A disease prevention and control method and system based on continuous monitoring of feeding environment

Abstract

The present invention discloses a disease prevention and control method and system based on continuous monitoring of a breeding environment, and relates to the technical field of breeding management. The present invention includes obtaining the growth rate of infected egg poultry with different disease types in each state of each collection time in the breeding farm according to the continuously acquired number of infected egg poultry and the disease types in the breeding farm; obtaining the range of environmental parameters of each type corresponding to each disease type in an easily contagious state according to the historical records of environmental parameters of each type in the breeding farm and the growth rate of infected egg poultry with different disease types in each state of each collection time; judging whether the environmental parameters of each type in the breeding farm at the current moment fall into the range of environmental parameters of each type corresponding to each disease type in an easily contagious state; if so, generating the target environmental parameters of each type in the breeding farm at the current moment; if not, performing continuous monitoring. The present invention can timely and effectively adjust the unfavorable state in the egg poultry breeding environment, and effectively avoid the occurrence and spread of diseases.

Description

Technical Field

[0001] The present invention belongs to the technical field of breeding management, and in particular relates to a disease prevention and control method and system based on continuous monitoring of breeding environment. Background Art

[0002] With the rapid development of animal husbandry, large-scale and intensive breeding models have gradually become the mainstream. In intensive breeding environments, the health of laying poultry faces many challenges, especially the spread of diseases. Once an epidemic breaks out in a farm, it will not only cause large-scale economic losses, but may also pose a serious threat to public health and safety. Therefore, how to effectively monitor and prevent the spread of diseases in breeding environments is an important issue that needs to be urgently addressed in the current animal husbandry field.

[0003] At present, traditional disease prevention and control methods mainly rely on manual inspections and laboratory testing. Although these methods have a certain degree of accuracy, they have problems such as long detection cycles and untimely responses. Summary of the invention

[0004] The purpose of the present invention is to provide a disease prevention and control method and system based on continuous monitoring of the breeding environment. By summarizing and analyzing the disease conditions and environmental historical records in the egg-laying poultry breeding environment, it is possible to timely and effectively adjust the adverse conditions in the egg-laying poultry breeding environment and effectively avoid the occurrence and spread of diseases.

[0005] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention provides a disease prevention and control method based on continuous monitoring of the feeding environment, comprising:

[0007] Continuously obtain multiple types of environmental parameters in the egg-laying poultry farm and obtain historical records, wherein the types of environmental parameters include temperature, humidity, suspended particulate matter concentration, noise and / or sound decibels;

[0008] Continuously obtain the number and types of diseases of diseased laying poultry in the farms;

[0009] According to the continuously acquired number and types of diseased laying poultry in the farm, the growth rate of the infected laying poultry of different disease types in the farm at each collection time is obtained;

[0010] According to the historical records of environmental parameters of each species in the farm and the growth rate of infected laying birds of different disease types at each collection time, the range of environmental parameters of each species corresponding to each disease type in the easily contagious state is obtained;

[0011] Obtain the environmental parameters of each species in the farm at the current moment;

[0012] Determine whether the environmental parameters of each species in the farm at the current moment fall within the environmental parameter range of each species corresponding to each disease species in a highly infectious state;

[0013] If yes, then generate the target environmental parameters for each species in the farm at the current moment;

[0014] If not, continue monitoring.

[0015] The present invention also discloses a disease prevention and control method based on continuous monitoring of the feeding environment, comprising:

[0016] Receive target environmental parameters for each species in the farm at the current moment;

[0017] The environmental parameters in the farm are adjusted according to the target environmental parameters of each species in the farm at the current moment.

[0018] The present invention also discloses a disease prevention and control system based on continuous monitoring of the feeding environment, comprising:

[0019] Environmental sensors are used to collect multiple types of environmental parameters in egg-laying poultry farms;

[0020] Disease detection unit, used to collect the number and types of diseased laying poultry in the farm;

[0021] An alarm unit is used to continuously obtain multiple types of environmental parameters in the egg-laying poultry farm and obtain historical records, wherein the types of environmental parameters include temperature, humidity, suspended particulate matter concentration, noise and / or sound decibels;

[0022] Continuously obtain the number and types of diseases of diseased laying poultry in the farms;

[0023] According to the continuously acquired number and types of diseased laying poultry in the farm, the growth rate of the infected laying poultry of different disease types in the farm at each collection time is obtained;

[0024] According to the historical records of environmental parameters of each species in the farm and the growth rate of infected laying birds of different disease types at each collection time, the range of environmental parameters of each species corresponding to each disease type in the easily contagious state is obtained;

[0025] Obtain the environmental parameters of each species in the farm at the current moment;

[0026] Determine whether the environmental parameters of each species in the farm at the current moment fall within the environmental parameter range of each species corresponding to each disease species in a highly infectious state;

[0027] If yes, then generate the target environmental parameters for each species in the farm at the current moment;

[0028] If not, then ongoing monitoring is performed;

[0029] An environmental adjustment device, used to receive target environmental parameters of each species in the farm at the current moment;

[0030] The environmental parameters in the farm are adjusted according to the target environmental parameters of each species in the farm at the current moment.

