Classical Swine Fever Virus Detection System Based on Cloud Analysis

Abstract

The present invention discloses a classical swine fever virus detection system based on cloud analysis, which includes an image acquisition unit, a data processing cloud, a disease monitoring unit and a warning management unit. The image acquisition unit is used to collect the limb images of live pigs, and the data processing cloud is used to construct an image analysis model to analyze the limb images of live pigs, comprehensively evaluate the suspected degree of classical swine fever risk from two perspectives of vascular risk and tissue edema, so as to assist in the diagnosis of classical swine fever virus detection; then the disease monitoring unit conducts long-term monitoring on the classical swine fever virus, analyzes the deterioration or recovery of the condition of diseased pigs, generates a health management plan for diseased pigs, and improves the targeted treatment effect of diseased pigs; furthermore, the warning management unit conducts a global analysis of the virus risk, generates a live pig breeding management plan, so as to conduct corresponding overall control on the infection degree of classical swine fever virus in the live pig breeding base, improve the warning management efficiency of the live pig breeding base, and reduce the loss and management cost of live pig breeding.

Description

Technical Field

[0001] The present invention relates to the technical field of virus detection, and particularly to a classical swine fever virus detection system based on cloud analysis. Background Art

[0002] Classical swine fever virus is the pathogen of classical swine fever. Classical swine fever is an acute, febrile, highly contagious disease, which is extremely harmful to pigs and will cause significant losses to the pig-raising industry. After being infected with classical swine fever virus, obvious fluid accumulation or local inflammation will appear in the limbs and other parts of live pigs. The blood vessels are red, hot and swollen, and local bleeding, infarction and necrosis may occur, indicating serious infection or complications. Therefore, live pigs with the above symptoms are determined to be suspected of being infected with classical swine fever virus;

[0003] The existing methods for detecting classical swine fever virus mainly rely on biomedical detection techniques. Samples are collected from suspected diseased pigs and then subjected to experimental detection. There are technical defects such as high virus detection costs, large demand for manual sampling, and easy spread of virus infection. Due to the sudden outbreak of classical swine fever and the shortage of manpower in live pig breeding bases, the work efficiency of classical swine fever virus diagnosis will be low. And the infectivity of classical swine fever virus is extremely strong, which may miss the best control opportunity. Moreover, traditional biological sample collection is mainly saliva or blood samples, and the collection process is also prone to virus spread and lead to the continuous deterioration of classical swine fever epidemic;

[0004] In view of the above technical defects, a solution is proposed now. Summary of the Invention

[0005] The purpose of the present invention is to solve the technical defects existing in the existing methods for detecting classical swine fever virus, such as high virus detection costs, large demand for manual sampling, and easy spread of virus infection. By remotely collecting live pig limb images and sending them to the cloud for data processing, the demand for manual sampling is reduced, and an image analysis model is constructed to evaluate the suspected degree of classical swine fever virus infection, improving the work efficiency of virus detection. By sampling biological detection to compare and test the accuracy of the image analysis model, the image analysis model is continuously optimized to improve the accuracy of virus detection, significantly reducing the trend of virus infection spread and effectively curbing the continuous deterioration of classical swine fever epidemic.

[0006] In order to achieve the above purpose, the present invention adopts the following technical scheme:

[0007] A classical swine fever virus detection system based on cloud analysis includes an image acquisition unit, a data processing cloud, a disease monitoring unit and an early warning management unit, wherein the image acquisition unit, the data processing cloud, the disease monitoring unit and the early warning management unit are communicatively connected;

[0008] The image acquisition unit is used to acquire the limb images of live pigs: Set the image acquisition period Tp. By binding the wearable device to the limb part of the live pig, an infrared image acquisition instrument is set in the wearable device. The infrared image acquisition instrument is used to regularly acquire the limb images of the live pig, and then the limb images of the live pig are transmitted to the data processing cloud through remote signals;

[0009] The data processing cloud is used to build an image analysis model to analyze the limb images of live pigs: The data processing cloud includes a vascular risk analysis module, a tissue edema analysis module, a swine fever risk assessment module, and a comparison and optimization module;

[0010] Through the vascular risk analysis module, analyze the blood flow of the limb blood vessels and evaluate the degree of vascular risk; Through the tissue edema analysis module, analyze the tissue edema of the limb part and evaluate the degree of tissue edema; Through the swine fever risk assessment module, combine the degree of vascular risk with the degree of tissue edema, comprehensively evaluate the suspected degree of swine fever to obtain the image detection result of the swine fever virus, so as to assist in the diagnosis of the swine fever virus detection; Through the comparison and optimization module, obtain the biological detection result of the swine fever virus, and feedback it to the image analysis model to compare with the image detection result, and determine the detection accuracy of the image analysis model, so as to continuously optimize the image analysis model;

[0011] The disease monitoring unit is used to monitor the swine fever virus for a long time: By regularly monitoring the image detection result of the swine fever virus, analyze the long-term development status of the swine fever virus, evaluate the health risk degree of the diseased pig, generate a health management plan for the diseased pig and give corresponding risk warnings;

[0012] The early warning management unit is used to conduct a global analysis of the virus risk: By comprehensively analyzing the degree of virus risk, evaluate the infection status of the swine fever virus in the live pig breeding base, generate a live pig breeding management plan and conduct corresponding early warning management.

[0013] Furthermore, the specific construction process of the image analysis model is as follows:

[0014] The image analysis model includes a vascular analysis sub-model, a tissue analysis sub-model, and a comprehensive analysis sub-model;

[0015] Sa, establish a vascular analysis sub-model through the vascular risk analysis module, analyze the blood flow of the limb blood vessels, and evaluate the degree of vascular risk;

[0016] Sb, establish a tissue analysis sub-model through the tissue edema analysis module, analyze the tissue edema of the limb part, and evaluate the degree of tissue edema;

[0017] Sc, establish a comprehensive analysis sub-model through the classical swine fever risk assessment module, combine the vascular risk degree with the tissue edema degree, comprehensively evaluate the suspicion degree of classical swine fever, obtain the image detection result of classical swine fever virus, so as to assist in the diagnosis of classical swine fever virus detection;

[0018] Sd, obtain the biological detection result of classical swine fever virus through the comparison and optimization module, and feedback it to the image analysis model to compare with the image detection result, determine the detection accuracy of the image analysis model, so as to continuously optimize the image analysis model.

