A regional animal epidemic prevention system evaluation method and system based on big data

Through the combination of Bayesian network and random forest algorithm, the challenges of data types diversity and intelligent management in regional animal epidemic prevention system evaluation have been solved, automated and intelligent evaluation have been realized, and the efficiency and accuracy of epidemic prevention capabilities have been improved. .

CN118626965BActive Publication Date: 2024-11-12江西省农业技术推广中心
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411103223.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-12
Estimated Expiration
2044-08-13

AI Technical Summary

Technical Problem

The existing technology cannot effectively conduct automated and intelligent regional animal epidemic prevention system evaluation, and cannot meet the needs of intelligent management, especially in the joint analysis of structured, unstructured and semi-structured data.

Method used

The Bayesian network algorithm is used to analyze the correlation of animal epidemic prevention system data, screen key data, and grading epidemic prevention capabilities through a random forest classification algorithm, and publish data in combination with a visual human-computer interaction platform to achieve automated and intelligent evaluation.

Benefits of technology

The efficiency and accuracy of classification of epidemic prevention capabilities have been improved, and an automatic and intelligent regional animal epidemic prevention system evaluation has been achieved, greatly improving the efficiency and accuracy of the evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118626965B_ABST
    Figure CN118626965B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of big data decision-making and evaluation, and proposes a regional animal epidemic prevention system evaluation method and system based on big data. The method uses a Bayesian network algorithm to perform correlation analysis on comprehensive data of the animal epidemic prevention system in a region, screens out non-critical data, and connects data of different modes and different data types, thereby avoiding the problem of unclear data categories when the epidemic prevention capability is subsequently classified according to a preset animal epidemic prevention capability classification standard, thereby improving the efficiency and accuracy of epidemic prevention capability classification, and then uses a random forest classification algorithm to perform epidemic prevention capability classification, automatically and accurately evaluates the epidemic prevention capability in a region, and uploads the evaluation results and data to a visual human-computer interaction platform for data publication, thereby realizing automatic and intelligent regional animal epidemic prevention system evaluation, and greatly improving the efficiency and accuracy of regional animal epidemic prevention system evaluation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of big data decision-making evaluation, and in particular to a regional animal epidemic prevention system evaluation method and system based on big data. Background Art

[0002] With the rapid development of animal husbandry, regionalized management of animal epidemic prevention has gradually become an indispensable part of the animal husbandry and veterinary industry. Therefore, evaluating the regionalized management of animal epidemic prevention, evaluating the development trend of animal epidemics, and carrying out targeted prevention and control work have naturally become important goals of animal husbandry and veterinary management.

[0003] In the prior art, the regional animal epidemic prevention system is usually evaluated by manual statistical data reclassification evaluation method. Because the epidemic prevention system data is complex, it cannot be processed separately for structured data or unstructured data, text data or image data. Instead, it is necessary to jointly analyze structured data, unstructured data and semi-structured data, and perform multi-mode processing on text data and image data. Therefore, the traditional manual statistical classification evaluation method is still unable to meet the requirements of increasingly intelligent animal epidemic prevention regional management.

[0004] Therefore, how to design a regional animal epidemic prevention system evaluation method to achieve automated and intelligent regional animal epidemic prevention system evaluation has become an urgent problem to be solved. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide a regional animal epidemic prevention system evaluation method and system based on big data, which uses a Bayesian network algorithm to perform correlation analysis on the comprehensive data of the animal epidemic prevention system in the region, screens out non-critical data, and connects data of different modes and different data types, thereby avoiding the problem of unclear data categories when the epidemic prevention capability is subsequently classified according to the preset animal epidemic prevention capability classification standard, thereby improving the efficiency and accuracy of epidemic prevention capability classification, and then uses a random forest classification algorithm to perform epidemic prevention capability classification, automatically and accurately evaluate the epidemic prevention capability in the region, and upload the evaluation results and data to a visual human-computer interaction platform for data publication, thereby realizing automatic and intelligent regional animal epidemic prevention system evaluation, and greatly improving the efficiency and accuracy of regional animal epidemic prevention system evaluation.