[0031] The present invention collects the environmental conditions and disease conditions in the egg-laying poultry farm through environmental sensors and disease detection units, and analyzes the correlation between the two through an alarm unit, thereby mining the environmental parameter range of each type corresponding to each disease type in a contagious state, thereby realizing early warning of the environmental parameters of each type in the farm at the current moment, and promptly reminding managers to pay attention to adjustments. The occurrence and spread of diseases in egg-laying poultry farms are effectively avoided.

[0032] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0034] Figure 1 A schematic diagram of functional units and information flows of an epidemic prevention and control system based on continuous monitoring of a feeding environment according to an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of a step flow of an alarm unit according to an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of a process flow of an environment adjustment device according to an embodiment of the present invention;

[0037] Figure 4 is a schematic diagram of step S4 of the present invention in an embodiment;

[0038] Figure 5 is a schematic diagram of step S41 of the present invention in an embodiment;

[0039] Figure 6 is a schematic diagram of step S44 of the present invention in an embodiment;

[0040] Figure 7 is a schematic diagram of step S443 of the present invention in an embodiment;

[0041] Figure 8 is a schematic diagram of step S4432 of the present invention in an embodiment;

[0042] Fig. 9 is a schematic diagram of step S7 of the present invention in an embodiment;

[0043] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0044] 1-Environmental sensor, 2-disease detection unit, 3-alarm unit, 4-environmental adjustment device. DETAILED DESCRIPTION

[0045] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0046] It should be noted that the terms "first", "second", etc. in 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 the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0047] See also Figures 1 to 3 As shown, the present invention provides a disease prevention and control system based on continuous monitoring of the breeding environment, which includes an environmental sensor 1, a disease detection unit 2, an alarm unit 3 and an environmental adjustment device 4 in terms of functional units. The environmental sensor 1 can be a hardware device of various types and functions, or a virtual functional unit to realize the input of various environmental parameters. The disease detection unit 2 can be a virtual functional unit to realize the collection of various disease information, the alarm unit 3 is a computing device, and the environmental adjustment device 4 can be a device with environmental adjustment function in a poultry and egg farm.

[0048] During the operation of the system, the environmental sensor 1 executes step S011 to collect multiple types of environmental parameters in the laying poultry farm, including temperature, humidity, suspended particulate matter concentration and noise decibels, which are closely related to the spread of pathogens in the air, and the noise decibels are closely related to the mental state of laying poultry. At the same time, the disease detection unit 2 executes step S021 to collect the number and types of diseases of the diseased laying poultry in the farm.

[0049] The alarm unit 3 in this system processes the various information collected by the environmental sensor 1 and the disease detection unit 2. Specifically, step S1 can be first executed to continuously obtain multiple types of environmental parameters in the egg-laying poultry farm and obtain historical records. Next, step S2 can be executed to continuously obtain the number and types of diseases of diseased egg-laying poultry in the farm. Next, step S3 can be executed to obtain the growth rate of diseased egg-laying poultry with different types of diseases in the farm at each collection time based on the continuously obtained number and types of diseases of diseased egg-laying poultry in the farm.

[0050] See also Figures 1 to 5 As shown, when the alarm unit performs correlation analysis on the environmental parameters and the disease status, step S4 can be executed to obtain the environmental parameter range of each type corresponding to each disease type in the easily contagious state according to the historical records of the environmental parameters of each type in the farm and the growth rate of the infected eggs and poultry of different disease types at each collection time. Specifically, step S41 can be first executed to obtain the critical value of the growth rate of the infected eggs and poultry of each disease type in the epidemic state according to the growth rate of the infected eggs and poultry of different disease types at each collection time. For each disease type, when calculating the critical value of the growth rate of infected eggs and poultry, step S411 can be first executed to arrange the growth rate of the infected eggs and poultry at each collection time according to the numerical value to obtain the growth rate series of infected eggs and poultry. Next, step S412 can be executed to calculate the difference between the maximum value and the minimum value in the growth rate series of infected eggs and poultry as the span of the growth rate series of infected eggs and poultry. Next, step S413 can be executed to calculate the ratio of the span of the growth rate series of infected eggs and poultry to the number of all elements in the growth rate series of infected eggs and poultry as the step length of the growth rate series of infected eggs and poultry. Next, step S414 can be executed to calculate the difference between two adjacent elements starting from the minimum value in the growth rate series of infected poultry and eggs, and determine whether the difference is less than the step length of the growth rate series of infected poultry and eggs. If so, then step S414 can be returned to continue to calculate the difference between two adjacent elements and make a judgment. If not, step S415 can be executed to use the maximum value involved in the calculation as the critical value of the growth rate of infected poultry and eggs for the disease type under the epidemic state. Finally, step S416 can be executed to summarize and obtain the critical value of the growth rate of infected poultry and eggs for each disease type under the epidemic state.