[0019] Furthermore, the specific process of establishing the vascular analysis sub-model is as follows:

[0020] Sa-1, input the image of the live pig's limb into the vascular analysis sub-model;

[0021] Extract N0 pixel points of the live pig's limb image and perform gray-scale acquisition, and mark the gray-scale value of any pixel point i as HDi;

[0022] Set the gray-scale interval Qh of the blood vessel, extract the pixel points whose gray-scale value HDi is within the gray-scale interval Qh, and integrate them into a blood vessel feature point set, and mark the area where the blood vessel feature point set is located as the blood vessel area;

[0023] Divide the blood vessel area into N1 characteristic areas and perform area state analysis, mark any characteristic area as J, and measure the gray-scale mean value η1 of n0 pixel points in the characteristic area J;

[0024] Set the gray-scale interval Qη of regional infarction. When the gray-scale mean value η1 of the characteristic area J is within the gray-scale interval Qη, mark the characteristic area as the infarction area; otherwise, mark the characteristic area as the blood flow area;

[0025] Sa-2, perform targeted analysis on the infarction area and the blood flow area respectively, and the specific process is as follows:

[0026] Sa-201, analyze the infarction area: obtain the infarction ratio η2 by measuring the proportion of all infarction areas in the blood vessel area;

[0027] Sa-202, analyze the blood flow area: extract the live pig's limb images corresponding to N2 image acquisition cycles Tp, and construct a dynamic curve S0 between the gray-scale mean value η1 of the blood flow area and the image acquisition cycle Tp, and obtain the pumping cycle Tb and pumping intensity Db through the dynamic curve S0;

[0028] Sa-3, combine the infarction ratio η2, the pumping cycle Tb and the pumping intensity Db to obtain the vascular risk assessment coefficient Xxg.

[0029] Furthermore, the specific process of establishing the tissue analysis sub-model is as follows:

[0030] Sb-1, extract the pixel points whose gray value HDi of the pig limb image is not in the gray interval Qh, and mark the area where the pixel point is located as the tissue area;

[0031] Sb-2, divide the tissue area into M1 characteristic areas and perform regional state analysis. Mark any one of the characteristic areas as R, and measure the average gray value φ1 of m0 pixel points in the characteristic area R;

[0032] Sb-201, set the gray interval Qs for regional edema. If the average gray value φ1 of the characteristic area R is in the gray interval Qs, then mark the characteristic area as the edema area;

[0033] Sb-202, obtain the edema ratio φ2 by cumulatively measuring the proportion of all edema areas in the tissue area. Extract the pig limb images corresponding to N2 image acquisition cycles Tp, and obtain the edema ratios of the pig limb images corresponding to N2 image acquisition cycles Tp;

[0034] Sb-203, obtain the edema ratio growth rate ψ through the edema ratios φ2 corresponding to two adjacent image acquisition cycles, and then obtain the average edema growth rate Ψr and the edema change coefficient σr;

[0035] Sb-3, combine the average edema growth rate Ψr and the edema change coefficient σr to obtain the tissue risk assessment coefficient Xzh.

[0036] Furthermore, the specific process of establishing the comprehensive analysis sub-model is as follows:

[0037] Sc-1, construct the change curve s1 between the blood vessel risk assessment coefficient Xxg and the image acquisition cycle Tp, and the change curve s2 between the tissue risk assessment coefficient Xzh and the image acquisition cycle Tp;

[0038] Synchronously extract M3 points of the change curve s1 and the change curve s2 to establish the risk parameter matrix V;

[0039] Sc-2, obtain the overall risk index va and the risk fluctuation index vb from the risk parameter matrix V, and then obtain the risk factor υ. Mark the risk factors of the blood vessel risk assessment coefficient Xxg and the tissue risk assessment coefficient Xzh as υ1 and υ2 respectively;

[0040] Sc-3, combine the risk factor υ1 of the blood vessel risk assessment coefficient Xxg and the risk factor υ2 of the tissue risk assessment coefficient Xzh to obtain the suspected swine fever reference index Zw;

[0041] Set the determination interval Qw of the suspected swine fever reference index Zw. When the suspected swine fever reference index Zw is in the determination interval Qw, it is determined that the image detection result is infected with the swine fever virus; otherwise, it is determined that the image detection result is not infected with the swine fever virus.

[0042] Further, the specific optimization process of the image analysis model is as follows:

[0043] Sd-1: Mark the total number of live pigs as ZT, set the sampling ratio q%, obtain the live pig sample size YB, select YB live pig samples by random sampling, conduct biological tests on the live pig samples, obtain the biological test results, set the biological test value Ja, and assign values to the biological test value Ja based on the biological test results;

[0044] Sd-2: Set the image detection value Pa, and assign values to the image detection value Pa based on the image detection results;

[0045] Sd-3: Compare the biological test value Ja and the image detection value Pa to obtain the detection deviation coefficient JP;

[0046] Sd-4: Set the evaluation interval of the detection deviation coefficient JP, evaluate the detection accuracy of the image analysis model through interval comparison, then set the correction amplitude of the image analysis model, and optimize and adjust the image analysis model.

[0047] Further, the specific process of long-term monitoring of classical swine fever virus is as follows:

[0048] When the image detection result and the biological test result of the classical swine fever virus both indicate infection with the classical swine fever virus, mark the live pig sample as a diseased pig, mark the number of diseased pigs as BZ, and extract the classical swine fever suspected reference index Zw corresponding to the image detection result of the diseased pig;

[0049] Set the virus monitoring period Td, construct the change curve sd between the classical swine fever suspected reference index Zw and the virus monitoring period Td, extract n3 points and their coordinates on the change curve sd, measure and obtain the slope values corresponding to the n3 points, and obtain the curve growth rate Ψs and the curvature fluctuation coefficient σs of the change curve sd;

[0050] When the slope value Kpo of any point is 0, determine that the point is a marked point, extract the curve segment sz between the marked point Yz and the end point of the change curve sd, and obtain the drop value Lz and the change rate Kz of the curve segment sz;

[0051] Furthermore, comprehensively obtain the health risk index Zjk of the diseased pigs, set the evaluation interval of the health risk index Zjk of the diseased pigs, evaluate the health risk degree of the diseased pigs through interval comparison, generate the corresponding health management plan for the diseased pigs and give risk warnings.

[0052] Further, the specific process of global analysis of virus risk is as follows:

[0053] Obtain the estimated number of diseased pigs in the total live pig population ZT by calculating the proportion of the number of diseased pigs BZ detected in the live pig sample size YB, and comprehensively analyze the virus risk level of all live pigs in the live pig breeding base in combination with the health risk index Zjk of the diseased pigs to obtain the classical swine fever virus infection index Zgr.

[0054] Set the evaluation interval of the classical swine fever virus infection index Zgr, evaluate the classical swine fever virus infection degree of the live pig breeding base through interval comparison, generate the corresponding live pig breeding management plan and conduct early warning management.