[0006] The present invention proposes a method for evaluating a regional animal epidemic prevention system based on big data, comprising:

[0007] Collect and pre-process the comprehensive data of the animal epidemic prevention system in the region to build an animal epidemic prevention system database;

[0008] Calling the pre-processed comprehensive data of the animal epidemic prevention system in the animal epidemic prevention system database, and performing a correlation analysis on the pre-processed comprehensive data of the animal epidemic prevention system according to a Bayesian network algorithm, so as to screen and obtain key data of the animal epidemic prevention system;

[0009] Classify the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system;

[0010] Classifying the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data;

[0011] Upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data release.

[0012] In summary, according to the above-mentioned regional animal epidemic prevention system evaluation method based on big data, the Bayesian network algorithm is used to perform correlation analysis on the comprehensive data of the animal epidemic prevention system in the region. While screening out non-critical data, the data of different modes and different data types are linked, avoiding the problem of unclear data categories when the epidemic prevention capacity is subsequently classified according to the preset animal epidemic prevention capacity classification standards, thereby improving the efficiency and accuracy of epidemic prevention capacity classification, and then using the random forest classification algorithm to perform epidemic prevention capacity classification, automatically and accurately evaluate the epidemic prevention capacity in the region, and upload the evaluation results and data to the visual human-computer interaction platform for data publication, realizing automatic and intelligent regional animal epidemic prevention system evaluation, greatly improving the efficiency and accuracy of regional animal epidemic prevention system evaluation. Specifically, the comprehensive data of the animal epidemic prevention system in the area is collected and preprocessed to build an animal epidemic prevention system database, the quality of the data is preliminarily processed, the efficiency and accuracy of subsequent classification and grading operations are improved, the preprocessed comprehensive data of the animal epidemic prevention system in the animal epidemic prevention system database is called, and the preprocessed comprehensive data of the animal epidemic prevention system is analyzed for correlation according to the Bayesian network algorithm to screen and obtain the key data of the animal epidemic prevention system, and while filtering out non-critical data, data of different modes and different data types are linked to avoid the problem of unclear data categories when the epidemic prevention capacity is subsequently classified according to the preset animal epidemic prevention capacity classification standard. The problem is solved, thereby improving the efficiency and accuracy of epidemic prevention capability classification. The key data of the animal epidemic prevention system are classified according to the preset animal epidemic prevention capability classification standards to obtain multi-category animal epidemic prevention system key data. The multi-category animal epidemic prevention system key data are graded according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data, and the epidemic prevention capabilities in the region are automatically and accurately evaluated. The multi-level animal epidemic prevention system key data are uploaded to the visual human-computer interaction platform to complete the data publication, thereby realizing automatic and intelligent regional animal epidemic prevention system evaluation, which greatly improves the efficiency and accuracy of regional animal epidemic prevention system evaluation.

[0013] Furthermore, the step of collecting the comprehensive data of the animal epidemic prevention system in the area and preprocessing it to build an animal epidemic prevention system database specifically includes:

[0014] Collect comprehensive data on the animal epidemic prevention system in the region, including data on compulsory immunization for major animal diseases, animal disease monitoring and epidemiological survey data, animal epidemic emergency response data, animal health supervision and management data, livestock and poultry slaughtering industry management data, major animal disease regional prevention and control data, and veterinary system core capacity building data;

[0015] Performing data integrity judgment on the comprehensive data of the animal epidemic prevention system. If it is determined that the comprehensive data of the animal epidemic prevention system is missing, locating the missing data value of the comprehensive data of the animal epidemic prevention system, performing interpolation processing on the comprehensive data of the animal epidemic prevention system to replace the missing data value, and performing data integrity judgment again;

[0016] If it is determined that the comprehensive data of the animal epidemic prevention system is in a complete state, then a data outlier judgment is performed on the comprehensive data of the animal epidemic prevention system; if it is determined that the comprehensive data of the animal epidemic prevention system has a data outlier, then the data outlier of the comprehensive data of the animal epidemic prevention system is located, and an outlier conversion process is performed on the comprehensive data of the animal epidemic prevention system to replace the data outlier, and the data outlier judgment is performed again;