[0051] In order to supplement the implementation process of the above steps S411 to S416, the source code of some functional modules is provided, and the explanation is compared in the comment section. In order to avoid the leakage of data involving commercial secrets, some data that does not affect the implementation of the solution are desensitized, the same below.

[0052] #include <iostream>

[0053] #include <vector>

[0054] #include <map>

[0055] #include <algorithm>

[0056] / / Define the disease data structure

[0057] struct DiseaseData {

[0058] int timestamp; / / Collection time

[0059] int diseaseType; / / disease type number

[0060] int infectedCount; / / Number of infected laying hens

[0061] };

[0062] / / Define history

[0063] std::map <int, std::vector <diseasedata>>diseaseHistory; / / Disease data stored by disease type

[0064] / / Calculate the growth rate of infected laying poultry for each disease

[0065] std::map <int, std::vector <double>>calculateGrowthSequences() {

[0066] std::map<int, std::vector <double>>growthSequences;

[0067] for (const auto&[diseaseType, records] : diseaseHistory) {

[0068] std::vector <double>growthRates;

[0069] for (size_t i = 1; i<records.size(); ++i) {

[0070] double growth = static_cast <double>(records[i].infectedCount -records[i - 1].infectedCount);

[0071] growthRates.push_back(growth);

[0072] }

[0073] growthSequences[diseaseType] = growthRates;

[0074] }

[0075] return growthSequences;

[0076] }

[0077] / / Calculate the critical value of the growth rate of infected laying poultry for each disease

[0078] std::map<int, double> calculateGrowthThresholds(const std::map <int,std::vector <double>>&growthSequences) {

[0079] std::map<int, double> thresholds;

[0080] for (const auto&[diseaseType, growthSequence] : growthSequences) {

[0081] if (growthSequence.empty()) {

[0082] thresholds[diseaseType] = 0.0; / / When there is no growth rate data, the threshold is set to 0

[0083] continue;

[0084] }

[0085] / / 1. Sort the growth rate series of infected laying poultry

[0086] std::vector <double>sortedGrowths = growthSequence;

[0087] std::sort(sortedGrowths.begin(), sortedGrowths.end());

[0088] / / 2. Calculate the span of the growth rate series of infected laying birds

[0089] double range = sortedGrowths.back() - sortedGrowths.front();

[0090] / / 3. Calculate the step length of the growth rate series of infected laying birds

[0091] double step = range / sortedGrowths.size();

[0092] / / 4. Find the critical value

[0093] double threshold = sortedGrowths.front();

[0094] for (size_t i = 1; i <sortedGrowths.size(); ++i) {

[0095] double diff = sortedGrowths[i] - sortedGrowths[i - 1];

[0096] if (diff>step) {

[0097] break; / / When the difference is greater than the step length, the calculation ends

[0098] }

[0099] threshold = sortedGrowths[i];

[0100] }

[0101] thresholds[diseaseType] = threshold;

[0102] }

[0103] return thresholds;

[0104] }

[0105] / / Main function

[0106] int main() {

[0107] / / Simulate disease historical data

[0108] diseaseHistory[1] = {

[0109] {0, 1, 10}, {1, 1, 15}, {2, 1, 25}, {3, 1, 30}, {4, 1, 50}

[0110] };

[0111] diseaseHistory[2] = {

[0112] {0, 2, 5}, {1, 2, 6}, {2, 2, 8}, {3, 2, 10}, {4, 2, 15}

[0113] };

[0114] / / 1. Calculate the growth rate sequence of diseased poultry

[0115] auto growthSequences = calculateGrowthSequences();

[0116] / / 2. Calculate the growth rate critical value

[0117] auto thresholds = calculateGrowthThresholds(growthSequences);

[0118] / / Output the result

[0119] for (const auto&[diseaseType, threshold] : thresholds) {

[0120] std::cout<<"The growth rate critical value for disease type "<<diseaseType<<" is: "<<threshold<<"\n";

[0121] }

[0122] return 0;

[0123] }

[0124] The code implements an algorithm to calculate the critical value of the growth rate of infected laying poultry for each disease. By sorting the growth rate data and calculating the step length, the maximum value of the stable growth rate range is identified and used as the critical value of the epidemic state. This method effectively excludes abnormal growth points or mutation points, thus laying the foundation for subsequent analysis of disease prevention and control.

