined to be 0. Otherwise, the environmental stress factor HY is determined to be ln[5×(m1 / MU)+1] / ln6. M is the total number of analysis windows in the monitoring period, and U is the preset abnormality ratio. The comprehensive stress index ZH is determined based on environmental stress factor HY, dietary abnormality measure Fdw, and production performance deviation PD. The expression of the comprehensive stress index is: ZH=β1×HY+β2×Fdw+β3×PD; Where β1 is the environmental weight, β2 is the dietary weight, β3 is the production weight, and β1+β2+β3=1.

7. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 6, characterized in that, Obtain the comprehensive stress index ZHp of the previous monitoring cycle adjacent to the current monitoring cycle to determine the stress load CZH, CZH=η×ZH+(1-η)×ZHp; Where η is the attenuation factor; Based on the stress load CZH, the egg production rate LRy for the next monitoring cycle is predicted, LRy=LR×[1-k×f(CZH)], where k is the maximum stress influence coefficient and f(CZH) is the stress effect function; The expression for f(CZH) is as follows: when CZH is less than or equal to a, f(CZH) = 0; when CZH is greater than a and less than b, f(CZH) = tanh[(CZH-a) / (ba)]; when CZH is greater than or equal to b, f(CZH) = 1. Where a is the initial threshold of stress influence and b is the saturation threshold of stress influence.

8. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 7, characterized in that, Obtain the maximum value Di of the disease incidence rate within the historical Q monitoring periods. At the same time, if there is an immunization event within the historical Q monitoring periods, record the immune marker Vf as 1; otherwise, record the immune marker Vf as 0. Based on Di and Vf, a disease risk factor DF is constructed, where DF = min(1, min(1, Di / Dh) + E × Vf); Where Dh is the disease incidence threshold and E is the immune stress coefficient.

9. The method for predicting and analyzing egg production rate in egg-laying hen farming environments according to claim 8, characterized in that, The prediction results of the egg production rate for the next monitoring cycle are updated based on the disease risk factor DF, and the updated prediction results of the egg production rate are set as LRy1, LRy1=LRy×(1-μ×DF); Where μ is the disease impact magnitude coefficient.

10. A feed additive, applied to the predictive analysis method for egg production rate of laying hens as described in any one of claims 1-9, characterized in that, include: Lysophospholipids 6.5%, Vitamin C 5%, Bentonite 88.5%.

Images