[0017] If it is determined that the comprehensive data of the animal epidemic prevention system does not contain data abnormal values, then the comprehensive data of the animal epidemic prevention system is judged to have duplicate values; if it is determined that the comprehensive data of the animal epidemic prevention system has data duplicate values, then the data duplicate values ​​of the comprehensive data of the animal epidemic prevention system are located, and the comprehensive data of the animal epidemic prevention system is sorted and de-duplicated to delete the data duplicate values, and then the duplicate value judgment is performed again;

[0018] If it is determined that the comprehensive data of the animal epidemic prevention system does not have duplicate values, the comprehensive data of the animal epidemic prevention system is standardized to construct an animal epidemic prevention system database.

[0019] Furthermore, the step of calling the pre-processed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database and performing a correlation analysis on the pre-processed animal epidemic prevention system comprehensive data according to the Bayesian network algorithm to screen and obtain key data of the animal epidemic prevention system specifically includes:

[0020] Calling the preprocessed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database, and dividing the preprocessed animal epidemic prevention system comprehensive data according to the data modality type to obtain text modality data and image modality data;

[0021] The text modality data is input into a text encoder to obtain text modality data features. The formula for obtaining text modality data features is as follows:

[0022]

[0023] in, Represents the text modality data features, , represents the feature dimension, represents the fully connected layer, represents a text encoder, Represents text modal data, Indicates the data ordinal number;

[0024] The image modality data is input into the convolution module to obtain the image modality data features. The formula for obtaining the image modality data features is as follows:

[0025]

[0026] in, Represents the image modality data features, represents the dimension conversion function, represents the convolution kernel, Represents image modality data;

[0027] The text modality data features and the image modality data features are input into a Bayesian network to obtain the data correlation between different modality data and the correlation between single modality data features and key data features. The algorithm of the Bayesian network is as follows:

[0028]

[0029]

[0030]

[0031] in, Indicates data association. Represents key data characteristics, represents the probability function;

[0032] Key data is screened based on the data correlation to obtain key data of the animal epidemic prevention system.

[0033] Furthermore, the step of classifying the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system specifically includes:

[0034] Extract the veterinary work institution data, veterinary staff quantity data, veterinary staff professional ability data, veterinary staff continuing education data, veterinary work institution funding data, veterinary work institution office facilities and equipment data, and veterinary work institution professional facilities and equipment data from the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capacity classification standards, so as to divide the human, financial and material resource allocation capacity data;

[0035] According to the preset animal epidemic prevention capacity classification standards, the veterinary work agency administrative regulations enforcement data, veterinary work agency daily management data, veterinary work agency emergency management data, veterinary work agency coordination management data, veterinary work agency risk warning data and veterinary work agency service data in the key data of the animal epidemic prevention system are extracted to divide the administrative management capacity data;

[0036] According to the preset animal epidemic prevention capacity classification standards, animal health supervision data, animal quarantine data, quarantine supervision and law enforcement connection data, harmless disposal supervision data of dead livestock and poultry, and identification and traceability data are extracted from the key data of the animal epidemic prevention system to divide the supervision and quarantine capacity data;

[0037] According to the preset animal epidemic prevention capacity classification standards, animal disease monitoring and epidemiological survey data, veterinary laboratory testing and diagnosis data, veterinary laboratory quality assurance data, animal epidemic report data and technical guidance and training data from the key data of the animal epidemic prevention system are extracted to divide the disease prevention and control capacity data;

[0038] The key data of the multi-category animal epidemic prevention system are obtained based on the human, financial and material resource allocation capability data, administrative management capability data, division of supervision and quarantine capability data and disease prevention and control capability data.