[0125] Please continue reading Figures 1 to 5 As shown, after the calculation of the critical value of the growth rate of infected egg-laying poultry is completed, step S42 can be executed next to obtain the epidemic state period of each disease type in the farm according to the growth rate of infected egg-laying poultry of different disease types at each collection time and the critical value of the growth rate of infected egg-laying poultry of each disease type in the epidemic state. Next, step S43 can be executed to obtain the environmental parameters of each type of disease in the farm at multiple collection times corresponding to each disease type in the easily contagious state according to the historical records of the environmental parameters of each type in the farm and the epidemic state period of each disease type in the farm. Finally, step S44 can be executed to obtain the environmental parameter range of each type of disease in the easily contagious state according to the environmental parameters of each type at multiple collection times corresponding to each disease type in the farm in the easily contagious state.

[0126] See also Figures 6 to 8 As shown, since the range of environmental parameters of each type of multiple collection moments corresponding to each type of disease in the easily contagious state in step S43 is too large, it may cause subsequent false alarm problems. Therefore, it is necessary to appropriately narrow the range of environmental parameters of each type corresponding to the easily contagious state on the basis of avoiding misjudgment. Specifically for each type of disease, firstly, step S441 can be executed to select two of the multiple collection moments corresponding to the type of disease in the easily contagious state as marked collection moments. Next, step S442 can be executed to subtract the environmental parameters of each type of the two collection moments and then add them up as the environmental difference between the two collection moments, and calculate the environmental difference between each marked collection moment and each other collection moment of the type of disease in the easily contagious state. Next, step S443 can be executed to obtain multiple post-screening collection moments corresponding to the type of disease in the easily contagious state according to the environmental difference between each marked collection moment and each other collection moment of the type of disease in the easily contagious state.

[0127] In operation, the multiple collection moments corresponding to the disease type in the easily contagious state can be divided into appropriate and overly sensitive, and the relative quantity relationship between these two categories should be stable when fully classified. In view of this, step S4431 can be first executed to divide each other collection moment with the smallest difference from the environment into the same moment set among the multiple collection moments corresponding to the disease type in the easily contagious state, and obtain two moment sets, namely, the appropriate and overly sensitive moment sets. Next, step S4432 can be executed to determine whether the environmental differences between all the collection moments contained in each moment set are convergent.

[0128] When judging whether there is convergence in the moment set, the relative quantity relationship between the two types of appropriate and oversensitive moment sets when fully classified should be stable. Therefore, in the process of executing step S4432, step S44321 can be first executed to calculate and obtain the ratio of the number of acquisition moments contained in the two moment sets. Next, step S44322 can be executed to calculate and obtain the mean environmental parameters of each type of all acquisition moments in the moment set for each moment set. Next, step S44323 can be executed to use the acquisition moment with the smallest environmental difference with the mean environmental parameters of each type of all acquisition moments in each moment set as the updated marked acquisition moment. Next, step S44324 can be executed to re-divide the updated moment set according to the updated marked acquisition moment. Next, step S44325 can be executed to determine whether the ratio of the number of acquisition moments contained in the two moment sets before and after the update has changed. If so, step S44326 can be executed to determine that there is no convergence, and if not, step S44327 can be executed to determine that there is convergence.

[0129] In the above identification and judgment process, if it is determined that there is convergence, then step S4433 can be executed next to use all the collection moments contained in the time set with more collection moments in the two time sets as multiple post-screening collection moments corresponding to the disease type in the easily contagious state. If it is determined that there is no convergence, step S4434 can be executed next, and return to execute step S4432 to regenerate the time set and re-judge whether the environmental differences between all the collection moments contained therein are convergent.

[0130] After obtaining the multiple post-screening collection moments corresponding to the disease type in the easily contagious state, step S444 can be executed next to use the numerical distribution range of each type of environmental parameters at the multiple post-screening collection moments corresponding to the disease type in the easily contagious state as the environmental parameter range of each type corresponding to the disease type in the easily contagious state. Finally, step S445 can be executed to summarize and obtain the environmental parameter range of each type corresponding to each disease type in the easily contagious state.

[0131] In order to provide additional explanation for the implementation process of the above-mentioned steps S441 to S445, source codes of some functional modules are provided, and comparative explanations are provided in the comments.