[0055] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are as follows:

[0056] The present invention remotely collects live pig limb images and sends them to the cloud for data processing, reducing the demand for manual sampling, and constructs an image analysis model to evaluate the suspected degree of classical swine fever virus infection, improving the work efficiency of virus detection. By means of sampling biological detection, the accuracy of the image analysis model is compared and tested, so as to continuously optimize the image analysis model, improve the accuracy of virus detection, significantly reduce the trend of virus infection spread, and effectively contain the continuous deterioration of the classical swine fever epidemic situation;

[0057] The present invention collects live pig limb images through an image acquisition unit, and constructs an image analysis model through a data processing cloud to analyze the live pig limb images, comprehensively evaluate the suspected degree of classical swine fever risk from two aspects of blood vessel risk and tissue edema, so as to assist in the diagnosis of classical swine fever virus detection; then, through a disease monitoring unit, long-term monitoring of the classical swine fever virus is carried out, the deterioration or recovery of the condition of diseased pigs is analyzed, and a health management plan for diseased pigs is generated, so as to conduct corresponding health management according to the health risk level of diseased pigs and improve the targeted treatment effect of diseased pigs;

[0058] The present invention conducts a global analysis of virus risks through an early warning management unit, generates a live pig breeding management plan, so as to conduct corresponding overall control according to the classical swine fever virus infection degree of the live pig breeding base, improve the early warning management efficiency of the live pig breeding base, and reduce the losses and management costs of live pig breeding. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Shows a schematic diagram of the modules of the present invention;

[0060] Figure 2 Shows a schematic diagram of the process of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0061] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0062] Embodiment 1:

[0063] As Figure 1 - Figure 2 shown, a classical swine fever virus detection system based on cloud analysis includes an image acquisition unit, a data processing cloud, a disease monitoring unit, and an early warning management unit. Among them, the image acquisition unit, the data processing cloud, the disease monitoring unit, and the early warning management unit are communicatively connected;

[0064] S1, the image acquisition unit acquires the limb images of live pigs: Set the image acquisition period Tp. By binding the wearable device to the limb part of the live pig, an infrared image acquisition instrument is set in the wearable device. The infrared image acquisition instrument periodically acquires the limb images of the live pig, and then remotely transmits the limb images of the live pig to the data processing cloud;

[0065] Through the wearable device, targeted health monitoring of the live pigs in the pig breeding base is carried out. The wearable device uses an infrared sensor for optical image monitoring. Through the wearable device, the body temperature, heart rate, blood pressure, and blood vessel conditions of the live pigs can be monitored for a long time, so as to comprehensively analyze the physical health status of the live pigs. In the case of classical swine fever virus infection, the abnormalities of the live pigs can be detected in time, realizing remote monitoring of the diseased pigs, and avoiding the spread of the virus caused by people carrying the virus;

[0066] S2, the data processing cloud constructs an image analysis model to analyze the limb images of live pigs: The data processing cloud includes a blood vessel risk analysis module, a tissue edema analysis module, a classical swine fever risk assessment module, and a comparison and optimization module; among them, the blood vessel risk analysis module, the tissue edema analysis module, the classical swine fever risk assessment module, and the comparison and optimization module are communicatively connected;

[0067] The blood flow condition of the limb blood vessels is analyzed through the blood vessel risk analysis module to evaluate the blood vessel risk degree; the tissue edema condition of the limb part is analyzed through the tissue edema analysis module to evaluate the tissue edema degree; through the classical swine fever risk assessment module, the blood vessel risk degree and the tissue edema degree are combined to comprehensively evaluate the classical swine fever suspicion degree to obtain the image detection result of the classical swine fever virus, so as to assist in the diagnosis of the classical swine fever virus detection; through the comparison and optimization module, the biological detection result of the classical swine fever virus is obtained, and it is fed back to the image analysis model to be compared with the image detection result to determine the detection accuracy of the image analysis model, so as to continuously optimize the image analysis model;

[0068] Among them, the biological test results of classical swine fever virus are obtained through existing pathological detection means, and the biological test results are remotely transmitted to the data processing cloud. The pathological detection means is to obtain pig pathological samples regularly, such as blood samples, and then conduct biological experiments on the pathological samples to determine whether the samples contain classical swine fever virus; for example, enzyme-linked immunosorbent assay is used to detect whether there are specific antibodies or antigens against classical swine fever virus in the serum through antigen-antibody reaction;

[0069] The specific construction process of the image analysis model is as follows: The image analysis model includes a vascular analysis sub-model, a tissue analysis sub-model, and a comprehensive analysis sub-model;

[0070] Sa. Establish a vascular analysis sub-model through the vascular risk analysis module, analyze the blood flow of limb blood vessels, and evaluate the degree of vascular risk. The specific process of establishing the vascular analysis sub-model is as follows:

[0071] Sa-1. Input the image of the pig's limb into the vascular analysis sub-model;

[0072] Extract N0 pixel points of the pig's limb image and perform gray-scale acquisition, and mark the gray-scale value of any pixel point i as HDi;

[0073] Set the gray-scale interval Qh of the blood vessel, extract the pixel points whose gray-scale value HDi is within the gray-scale interval Qh, and integrate them into a set of blood vessel feature points, and mark the area where the set of blood vessel feature points is located as the blood vessel area;

[0074] Divide the blood vessel area into N1 characteristic regions and conduct regional state analysis. Mark any characteristic region as J, and measure the gray-scale mean value η1 of n0 pixel points in the characteristic region J: ;

[0075] Set the gray-scale interval Qη of regional infarction. When the gray-scale mean value η1 of the characteristic region J is within the gray-scale interval Qη, it is determined that the characteristic region J shows vascular infarction necrosis, and mark this characteristic region as the infarction area; otherwise, it is determined that the characteristic region J shows blood flow in the blood vessel, and mark this characteristic region as the blood flow area;

[0076] Sa-2. Conduct targeted analysis on the infarction area and the blood flow area respectively. The specific process is as follows:

[0077] Sa-201. Analyze the infarction area: Mark the number of infarction areas as n1, mark the area of any infarction area as Sg, and mark the area of the blood vessel area as Sp. Then, cumulatively measure the proportion of all infarction areas in the blood vessel area and mark it as the infarction proportion η2: ;

[0078] Sa-202, Analyze the blood flow area: Extract the limb images of the live pig corresponding to N2 image acquisition cycles Tp, and construct a dynamic curve S0 between the gray-scale mean value η1 of the blood flow area and the image acquisition cycle Tp;