[0039] Furthermore, the step of grading the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data specifically includes:

[0040] Obtain the data characteristics of each type of epidemic prevention capability in the key data of multi-category animal epidemic prevention system and perform standardized processing;

[0041] Randomly select from the data features of each type of epidemic prevention capability K Cluster centers are obtained by dividing according to the K-MEANS clustering algorithm K A single epidemic prevention capability grading evaluation data set, the loss function of the K-MEANS clustering algorithm is as follows:

[0042]

[0043] in, Indicates loss, A sample representing the characteristics of the data, represents the cluster center, , represents the clustering judgment value, represents the sample ordinal number, represents the number of samples, K is a hyperparameter, represents the cluster center ordinal number, Represents the Euclidean distance from the data sample to the cluster center;

[0044] The K The single-item epidemic prevention capability grading evaluation data set is input into the corresponding K In the random forest classifiers, each of the random forest classifiers includes five classification judgment layers, and each of the classification judgment layers is respectively provided with a corresponding preset single epidemic prevention capability level standard;

[0045] The classification judgment layer divides the data in the corresponding single-item epidemic prevention capability grading assessment data set into first-level animal epidemic prevention system key data to fifth-level animal epidemic prevention system key data according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data.

[0046] Furthermore, the random forest classification algorithm specifically includes:

[0047] The single epidemic prevention capability hierarchical assessment data set is input into the classification judgment layer of the random forest classifier, and the classification judgment layer determines whether the single epidemic prevention capability hierarchical assessment data set meets the preset single epidemic prevention capability level standard of the current classification judgment layer;

[0048] If the single epidemic prevention capability hierarchical assessment data set meets the preset single epidemic prevention capability level standard of the current classification judgment layer, it is classified as key data of the animal epidemic prevention system of the corresponding level of the current classification judgment layer;

[0049] If the single epidemic prevention capability hierarchical assessment data set does not meet the preset single epidemic prevention capability level standard of the current classification judgment layer, the single epidemic prevention capability hierarchical assessment data set is sent to the next classification judgment layer;

[0050] The random forest classifier is defined as follows:

[0051]

[0052] in, Indicates the capability level of the final output, Represents the weight of each classification judgment layer, The output result of each classification judgment layer is Indicates the number of classification judgment layers, (1,2,3,4,5).

[0053] Furthermore, the step of uploading the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data publication specifically includes:

[0054] Upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform, which includes a regional distribution module, an assessment announcement module, and a trend analysis module;

[0055] The regional distribution module marks the location of animal disease discovery, the scope of animal disease impact and the location of the epidemic prevention agency on the map of the current area based on the key data of the multi-level animal epidemic prevention system;

[0056] The assessment and publication module publishes the assessment results of the epidemic prevention agencies marked by the regional distribution module according to the key data of the multi-level animal epidemic prevention system, and the assessment results include the epidemic prevention capability information of the epidemic prevention agencies and the level information of the corresponding epidemic prevention capabilities;

[0057] The trend analysis module produces epidemic data charts and epidemic prevention capacity charts based on key data of the multi-level animal epidemic prevention system, and conducts comparative analysis to publish comprehensive trend charts.

[0058] The present invention proposes a regional animal epidemic prevention system evaluation system based on big data, comprising:

[0059] The data collection module is used to collect and pre-process the comprehensive data of the animal epidemic prevention system in the region to build an animal epidemic prevention system database;

[0060] A correlation analysis module is used to call the pre-processed comprehensive data of the animal epidemic prevention system in the animal epidemic prevention system database, and perform correlation analysis on the pre-processed comprehensive data of the animal epidemic prevention system according to the Bayesian network algorithm to screen and obtain key data of the animal epidemic prevention system;

[0061] A capability classification module is used to classify the key data of the animal epidemic prevention system according to a preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system;

[0062] A capability grading module, used to grade the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to a random forest classification algorithm, so as to obtain multi-level animal epidemic prevention system key data;

[0063] The data interaction module is used to upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data publication.

[0064] The present invention also provides a storage medium, which stores one or more programs, and when the programs are executed by a processor, they implement the regional animal epidemic prevention system evaluation method based on big data as mentioned above.