[0132] #include <iostream>

[0133] #include <vector>

[0134] #include <map>

[0135] #include <cmath>

[0136] #include <limits>

[0137] #include <algorithm>

[0138] / / Define the environment parameter structure

[0139] struct EnvironmentData {

[0140] double temperature; / / temperature

[0141] double humidity; / / humidity

[0142] double particles; / / suspended particle concentration

[0143] double noise; / / noise

[0144] };

[0145] / / Define the environment record for disease data

[0146] using DiseaseEnvironmentRecords = std::map <int, std::vector <environmentdata>>;

[0147] / / Calculate the environment difference

[0148] double calculateDifference(const EnvironmentData&env1, constEnvironmentData&env2) {

[0149] return std::abs(env1.temperature - env2.temperature) +

[0150] std::abs(env1.humidity - env2.humidity) +

[0151] std::abs(env1.particles - env2.particles) +

[0152] std::abs(env1.noise - env2.noise);

[0153] }

[0154] / / Calculate the environmental mean parameters within the collection

[0155] EnvironmentData calculateMeanEnvironment(const std::vector <environmentdata>&envSet) {

[0156] EnvironmentData mean = {0.0, 0.0, 0.0, 0.0};

[0157] for (const auto&env : envSet) {

[0158] mean.temperature += env.temperature;

[0159] mean.humidity += env.humidity;

[0160] mean.particles += env.particles;

[0161] mean.noise += env.noise;

[0162] }

[0163] int size = envSet.size();

[0164] mean.temperature / = size;

[0165] mean.humidity / = size;

[0166] mean.particles / = size;

[0167] mean.noise / = size;

[0168] return mean;

[0169] }

[0170] / / Divide the set of moments

[0171] std::pair<std::vector <environmentdata>, std::vector <environmentdata>>partitionTimestamps(

[0172] const std::vector <environmentdata>&envData,

[0173] const EnvironmentData&marker1,

[0174] const EnvironmentData&marker2) {

[0175] std::vector <environmentdata>set1, set2;

[0176] for (const auto&env : envData) {

[0177] double diffToMarker1 = calculateDifference(env, marker1);

[0178] double diffToMarker2 = calculateDifference(env, marker2);

[0179] if (diffToMarker1 <diffToMarker2) {

[0180] set1.push_back(env);

[0181] } else {

[0182] set2.push_back(env);

[0183] }

[0184] }

[0185] return {set1, set2};

[0186] }

[0187] / / Determine whether the set is convergent

[0188] bool hasConvergence(

[0189] const std::vector <environmentdata>&prevSet1,

[0190] const std::vector <environmentdata>&prevSet2,

[0191] const std::vector <environmentdata>&newSet1,

[0192] const std::vector <environmentdata>&newSet2) {

[0193] return prevSet1.size() == newSet1.size()&&prevSet2.size() ==newSet2.size();

[0194] }

[0195] / / Recursive algorithm to identify the set of post-screening moments

[0196] std::vector <environmentdata>findConvergentSet(

[0197] std::vector <environmentdata>envData,

[0198] EnvironmentData marker1,

[0199] EnvironmentData marker2) {

[0200] auto [set1, set2] = partitionTimestamps(envData, marker1, marker2);

[0201] / / If a collection is empty, return another collection directly

[0202] if (set1.empty()) return set2;

[0203] if (set2.empty()) return set1;

[0204] / / Calculate mean environmental parameters

[0205] EnvironmentData mean1 = calculateMeanEnvironment(set1);

[0206] EnvironmentData mean2 = calculateMeanEnvironment(set2);

[0207] / / Update the mark collection time

[0208] EnvironmentData newMarker1 = *std::min_element(set1.begin(), set1.end(), [&mean1](const EnvironmentData&a, const EnvironmentData&b) {

[0209] return calculateDifference(a, mean1) <calculateDifference(b, mean1);

[0210] });

[0211] EnvironmentData newMarker2 = *std::min_element(set2.begin(), set2.end(), [&mean2](const EnvironmentData&a, const EnvironmentData&b) {

[0212] return calculateDifference(a, mean2) <calculateDifference(b, mean2);

[0213] });

[0214] / / Repartition the collection

[0215] auto [newSet1, newSet2] = partitionTimestamps(envData, newMarker1,newMarker2);

[0216] / / Determine convergence

[0217] if (hasConvergence(set1, set2, newSet1, newSet2)) {

[0218] return newSet1.size()>newSet2.size() ? newSet1 : newSet2;

[0219] } else {

[0220] return findConvergentSet(envData, newMarker1, newMarker2);