[0079] Measure the pumping cycle Tb and the pumping intensity Db through the dynamic curve S0. The specific process is as follows: By calculating the slope values of n2 points of the dynamic curve S0, obtain the peak points and valley points of the dynamic curve S0, and mark the number of peak points and valley points as N3. Then, mark any group of peak points and valley points as a peak-valley pair;

[0080] By calculating the abscissa difference between two adjacent peak points, obtain the peak point cycle length and mark it as the pumping cycle Tb; and by calculating the ordinate difference between the adjacent peak point and valley point, obtain the peak-valley floating difference e1, and then measure the ordinate mean value between the adjacent peak point and valley point to obtain the peak-valley gray-scale mean value e2;

[0081] Then, combine the peak-valley floating differences e1 and the peak-valley gray-scale mean values e2 of N3 groups of peak-valley pairs to analyze the pumping intensity Db: ;

[0082] Among them, α1 and α2 are respectively the weight factor coefficients of the peak-valley floating difference e1 and the peak-valley gray-scale mean value e2, and both α1 and α2 are greater than 0. The weight factor coefficients are preset after being measured through a large amount of experimental data. When the peak-valley floating difference e1 and the peak-valley gray-scale mean value e2 are higher, the pumping intensity Db is higher, indicating that the contrast gap of the blood volume between the vasoconstriction and dilation states within the pumping cycle Tb is large and the overall level is high, indicating that the blood state in the blood vessel is relatively active, may be in a congested state, and the blood flow intensity is higher;

[0083] Sa-3, Combine the infarction ratio η2, the pumping cycle Tb, and the pumping intensity Db to obtain the blood vessel risk assessment coefficient Xxg: ;

[0084] Among them, by combining the pumping cycle Tb and the pumping intensity Db, obtain the blood flow state coefficient. Set ω1 and ω2 as the weight factor coefficients of the infarction ratio η2 and the blood flow state coefficient respectively, and both ω1 and ω2 are greater than 0; when the pumping cycle Tb is lower and the pumping intensity Db is higher, the blood flow state coefficient is higher, indicating that the blood flow state is stronger. At the same time, when the infarction ratio η2 is higher, it indicates that the situation of blood vessel infarction or necrosis is more serious, and the blood vessel risk assessment coefficient Xxg is higher, indicating that the comprehensive risk of the blood vessel infarction state and the blood flow state is higher, which will make the symptoms of classical swine fever more serious and the suspected degree of classical swine fever virus infection higher;

[0085] Sb, Establish a tissue analysis sub-model through the tissue edema analysis module to analyze the tissue edema situation of the limb part and evaluate the tissue edema degree. The specific process of establishing the tissue analysis sub-model is as follows:

[0086] Sb-1, extract the pixel points whose gray values HDi of the pig limb image are not in the gray value interval Qh, that is, all pixel points outside the vascular feature point set, and mark the area where they are located as the tissue area, that is, the non-vascular area;

[0087] Sb-2, divide the tissue area into M1 characteristic regions and perform regional state analysis. Mark any one of the characteristic regions as R, and measure the average gray value φ1 of m0 pixel points in the characteristic region R;

[0088] Sb-201, set the gray value interval Qs for regional edema. If the average gray value φ1 of the characteristic region R is in the gray value interval Qs, it is determined that the characteristic region R is in a state of tissue edema, and mark this characteristic region as the edema area; otherwise, it is determined that this characteristic region is normal;

[0089] Sb-202, mark the number of edema areas in the pig limb image as m1, mark the area of any one edema area as Sz, then cumulatively measure the proportion of all edema areas in the tissue area and mark it as the edema proportion φ2;

[0090] Extract the pig limb images corresponding to N2 image acquisition cycles Tp, and obtain the edema proportions of the pig limb images corresponding to N2 image acquisition cycles Tp;

[0091] Mark two adjacent image acquisition cycles as Tp1 and Tp2 respectively. Mark the edema proportion corresponding to the image acquisition cycle Tp1 as φ2a, and mark the edema proportion corresponding to the image acquisition cycle Tp2 as φ2b;

[0092] Sb-203, measure the growth rate ψ of the edema proportion φ2 corresponding to two adjacent image acquisition cycles: , and through the pig limb images corresponding to N2 image acquisition cycles Tp, successively measure the growth rates of the edema proportions corresponding to two image acquisition cycles, so as to obtain M2 growth rates ψ of the edema proportions, where, ;

[0093] Calculate the average value through the M2 growth rates ψ of the edema proportions to obtain the average edema growth rate Ψr: , and then calculate the standard deviation to obtain the edema change coefficient σr: ;

[0094] Sb-3, combine the average edema growth rate Ψr and the edema change coefficient σr to obtain the tissue risk assessment coefficient Xzh: ;

[0095] Among them, μ1 and μ2 are the weight factor coefficients of the average edema growth rate Ψr and the edema change coefficient σr respectively, and both μ1 and μ2 are greater than 0; when the average edema growth rate Ψr and the edema change coefficient σr are higher, the tissue risk assessment coefficient Xzh is higher, indicating that the edema growth trend is more obvious and the floating change degree is higher, and the tissue edema risk degree is higher, which will make the symptoms of classical swine fever more serious and the suspected degree of classical swine fever virus infection higher;

[0096] Sc, establish a comprehensive analysis sub-model through the classical swine fever risk assessment module, combine the vascular risk degree and the tissue edema degree, comprehensively evaluate the suspected degree of classical swine fever to obtain the image detection result of classical swine fever virus, so as to assist in the diagnosis of classical swine fever virus detection. The specific process of establishing the comprehensive analysis sub-model is as follows:

[0097] Sc-1, construct the change curve s1 between the vascular risk assessment coefficient Xxg and the image acquisition period Tp;

[0098] Construct the change curve s2 between the tissue risk assessment coefficient Xzh and the image acquisition period Tp;

[0099] Synchronously extract M3 points of the change curve s1 and the change curve s2, and establish the risk parameter matrix V:

[0100] ;

[0101] Sc-2, by taking the mean of the column vectors of the risk parameter matrix V, obtain the overall risk index va, and then calculate the variance of the column vectors to obtain the risk fluctuation index vb. Then, combine the overall risk index va and the risk fluctuation index vb to obtain the risk factor υ;

[0102] Among them, the overall risk index va1 of the vascular risk assessment coefficient Xxg: ; The risk fluctuation index vb1 of the vascular risk assessment coefficient Xxg: ; Then the risk factor υ1 of the vascular risk assessment coefficient Xxg: , set ρ １１ and ρ １２ are the weight factor coefficients of the overall risk index va1 and the risk fluctuation index vb1 respectively, and ρ １１ and ρ １２ are both greater than 0;