[0065] The present invention also provides a computer device, the computer device comprising a memory and a processor, wherein:

[0066] The memory is used to store computer programs;

[0067] When the processor is used to execute the computer program stored in the memory, it implements the regional animal epidemic prevention system evaluation method based on big data as mentioned above. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A flowchart of a method for evaluating a regional animal epidemic prevention system based on big data proposed in the first embodiment of the present invention;

[0069] Figure 2 A flow chart of a method for evaluating a regional animal epidemic prevention system based on big data proposed in a second embodiment of the present invention;

[0070] Figure 3 This is a schematic diagram of the structure of a regional animal epidemic prevention system evaluation system based on big data proposed in the third embodiment of the present invention.

[0071] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0072] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0073] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0075] See also Figure 1 , which is a flow chart of a regional animal epidemic prevention system evaluation method based on big data proposed in the first embodiment of the present invention, and the regional animal epidemic prevention system evaluation method based on big data includes steps S01 to S05, wherein:

[0076] Step S01: Collecting and preprocessing the comprehensive data of the animal epidemic prevention system in the region to build an animal epidemic prevention system database;

[0077] It should be noted that in this embodiment, comprehensive data of the animal epidemic prevention system in the area is collected, and the comprehensive data of the animal epidemic prevention system includes comprehensive compulsory immunization data for major animal diseases, animal disease monitoring and epidemiological investigation data, animal epidemic emergency disposal data, animal health supervision management data, livestock and poultry slaughter industry management data, major animal disease zoning prevention and control data and veterinary system core capacity building data. In order to ensure the accuracy of subsequent classification and grading, it is necessary to judge the data quality before building the database. First, the data integrity of the comprehensive data of the animal epidemic prevention system is judged. If the comprehensive data of the animal epidemic prevention system is judged to be missing, the data missing values ​​of the comprehensive data of the animal epidemic prevention system are located, and the comprehensive data of the animal epidemic prevention system are interpolated to replace the data missing values, and the data integrity is judged again. If the comprehensive data of the animal epidemic prevention system is judged to be complete, the animal The comprehensive data of the animal epidemic prevention system is judged as data outliers. If it is determined that the comprehensive data of the animal epidemic prevention system has data outliers, the data outliers of the comprehensive data of the animal epidemic prevention system are located, and the comprehensive data of the animal epidemic prevention system is converted into outliers to replace the data outliers, and the data outlier judgment is performed again. If it is determined that the comprehensive data of the animal epidemic prevention system does not have data outliers, a duplicate value judgment is performed on the comprehensive data of the animal epidemic prevention system. If it is determined that the comprehensive data of the animal epidemic prevention system has data duplicate values, the data duplicate values ​​of the comprehensive data of the animal epidemic prevention system are located, and the comprehensive data of the animal epidemic prevention system is sorted and deduplicated to delete the data duplicate values, and the duplicate value judgment is performed again. If it is determined that the comprehensive data of the animal epidemic prevention system does not have duplicate values, the comprehensive data of the animal epidemic prevention system is standardized and an animal epidemic prevention system database is constructed.

[0078] Step S02: calling the pre-processed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database, and performing a correlation analysis on the pre-processed animal epidemic prevention system comprehensive data according to the Bayesian network algorithm to screen and obtain key data of the animal epidemic prevention system;

[0079] It should be noted that, in this embodiment, before performing correlation analysis on the preprocessed animal epidemic prevention system comprehensive data according to the Bayesian network algorithm, it is also necessary to extract features from data of different modalities. First, the preprocessed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database is called, and the preprocessed animal epidemic prevention system comprehensive data is divided according to the data modality type to obtain text modality data and image modality data, and the text modality data is input into a text encoder to obtain text modality data features. The formula for obtaining text modality data features is as follows:

[0080]

[0081] in, Represents the text modality data features, , represents the feature dimension, represents the fully connected layer, represents a text encoder, Represents text modal data, Represents the data ordinal number, and the image modality data is input into the convolution module to obtain the image modality data features. The formula for obtaining the image modality data features is as follows:

[0082]

[0083] in, Represents the image modality data features, represents the dimension conversion function, represents the convolution kernel, Representing image modality data, the text modality data features and the image modality data features are input into the Bayesian network to obtain the data correlation between different modality data and the correlation between single modality data features and key data features. The algorithm of the Bayesian network is as follows:

[0084]

[0085]

[0086]

[0087] in, Indicates data association. Represents key data characteristics, It represents a probability function, and performs key data screening according to the data correlation to obtain key data of the animal epidemic prevention system.