[0221] }

[0222] }

[0223] / / Calculate the environment parameter range

[0224] std::map <std::string, std::pair<double, double> >calculateEnvironmentRange(const std::vector <environmentdata>&envSet) {

[0225] std::map<std::string, std::pair<double, double>>ranges = {

[0226] {"temperature", {std::numeric_limits <double>::max(), std::numeric_limits <double>::lowest()}},

[0227] {"humidity", {std::numeric_limits <double>::max(), std::numeric_limits <double>::lowest()}},

[0228] {"particles", {std::numeric_limits <double>::max(), std::numeric_limits <double>::lowest()}},

[0229] {"noise", {std::numeric_limits <double>::max(), std::numeric_limits <double>::lowest()}}

[0230] };

[0231] for (const auto&env : envSet) {

[0232] ranges["temperature"].first = std::min(ranges["temperature"].first,env.temperature);

[0233] ranges["temperature"].second = std::max(ranges["temperature"].second,env.temperature);

[0234] ranges["humidity"].first = std::min(ranges["humidity"].first,env.humidity);

[0235] ranges["humidity"].second = std::max(ranges["humidity"].second,env.humidity);

[0236] ranges["particles"].first = std::min(ranges["particles"].first,env.particles);

[0237] ranges["particles"].second = std::max(ranges["particles"].second,env.particles);

[0238] ranges["noise"].first = std::min(ranges["noise"].first, env.noise);

[0239] ranges["noise"].second = std::max(ranges["noise"].second, env.noise);

[0240] }

[0241] return ranges;

[0242] }

[0243] / / Main function

[0244] int main() {

[0245] / / Simulate data

[0246] std::vector <environmentdata>envData = {

[0247] {20.0, 60.0, 30.0, 50.0}, {21.0, 61.0, 31.0, 49.0}, {19.5, 59.0,30.5, 48.5},

[0248] {22.0, 62.0, 32.0, 51.0}, {21.5, 60.5, 31.5, 50.5}

[0249] };

[0250] / / Initialize the mark collection time

[0251] EnvironmentData marker1 = envData[0];

[0252] EnvironmentData marker2 = envData[1];

[0253] / / Recursively find the post-screening moment set

[0254] auto filteredSet = findConvergentSet(envData, marker1, marker2);

[0255] / / Calculate the environment parameter range

[0256] auto ranges = calculateEnvironmentRange(filteredSet);

[0257] / / Output results

[0258] std::cout<<"Environment parameter range after screening:\n";

[0259] for (const auto&[param, range] : ranges) {

[0260] std::cout< <param<<": ["<<range.first<<", "<<range.second<<"]\n";

[0261] }

[0262] return 0;

[0263] }

[0264] The above code implements a complex time division and environmental parameter range calculation algorithm, which is used to analyze the environmental characteristics of the disease in a contagious state. By recursively comparing the environmental differences and re-dividing the time set, a collection time set with convergence is finally extracted, and the environmental parameter range of these moments is calculated. This algorithm can accurately identify environmental conditions with transmission characteristics and is suitable for accurate prevention and control of farm diseases.

[0265] Please continue reading Figures 1 to 4 As shown, in the process of real-time disease monitoring of egg-laying poultry farms, step S5 can be first executed to obtain the environmental parameters of each species in the farm at the current moment. Next, step S6 can be executed to determine whether the environmental parameters of each species in the farm at the current moment fall into the environmental parameter range of each species corresponding to each disease species in an easily contagious state. If so, step S7 can be executed next to generate the target environmental parameters of each species in the farm at the current moment. If not, steps S1 to S7 can be executed next to perform continuous monitoring.

[0266] See also Fig. 9 As shown, in the process of adjusting the farm environment, it is necessary to avoid suitable environmental parameters for the outbreak of the disease. Therefore, step S71 can be first executed to obtain the epidemic state period of each disease type in the farm according to the growth rate of infected egg poultry of different disease types at each collection time and the critical value of the growth rate of infected egg poultry of each disease type in the epidemic state. Next, step S72 can be executed to obtain multiple collection moments corresponding to each disease type in the farm in the non-infectious state as the non-infectious state collection moment according to the historical records of the environmental parameters of each type in the farm and the non-epidemic state period of each disease type in the farm. Next, step S73 can be executed to select the target collection moment from multiple non-infectious state collection moments. For the convenience of adjustment, among multiple non-infectious state collection moments, the non-infectious state collection moment with the smallest environmental difference from the current moment can be used as the target collection moment. Finally, step S74 can be executed to use the target environmental parameters of each type at the target moment as the target environmental parameters of each type at the current moment.