[0103] The overall risk index va2 of the tissue risk assessment coefficient Xzh: ; The risk fluctuation index vb2 of the tissue risk assessment coefficient Xzh: ; Then the risk factor υ2 of the tissue risk assessment coefficient Xzh: , set ρ ２１ and ρ ２２They are the weight factor coefficients of the overall risk index va2 and the risk volatility index vb2, respectively, and ρ ２１ and ρ ２２ are both greater than 0;

[0104] Sc-3, by combining the risk factor υ1 of the vascular risk assessment coefficient Xxg and the risk factor υ2 of the tissue risk assessment coefficient Xzh, the suspected classical swine fever reference index Zw is obtained: ;

[0105] Among them, ε1 and ε2 are set as the weight factor coefficients of the risk factor υ1 and the risk factor υ2 respectively, and both ε1 and ε2 are greater than 0; when the risk factor υ1 of the vascular risk assessment coefficient Xxg and the risk factor υ2 of the tissue risk assessment coefficient Xzh are higher, the suspected classical swine fever reference index Zw is higher, and thus the suspected degree of classical swine fever is higher;

[0106] Set the determination interval Qw of the suspected classical swine fever reference index Zw. When the suspected classical swine fever reference index Zw is within the determination interval Qw, it is determined that the image detection result is infected with the classical swine fever virus; otherwise, it is determined that the image detection result is not infected with the classical swine fever virus, and the image detection result and the suspected classical swine fever reference index Zw are sent to the live pig breeding management background for professional managers to assist in the diagnosis of classical swine fever virus detection;

[0107] Sd, obtain the biological detection result of the classical swine fever virus through the comparison and optimization module, and feedback it to the image analysis model for comparison with the image detection result to determine the detection accuracy of the image analysis model, and thus continuously optimize the image analysis model. The specific optimization process of the image analysis model is as follows:

[0108] Sd-1, mark the total amount of live pigs as ZT, set the sampling ratio q%, and obtain the live pig sample size YB: , select YB live pig samples by random sampling, and conduct biological detection on the live pig samples to determine whether they are infected with the classical swine fever virus, and set the biological detection value Ja;

[0109] If the biological detection result is infected with the classical swine fever virus, let the biological detection value Ja = 1;

[0110] If the biological detection result is not infected with the classical swine fever virus, let the biological detection value Ja = 0;

[0111] Sd-2, set the image detection value Pa;

[0112] When the image detection result is infected with the classical swine fever virus, let the image detection value Pa = 1;

[0113] When the image detection result is not infected with the classical swine fever virus, let the image detection value Pa = 0;

[0114] Sd-3, compare the biological detection value Ja and the image detection value Pa to obtain the detection deviation coefficient JP: ;

[0115] When the biological detection value Ja and the image detection value Pa are different, it means that there is a deviation in the image detection result; on the contrary, when the biological detection value Ja and the image detection value Pa are the same, it means that the image detection result is correct; by comparing the detection results of YB pig samples, the detection accuracy of the image analysis model is cumulatively measured and evaluated;

[0116] Sd-4, set the evaluation interval of the detection deviation coefficient JP, and evaluate the detection accuracy of the image analysis model through interval comparison;

[0117] There are u evaluation intervals of the preset detection deviation coefficient JP, and any evaluation interval is marked as Qu. When the detection deviation coefficient JP is in the evaluation interval Qu, the detection accuracy of the evaluation image analysis model is u level. When the detection deviation coefficient JP is higher, the detection accuracy of the evaluation image analysis model is lower.

[0118] When the detection accuracy level of the image analysis model is u, the correction amplitude Fu% of the image analysis model is set, and the preset parameters of the image analysis model are adjusted by the correction amplitude Fu%;

[0119] Among them, the prediction parameters of the image analysis model include weight factor coefficients ε1 and ε2. When the image detection value Pa=1 and the biological detection value Ja=0, it means that the image detection value Pa is too large, which means that the suspected reference index Zw of swine fever is too large. In this case, the weight factor coefficients ε1 and ε2 need to be reduced. The adjusted weight factor coefficients are marked as ε1t and ε2t respectively. , , by correcting the preset parameters with corresponding amplitudes, the model fitting accuracy is continuously improved, thereby improving the detection accuracy of the image analysis model;

[0120] S3, the disease monitoring unit conducts long-term monitoring of the classical swine fever virus: by regularly monitoring the image detection results of the classical swine fever virus, analyzing the long-term development status of the classical swine fever virus, assessing the health risk level of sick pigs, generating a health management plan for sick pigs and providing corresponding risk warnings. The specific process is as follows:

[0121] When both the image detection result and the biological detection result of classical swine fever virus are infected with classical swine fever virus, the live pig sample is marked as a sick pig, the number of sick pigs is marked as BZ, the classical swine fever suspected reference index Zw corresponding to the image detection result of the sick pig is extracted, and the image detection result of classical swine fever virus is monitored regularly to analyze the long-term development status of classical swine fever virus in the sick pig;

[0122] Set the virus monitoring period Td. With the suspected classical swine fever reference index Zw as the ordinate and the virus monitoring period Td as the abscissa, construct a change curve sd between the suspected classical swine fever reference index Zw and the virus monitoring period Td. Extract n3 points and their coordinates on the change curve sd, measure and obtain the slope values corresponding to the n3 points, and mark the slope value of any point as Kpo;

[0123] Among them, the calculation method of the slope Kpo refers to the growth rate ψ calculation formula and is calculated through the coordinates of adjacent points on the change curve sd;

[0124] Calculate the average value through the slope values Kpo of the n3 points to obtain the curve growth rate Ψs of the change curve sd, and then calculate the standard deviation through the slope values Kpo of the n3 points to obtain the curvature fluctuation coefficient σs of the change curve sd;

[0125] When the slope value Kpo of any point = 0, then determine that this point is a marked point, and obtain the slope value of the point corresponding to the next period after the marked point and mark it as Kpj. If the slope value Kpj is greater than 0, it means that it shows an upward trend after the marked point, and determine that this marked point is a valley point; if the slope value Kpj is less than 0, it means that it shows a downward trend after the marked point, and determine that this marked point is a peak point;

[0126] Mark the marked point closest to the end of the change curve sd as Yz, extract the curve segment between the marked point Yz and the end point of the change curve sd and mark it as sz, mark the coordinates of the marked point Yz as (Xz, Yz), mark the coordinates of the end point of the change curve sd as (Xm, Ym), and analyze the drop value Lz and the change rate Kz of the curve segment sz;