[0088] Step S03: classifying the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system;

[0089] It should be noted that the preset animal epidemic prevention capacity classification standard in the present embodiment is formulated according to the capacity classification in the "County-level Veterinary Institution Effectiveness Evaluation Index System". In the present embodiment, the epidemic prevention capacity classification is carried out. First, the veterinary work agency data, veterinary staff quantity data, veterinary staff professional capacity data, veterinary staff continuing education data, veterinary work agency funding data, veterinary work agency office facilities and equipment data and veterinary work agency professional facilities and equipment data in the key data of the animal epidemic prevention system are extracted according to the preset animal epidemic prevention capacity classification standard to divide the human, financial and material resource allocation capacity data. According to the preset animal epidemic prevention capacity classification standard, the veterinary work agency administrative regulations enforcement data, veterinary work agency daily management data, veterinary work agency emergency management data, veterinary work agency coordination management data, veterinary work The risk warning data of veterinary institutions and the service data of veterinary institutions are used to divide the administrative management capacity data. According to the preset animal epidemic prevention capacity classification standards, the animal health supervision data, animal quarantine data, quarantine supervision and law enforcement connection data, and the harmless disposal supervision data of dead livestock and poultry and identification and traceability data in the key data of the animal epidemic prevention system are extracted to divide the supervision and quarantine capacity data. According to the preset animal epidemic prevention capacity classification standards, the animal disease monitoring and epidemiological investigation data, veterinary laboratory testing and diagnosis data, veterinary laboratory quality assurance data, animal epidemic reporting data, and technical guidance and training data in the key data of the animal epidemic prevention system are extracted to divide the disease prevention and control capacity data. According to the human, financial and material resource allocation capacity data, administrative management capacity data, and the division of supervision and quarantine capacity data and disease prevention and control capacity data, multiple categories of animal epidemic prevention system key data are obtained.

[0090] Step S04: classifying the epidemic prevention capabilities of multiple categories of key data of animal epidemic prevention systems according to the random forest classification algorithm to obtain multi-level key data of animal epidemic prevention systems;

[0091] It should be noted that in this embodiment, the classification of epidemic prevention capabilities requires first obtaining the data characteristics of each type of epidemic prevention capability in the key data of the multi-category animal epidemic prevention system, and performing standardization processing. K Cluster centers are obtained by dividing according to the K-MEANS clustering algorithm K A single epidemic prevention capability grading evaluation data set, the loss function of the K-MEANS clustering algorithm is as follows:

[0092]

[0093] in, Indicates loss, A sample representing the characteristics of the data, represents the cluster center, , represents the clustering judgment value, represents the sample ordinal number, represents the number of samples, K is a hyperparameter, represents the cluster center ordinal number, Represents the Euclidean distance from the data sample to the cluster center. K The single-item epidemic prevention capability grading evaluation data set is input into the corresponding K In a random forest classifier, each of the random forest classifiers includes five classification judgment layers, each of which is provided with a corresponding preset single epidemic prevention capability level standard. The classification judgment layer divides the data in the corresponding single epidemic prevention capability hierarchical evaluation data set into the first-level animal epidemic prevention system key data to the fifth-level animal epidemic prevention system key data according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data. The random forest algorithm in this embodiment first inputs the single epidemic prevention capability hierarchical evaluation data set into the classification judgment layer of the random forest classifier, and the classification judgment layer judges whether the single epidemic prevention capability hierarchical evaluation data set meets the preset single epidemic prevention capability level standard of the current classification judgment layer. If the single epidemic prevention capability hierarchical evaluation data set meets the preset single epidemic prevention capability level standard of the current classification judgment layer, it is divided into the animal epidemic prevention system key data of the corresponding level of the current classification judgment layer. If the single epidemic prevention capability hierarchical evaluation data set does not meet the preset single epidemic prevention capability level standard of the current classification judgment layer, the single epidemic prevention capability hierarchical evaluation data set is sent to the next classification judgment layer. The definition of the random forest classifier is as follows:

[0094]

[0095] in, Indicates the capability level of the final output, Represents the weight of each classification judgment layer, The output result of each classification judgment layer is Indicates the number of classification judgment layers, (1,2,3,4,5).