[0267] Please continue reading Figures 1 to 3 As shown, the environment adjustment device 4 in this solution can first perform step S041 to receive the target environment parameters of each type in the farm at the current moment during operation, and then perform step S042 to adjust the environment parameters in the farm according to the target environment parameters of each type in the farm at the current moment.

[0268] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, system, method and computer program product according to multiple embodiments of the present application. In this regard, each square frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the square frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square frames can actually be executed substantially in parallel, and they can also be executed in reverse order sometimes, depending on the functions involved.

[0269] It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented by hardware that performs the corresponding function or action, such as a circuit or ASIC (Application Specific Integrated Circuit), or can be implemented by a combination of hardware and software, such as firmware.

[0270] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0271] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those of ordinary skill in the art without departing from the scope of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.< / environmentdata> < / double> < / double> < / double> < / double> < / double> < / double> < / double> < / double> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / environmentdata> < / algorithm> < / limits> < / cmath> < / map> < / vector> < / iostream> < / double> < / double> < / double> < / double> < / double> < / double> < / diseasedata> < / algorithm> < / map> < / vector> < / iostream>

Claims

1. A disease prevention and control method based on continuous monitoring of the feeding environment, characterized in that: include, Continuously acquiring multiple types of environmental parameters in a laying poultry farm and obtaining historical records, wherein the types of environmental parameters include temperature, humidity, suspended particulate matter concentration and / or noise decibels; Continuously obtain the number and types of diseases of diseased laying poultry in the farms; According to the continuously acquired number and types of diseased laying poultry in the farm, the growth rate of the infected laying poultry of different disease types in the farm at each collection time is obtained; According to the growth rate of infected laying poultry with different types of diseases at each collection time, the critical value of the growth rate of infected laying poultry with each type of disease under the epidemic state is obtained; According to the growth rate of infected laying poultry of different disease types at each collection time and the critical value of the growth rate of infected laying poultry of each disease type under the epidemic state, the epidemic state period of each disease type in the farm can be obtained; According to the historical records of environmental parameters of each species in the farm and the epidemic period of each disease type in the farm, the environmental parameters of each species at multiple collection times corresponding to each disease type in the farm in a highly infectious state are obtained; Obtaining the environmental parameter range of each type of disease in a highly infectious state according to the environmental parameters of each type at multiple collection times corresponding to each type of disease in a highly infectious state in the farm; Obtain the environmental parameters of each species in the farm at the current moment; Determine whether the environmental parameters of each species in the farm at the current moment fall within the environmental parameter range of each species corresponding to each disease species in a highly infectious state; If yes, then generate the target environmental parameters for each species in the farm at the current moment; If not, continue monitoring.

2. The method according to claim 1, characterized in that The step of obtaining the critical value of the growth rate of infected poultry eggs of each disease type under the epidemic state according to the growth rate of infected poultry eggs of different disease types at each collection time, include, For each disease type, perform the following steps separately: Arrange the growth rate of infected laying hens at each collection moment according to the numerical value to obtain the growth rate series of infected laying hens. Calculate the difference between the maximum and minimum values ​​in the growth rate series of infected egg-laying poultry as the span of the growth rate series of infected egg-laying poultry. Calculate the ratio of the span of the diseased egg poultry growth rate series to the number of all elements in the diseased egg poultry growth rate series as the step length of the diseased egg poultry growth rate series. Starting from the minimum value in the growth rate series of infected poultry, the difference between two adjacent elements is calculated in sequence, and it is determined whether the difference is less than the step length of the growth rate series of infected poultry. If so, continue to calculate the difference between two adjacent elements and judge, If not, the maximum value involved in the calculation will be used as the critical value of the growth rate of infected laying poultry under the epidemic situation of the disease type; The critical value of the growth rate of infected laying poultry under the epidemic situation of each disease type is summarized.

3. The method according to claim 1, characterized in that The step of obtaining the range of environmental parameters for each type of disease in an easily contagious state according to the environmental parameters for each type at multiple collection times corresponding to each type of disease in an easily contagious state in the farm, include, For each disease type, perform the following steps separately: Select two of the multiple collection times corresponding to the disease type in the easily contagious state as the marked collection times, Subtract the corresponding environmental parameters of each type at the two collection times and add them up as the environmental difference between the two collection times. Calculate the environmental difference between each marked collection time and each other collection time of the disease type in the easily contagious state. According to the environmental difference between each marked collection time of the disease type in the easily contagious state and each other collection time, multiple post-screening collection times corresponding to the disease type in the easily contagious state are obtained. The numerical distribution range of the environmental parameters of each type at multiple post-screening collection moments corresponding to the disease type in the easily contagious state is used as the environmental parameter range of each type corresponding to the disease type in the easily contagious state; The environmental parameter ranges for each type of disease in a highly contagious state are summarized.