[0127] Among them, the drop value Lz: ; The change rate Kz: ;

[0128] If the marked point is a peak point, then mark this peak point as POf, mark the ordinate of the peak point POf as Yf, extract the curve segment between the peak point POf and the end point of the change curve sd and mark it as sf, then the change rate Kz of the curve segment sf is negative, indicating that the curve segment sf shows a downward trend, indicating that the classical swine fever virus of the sick pig is decreasing and the health level is recovering; when the drop value Lz of the curve segment sf is higher, it means that the recovery degree of the health state of the sick pig is higher;

[0129] If the marked point is a valley point, then mark this valley point as POg, mark the ordinate of the valley point POg as Yg, extract the curve segment between the valley point POg and the end point of the change curve sd and mark it as sg. Then the change rate Kz of the curve segment sg is positive, indicating that the curve segment sg shows an upward trend, representing that the suspected classical swine fever reference index Zw of the sick pig is on the rise. This shows that the classical swine fever virus of the sick pig is increasing and the physical condition is deteriorating. When the drop value Lz of the curve segment sg is higher, it indicates that the degree of deterioration of the physical condition of the sick pig is higher.

[0130] By combining the curve growth rate Ψs and the curvature fluctuation coefficient σs of the change curve sd, as well as the drop value Lz and the change rate Kz of the curve segment sz, obtain the health risk index Zjk of the sick pig:

[0131] ;

[0132] Among them, by combining the curve growth rate Ψs and the curvature fluctuation coefficient σs of the change curve sd, analyze the overall level of health risk. When the curve growth rate Ψs and the curvature fluctuation coefficient σs of the change curve sd are higher, it indicates that the overall level of classical swine fever virus risk is high and the fluctuation range is large, indicating that the virus state is active and unstable. Then, through the drop value Lz and the change rate Kz of the curve segment sz, analyze the current change of health risk. When the drop value Lz and the change rate Kz of the curve segment sz are positive and higher, it indicates that the current risk change of classical swine fever virus shows a gradually deteriorating state and the degree of deterioration is high. When the drop value Lz and the change rate Kz of the curve segment sz are negative and the absolute value is higher, it indicates that the current risk change of classical swine fever virus shows a gradually recovering state and the degree of recovery is high. Set δ1 and δ2 as the weight factor coefficients of the overall risk level and the current risk change respectively, and both δ1 and δ2 are greater than 0.

[0133] Set the evaluation interval of the health risk index Zjk of the sick pig, and evaluate the health risk degree of the sick pig through interval comparison. When the health risk index Zjk of the sick pig is higher, the health risk degree of the sick pig is higher.

[0134] Preset the evaluation interval of the health risk index Zjk of the sick pig as [Qj1, Qj2]. When the health risk index Zjk of the sick pig is lower than Qj1, it is determined that the health risk degree of the sick pig is mild. When the health risk index Zjk of the sick pig is within the evaluation interval [Qj1, Qj2], it is determined that the health risk degree of the sick pig is moderate. When the health risk index Zjk of the sick pig is higher than Qj2, it is determined that the health risk degree of the sick pig is severe.

[0135] Generate corresponding health management plans for sick pigs according to the health risk degree and give risk warnings.

[0136] When the health risk level of diseased pigs is mild, a Level-I diseased pig health management plan and a first risk warning signal are generated; when the health risk level of diseased pigs is moderate, a Level-II diseased pig health management plan and a second risk warning signal are generated; when the health risk level of diseased pigs is severe, a Level-III diseased pig health management plan and a third risk warning signal are generated;

[0137] Among them, the diseased pig health management plan is preset by breeding managers according to the health risk level of diseased pigs. For example, the Level-I diseased pig health management plan applies enhanced immunization measures, conducts secondary or booster vaccinations, enhances the immune response, provides easily digestible and nutritious feed, and improves the physical resistance of diseased pigs; the Level-II diseased pig health management plan uses appropriate drugs for symptomatic treatment according to the doctor's diagnosis and uses drugs to relieve the discomfort symptoms of diseased pigs; the Level-III diseased pig health management plan comprehensively implements the Level-I diseased pig health management plan and the Level-II diseased pig health management plan;

[0138] Thus, for diseased pigs that may be infected with classical swine fever virus during the pig breeding process, different levels of treatment and control are carried out, the efficiency of diseased pig health management is improved, thereby enhancing the targeted treatment effect of diseased pigs, inhibiting the further deterioration and spread of classical swine fever virus, reducing pig breeding losses and management costs;

[0139] S4. The early warning management unit conducts a global analysis of virus risks: By comprehensively analyzing the virus risk level, the classical swine fever virus infection status of the pig breeding base is evaluated, a pig breeding management plan is generated and corresponding early warning management is carried out. The specific process is as follows:

[0140] By comprehensively analyzing the virus risk levels of all pigs in the pig breeding base, the classical swine fever virus infection index Zgr is obtained: ;

[0141] The higher the proportion of the detected number of diseased pigs BZ in the pig sample size YB, the higher the estimated number of diseased pigs extended to the total pig population ZT The higher; the higher the health risk index Zjk of diseased pigs, the higher the degree of deterioration of classical swine fever virus. Thus, the higher the classical swine fever virus infection index Zgr, and the more serious the evaluated classical swine fever virus infection status of the pig breeding base;

[0142] Set the evaluation interval of the classical swine fever virus infection index Zgr, and evaluate the classical swine fever virus infection degree of the pig breeding base through interval comparison. When the classical swine fever virus infection index Zgr is higher, the classical swine fever virus infection degree of the pig breeding base is higher;

[0143] The evaluation range of the preset classical swine fever virus infection index Zgr is [Qr1, Qr2]. When the classical swine fever virus infection index Zgr is lower than Qr1, the degree of classical swine fever virus infection is determined to be mild; when the classical swine fever virus infection index Zgr is within the evaluation range [Qr1, Qr2], the degree of classical swine fever virus infection is determined to be moderate; when the classical swine fever virus infection index Zgr is higher than Qr2, the degree of classical swine fever virus infection is determined to be severe;

[0144] Generate corresponding pig breeding management plans and conduct early warning management according to the classical swine fever virus infection status of the pig breeding base;

[0145] When the degree of classical swine fever virus infection is mild, generate a Grade I pig breeding management plan and a No. 1 early warning management signal; when the degree of classical swine fever virus infection is moderate, generate a Grade II pig breeding management plan and a No. 2 early warning management signal; when the degree of classical swine fever virus infection is severe, generate a Grade III pig breeding management plan and a No. 3 early warning management signal;