4. The method according to claim 3, characterized in that: The step of obtaining a plurality of post-screening collection times corresponding to the disease type in an easily contagious state according to the environmental difference between each marked collection time and each other collection time of the disease type in an easily contagious state comprises: Among the multiple collection moments corresponding to the infectious state of the disease type, each marked collection moment with the smallest difference from the environment is divided into the same time set to obtain two time sets. Determine whether the environmental differences between all the collected moments in each moment set are similar. If so, all the collection times contained in the time set with more collection times in the two time sets are used as multiple post-screening collection times corresponding to the disease type in the easily contagious state. If not, then the time set is regenerated and it is re-determined whether the environmental differences between all the included collection moments are convergent.

5. The method according to claim 4, characterized in that The step of judging whether the environmental differences between all the collection moments included in each moment set are similar, include, Calculate the ratio of the number of collected moments contained in the two moment sets. For each time set, calculate and obtain the mean environmental parameters of each type of all collected time points in the time set. In each time set, the collection time with the smallest environmental difference from the mean environmental parameters of each type of all collection times in the collection time set is used as the updated marked collection time. Re-partition according to the updated marked collection time to obtain the updated time set, Determine whether the ratio of the number of collected moments contained in the two moment sets before and after the update has changed. If so, it is considered that there is no convergence. If not, it is considered to be convergent.

6. The method according to any one of claims 1 to 5, characterized in that: The step of generating target environmental parameters for each species in the farm at the current moment, include, According to the growth rate of infected laying poultry of different disease types at each collection time and the critical value of the growth rate of infected laying poultry of each disease type under the epidemic state, the epidemic state period of each disease type in the farm can be obtained; According to the historical records of environmental parameters of each type in the farm and each type of disease in the farm during the non-epidemic period, multiple collection times corresponding to each type of disease in the farm in the non-infectious state are obtained as the non-infectious state collection times; Selecting a target collection time from multiple non-infectious state collection times; The target environment parameters of each category at the target moment are used as the target environment parameters of each category at the current moment.

7. The method according to claim 6, characterized in that The step of selecting a target collection time from a plurality of non-infectious state collection times includes: Among multiple non-infectious state collection moments, the non-infectious state collection moment with the smallest environmental difference from the current moment is taken as the target collection moment.

8. A disease prevention and control method based on continuous monitoring of the feeding environment, characterized in that: include, Receiving the target environmental parameters of each species in the farm at the current moment in the disease prevention and control method based on continuous monitoring of the breeding environment as described in any one of claims 1 to 7; The environmental parameters in the farm are adjusted according to the target environmental parameters of each species in the farm at the current moment.

9. A disease prevention and control system based on continuous monitoring of the feeding environment, characterized in that: include, Environmental sensors are used to collect multiple types of environmental parameters in egg-laying poultry farms; Disease detection unit, used to collect the number and types of diseased laying poultry in the farm; An alarm unit is used to continuously obtain multiple types of environmental parameters in the egg-laying poultry farm and obtain historical records, wherein the types of environmental parameters include temperature, humidity, suspended particulate matter concentration, noise and / or sound decibels; Continuously obtain the number and types of diseases of diseased laying poultry in the farms; According to the continuously acquired number and types of diseased laying poultry in the farm, the growth rate of the infected laying poultry of different disease types in the farm at each collection time is obtained; According to the growth rate of infected laying poultry with different types of diseases at each collection time, the critical value of the growth rate of infected laying poultry with each type of disease under the epidemic state is obtained; According to the growth rate of infected laying poultry of different disease types at each collection time and the critical value of the growth rate of infected laying poultry of each disease type under the epidemic state, the epidemic state period of each disease type in the farm can be obtained; According to the historical records of environmental parameters of each species in the farm and the epidemic period of each disease type in the farm, the environmental parameters of each species at multiple collection times corresponding to each disease type in the farm in a highly infectious state are obtained; Obtaining the environmental parameter range of each type of disease in a highly infectious state according to the environmental parameters of each type at multiple collection times corresponding to each type of disease in a highly infectious state in the farm; Obtain the environmental parameters of each species in the farm at the current moment; Determine whether the environmental parameters of each species in the farm at the current moment fall within the environmental parameter range of each species corresponding to each disease species in a highly infectious state; If yes, then generate the target environmental parameters for each species in the farm at the current moment; If not, ongoing monitoring is performed; An environmental adjustment device is used to receive the target environmental parameters of each species in the farm at the current moment; The environmental parameters in the farm are adjusted according to the target environmental parameters of each species in the farm at the current moment.

Images