[0146] Among them, the pig breeding management plan is preset by the breeding management personnel according to the classical swine fever virus infection status of the pig breeding base. For example, the Grade I pig breeding management plan implements preventive measures, including regularly vaccinating the pig herd against classical swine fever to enhance immunity, regularly checking the health status of the pig herd to detect suspected cases early, maintaining the breeding environment hygiene, and regularly disinfecting feed, utensils, and vehicles; the Grade II pig breeding management plan conducts emergency responses. For sudden epidemics, formulate clear emergency treatment procedures, isolate and observe suspected infected pigs to prevent transmission, thoroughly clean and disinfect the breeding area to eliminate potential viruses; the Grade III pig breeding management plan conducts disease treatment, uses drugs for treatment to detect their health status, control the degree of disease deterioration, and harmless treatment of dead pigs, and strictly handle dead pigs according to regulations, such as incineration and burial, to avoid virus spread;

[0147] Thus, different levels of unified control are carried out on the overall classical swine fever virus infection situation of the pig breeding base, improving the early warning management efficiency of the pig breeding base, thereby inhibiting the further deterioration and spread of the classical swine fever virus, reducing pig breeding losses and management costs.

[0148] In summary, the present invention remotely collects pig limb images and sends them to the cloud for data processing, reducing the demand for manual sampling, constructing an image analysis model to evaluate the suspected degree of classical swine fever virus infection, improving the work efficiency of virus detection, comparing and testing the accuracy of the image analysis model through sampling biological detection, thereby continuously optimizing the image analysis model, improving the accuracy of virus detection, significantly reducing the trend of virus infection and spread, and effectively curbing the continuous deterioration of the classical swine fever epidemic;

[0149] The present invention collects the limb images of live pigs through an image acquisition unit, and constructs an image analysis model through a data processing cloud to analyze the limb images of live pigs, comprehensively evaluate the suspected degree of swine fever risk from two perspectives of vascular risk and tissue edema, so as to assist in the diagnosis of swine fever virus detection; and then monitors the swine fever virus for a long time through a disease monitoring unit, analyzes the deterioration or recovery of the condition of diseased pigs, generates a health management plan for diseased pigs, so as to perform corresponding health management according to the degree of health risk of diseased pigs, and improve the targeted treatment effect of diseased pigs;

[0150] The present invention globally analyzes the virus risk through an early warning management unit, generates a live pig breeding management plan, so as to perform corresponding overall control according to the infection degree of swine fever virus in a live pig breeding base, improve the early warning management efficiency of the live pig breeding base, and reduce the losses and management costs of live pig breeding.

[0151] The setting of the size of the interval and threshold is for the convenience of comparison. Regarding the size of the threshold, it depends on the amount of sample data and the number of base numbers set by those skilled in the art for each group of sample data; as long as the proportional relationship between the parameter and the quantified value is not affected.

[0152] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by software simulation of a large amount of collected data to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation;

[0153] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A classical swine fever virus detection system based on cloud analysis, characterized in that: It includes an image acquisition unit, a data processing cloud, a disease monitoring unit, and an early warning management unit. Among them, the image acquisition unit, the data processing cloud, the disease monitoring unit, and the early warning management unit are communicatively connected; The image acquisition unit is used to acquire the limb images of live pigs: Set the image acquisition period Tp. By binding the wearable device to the limb part of the live pig, an infrared image acquisition instrument is set in the wearable device, and the infrared image acquisition instrument is used to regularly acquire the limb images of the live pig, and then the limb images of the live pig are transmitted to the data processing cloud through remote signals; The data processing cloud is used to build an image analysis model to analyze the limb images of live pigs: The data processing cloud includes a vascular risk analysis module, a tissue edema analysis module, a classical swine fever risk assessment module, and a comparison and optimization module; The blood flow condition of the limb blood vessels is analyzed through the vascular risk analysis module to evaluate the degree of vascular risk; the tissue edema condition of the limb part is analyzed through the tissue edema analysis module to evaluate the degree of tissue edema; the classical swine fever risk assessment module combines the degree of vascular risk with the degree of tissue edema to comprehensively evaluate the suspected degree of classical swine fever and obtain the image detection result of classical swine fever virus, so as to assist in the diagnosis of classical swine fever virus detection; the comparison and optimization module obtains the biological detection result of classical swine fever virus and feeds it back to the image analysis model for comparison with the image detection result to determine the detection accuracy of the image analysis model, so as to continuously optimize the image analysis model; The disease monitoring unit is used to monitor the classical swine fever virus for a long time: By regularly monitoring the image detection result of the classical swine fever virus, analyze the long-term development state of the classical swine fever virus, evaluate the health risk degree of the diseased pigs, generate a health management plan for the diseased pigs and give corresponding risk warnings; The early warning management unit is used to conduct a global analysis of the virus risk: By comprehensively analyzing the degree of virus risk, evaluate the infection state of classical swine fever virus in the live pig breeding base, generate a live pig breeding management plan and conduct corresponding early warning management.

2. The hog cholera virus detection system based on cloud analysis according to claim 1, characterized in that: The specific construction process of the image analysis model is as follows: The image analysis model includes a vascular analysis sub-model, a tissue analysis sub-model, and a comprehensive analysis sub-model; Sa. Establish a vascular analysis sub-model through the vascular risk analysis module to analyze the blood flow condition of the limb blood vessels and evaluate the degree of vascular risk; Sb. Establish a tissue analysis sub-model through the tissue edema analysis module to analyze the tissue edema condition of the limb part and evaluate the degree of tissue edema; Sc. Establish a comprehensive analysis sub-model through the classical swine fever risk assessment module, combine the degree of vascular risk with the degree of tissue edema, comprehensively evaluate the suspected degree of classical swine fever and obtain the image detection result of classical swine fever virus, so as to assist in the diagnosis of classical swine fever virus detection; Sd. Obtain the biological detection result of classical swine fever virus through the comparison and optimization module and feed it back to the image analysis model for comparison with the image detection result to determine the detection accuracy of the image analysis model, so as to continuously optimize the image analysis model.

3. The swine fever virus detection system based on cloud analysis according to claim 2, wherein: The specific process of establishing the vascular analysis sub-model is as follows: Sa-1. Input the limb image of the live pig into the vascular analysis sub-model; Extract N0 pixel points of the limb image of the live pig and perform gray-scale acquisition, and mark the gray-scale value of any pixel point i as HDi; Set the gray - scale interval Qh of blood vessels, extract the pixel points whose gray - scale values HDi are within the gray - scale interval Qh, and integrate them into a blood - vessel feature - point set. Mark the area where the blood - vessel feature - point set is located as the blood - vessel area; Divide the blood - vessel area into N1 characteristic regions and conduct regional - state analysis. Mark any one of the characteristic regions as J, and measure the gray - scale mean value η1 of n0 pixel points in the characteristic region J; Set the gray - scale interval Qη for regional infarction. When the gray - scale mean value η1 of the characteristic region J is within the gray - scale interval Qη, mark this characteristic region as the infarction area; otherwise, mark this characteristic region as the blood - flow area; Sa - 2. Conduct targeted analysis on the infarction area and the blood - flow area respectively. The specific process is as follows: Sa - 201. Analyze the infarction area: Obtain the infarction proportion η2 by measuring the proportion of all infarction areas in the blood - vessel area; Sa - 202. Analyze the blood - flow area: Extract the pig - limb images corresponding to N2 image - acquisition cycles Tp, and construct a dynamic curve S0 between the gray - scale mean value η1 of the blood - flow area and the image - acquisition cycle Tp. Obtain the pumping cycle Tb and the pumping intensity Db through the dynamic curve S0; Sa - 3. Combine the infarction proportion η2, the pumping cycle Tb, and the pumping intensity Db to obtain the blood - vessel risk - assessment coefficient Xxg.

4. The swine fever virus detection system based on cloud analysis according to claim 3, wherein: The specific process of establishing the tissue - analysis sub - model is as follows: Sb - 1. Extract the pixel points whose gray - scale values HDi of the pig - limb image are not within the gray - scale interval Qh, and mark the area where these pixel points are located as the tissue area; Sb - 2. Divide the tissue area into M1 characteristic regions and conduct regional - state analysis. Mark any one of the characteristic regions as R, and measure the gray - scale mean value φ1 of m0 pixel points in the characteristic region R; Sb - 201. Set the gray - scale interval Qs for regional edema. If the gray - scale mean value φ1 of the characteristic region R is within the gray - scale interval Qs, mark this characteristic region as the edema area; Sb - 202. Obtain the edema proportion φ2 by cumulatively measuring the proportion of all edema areas in the tissue area. Extract the pig - limb images corresponding to N2 image - acquisition cycles Tp, and obtain the edema proportion of the pig - limb images corresponding to N2 image - acquisition cycles Tp; Sb - 203. Obtain the edema - proportion growth rate ψ through the edema proportion φ2 corresponding to two adjacent image - acquisition cycles, and further obtain the average edema - growth rate Ψr and the edema - change coefficient σr; Sb - 3. Combine the average edema - growth rate Ψr and the edema - change coefficient σr to obtain the tissue - risk - assessment coefficient Xzh.

5. The hog cholera virus detection system based on cloud analysis according to claim 4, wherein: The specific process of establishing the comprehensive - analysis sub - model is as follows: Sc - 1. Construct a change curve s1 between the blood - vessel risk - assessment coefficient Xxg and the image - acquisition cycle Tp, and a change curve s2 between the tissue - risk - assessment coefficient Xzh and the image - acquisition cycle Tp; Synchronously extract M3 points of the change curve s1 and the change curve s2 to establish a risk - parameter matrix V; Sc - 2. Obtain the overall risk index va and the risk - fluctuation index vb from the risk - parameter matrix V, and further obtain the risk factor υ. Mark the risk factors of the blood - vessel risk - assessment coefficient Xxg and the tissue - risk - assessment coefficient Xzh as υ1 and υ2 respectively; Sc-3, combine the risk factor υ1 of the vascular risk assessment coefficient Xxg and the risk factor υ2 of the tissue risk assessment coefficient Xzh to obtain the suspected classical swine fever reference index Zw; Set the determination interval Qw of the suspected classical swine fever reference index Zw. When the suspected classical swine fever reference index Zw is within the determination interval Qw, it is determined that the image detection result is infected with the classical swine fever virus; otherwise, it is determined that the image detection result is not infected with the classical swine fever virus.

6. The hog cholera virus detection system based on cloud analysis according to claim 5, wherein: The specific optimization process of the image analysis model is as follows: Sd-1, mark the total number of live pigs as ZT, set the sampling ratio q%, obtain the live pig sample size YB, select YB live pig samples by random sampling, and conduct biological tests on the live pig samples to obtain the biological test results. Set the biological test value Ja and assign values to the biological test value Ja according to the biological test results; Sd-2, set the image detection value Pa and assign values to the image detection value Pa according to the image detection results; Sd-3, compare the biological test value Ja and the image detection value Pa to obtain the detection deviation coefficient JP; Sd-4, set the evaluation interval of the detection deviation coefficient JP, evaluate the detection accuracy of the image analysis model through interval comparison, and then set the correction amplitude of the image analysis model to optimize and adjust the image analysis model.

7. The hog cholera virus detection system based on cloud analysis according to claim 6, characterized in that: The specific process of long-term monitoring of the classical swine fever virus is as follows: When both the image detection result and the biological test result of the classical swine fever virus are positive for the classical swine fever virus, mark the live pig sample as a diseased pig, mark the number of diseased pigs as BZ, and extract the suspected classical swine fever reference index Zw corresponding to the image detection result of the diseased pig; Set the virus monitoring period Td, construct the change curve sd between the suspected classical swine fever reference index Zw and the virus monitoring period Td, extract n3 points and their coordinates on the change curve sd, calculate the slope values corresponding to the n3 points, and obtain the curve growth rate Ψs and the curvature fluctuation coefficient σs of the change curve sd; When the slope value Kpo = 0 at any point, determine that the point is a marked point, extract the curve segment sz between the marked point Yz and the end point of the change curve sd, and obtain the drop value Lz and the change rate Kz of the curve segment sz; Furthermore, comprehensively obtain the health risk index Zjk of the diseased pigs, set the evaluation interval of the health risk index Zjk of the diseased pigs, evaluate the health risk degree of the diseased pigs through interval comparison, generate the corresponding health management plan for the diseased pigs and give risk warnings.

8. The classical swine fever virus detection system based on cloud analysis according to claim 7, wherein: The specific process of global analysis of the virus risk is as follows: Obtain the estimated number of diseased pigs in the total number of live pigs ZT by the proportion of the number of diseased pigs BZ detected in the live pig sample size YB, and combine the health risk index Zjk of the diseased pigs to conduct an overall analysis of the virus risk degree of all the live pigs in the live pig breeding base to obtain the classical swine fever virus infection index Zgr; Set the evaluation interval of the classical swine fever virus infection index Zgr, evaluate the classical swine fever virus infection degree of the live pig breeding base through interval comparison, generate the corresponding live pig breeding management plan and conduct early warning management.

Images