[0096] Step S05: Upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data release;

[0097] It should be noted that the visual human-computer interaction platform in this embodiment includes a regional distribution module, an assessment and publication module, and a trend analysis module. The regional distribution module marks the location of animal disease discovery, the scope of animal disease impact, and the location of the epidemic prevention agency on the map of the current area based on the key data of the multi-level animal epidemic prevention system. The assessment and publication module publishes the assessment results of the epidemic prevention agencies marked by the regional distribution module based on the key data of the multi-level animal epidemic prevention system. The assessment results include the epidemic prevention capability information of the epidemic prevention agency and the level information of the corresponding epidemic prevention capability. The trend analysis module creates epidemic data charts and epidemic prevention capability charts based on the key data of the multi-level animal epidemic prevention system, and conducts comparative analysis to publish comprehensive trend charts.

[0098] In summary, according to the above-mentioned regional animal epidemic prevention system evaluation method based on big data, the Bayesian network algorithm is used to perform correlation analysis on the comprehensive data of the animal epidemic prevention system in the region. While screening out non-critical data, the data of different modes and different data types are linked, avoiding the problem of unclear data categories when the epidemic prevention capacity is subsequently classified according to the preset animal epidemic prevention capacity classification standards, thereby improving the efficiency and accuracy of epidemic prevention capacity classification, and then using the random forest classification algorithm to perform epidemic prevention capacity classification, automatically and accurately evaluate the epidemic prevention capacity in the region, and upload the evaluation results and data to the visual human-computer interaction platform for data publication, realizing automatic and intelligent regional animal epidemic prevention system evaluation, greatly improving the efficiency and accuracy of regional animal epidemic prevention system evaluation. Specifically, the comprehensive data of the animal epidemic prevention system in the area is collected and preprocessed to build an animal epidemic prevention system database, the quality of the data is preliminarily processed, the efficiency and accuracy of subsequent classification and grading operations are improved, the preprocessed comprehensive data of the animal epidemic prevention system in the animal epidemic prevention system database is called, and the preprocessed comprehensive data of the animal epidemic prevention system is analyzed for correlation according to the Bayesian network algorithm to screen and obtain the key data of the animal epidemic prevention system, and while filtering out non-critical data, data of different modes and different data types are linked to avoid the problem of unclear data categories when the epidemic prevention capacity is subsequently classified according to the preset animal epidemic prevention capacity classification standard. The problem is solved, thereby improving the efficiency and accuracy of epidemic prevention capability classification. The key data of the animal epidemic prevention system are classified according to the preset animal epidemic prevention capability classification standards to obtain multi-category animal epidemic prevention system key data. The multi-category animal epidemic prevention system key data are graded according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data, and the epidemic prevention capabilities in the region are automatically and accurately evaluated. The multi-level animal epidemic prevention system key data are uploaded to the visual human-computer interaction platform to complete the data publication, thereby realizing automatic and intelligent regional animal epidemic prevention system evaluation, which greatly improves the efficiency and accuracy of regional animal epidemic prevention system evaluation.

[0099] See also Figure 2 , which is a flow chart of a regional animal epidemic prevention system evaluation method based on big data proposed in the second embodiment of the present invention, and the regional animal epidemic prevention system evaluation method based on big data includes steps S11 to S15, wherein:

[0100] Step S11: Collecting comprehensive data of the animal epidemic prevention system in the region, judging the data integrity, abnormal value and duplicate value of the comprehensive data of the animal epidemic prevention system and performing corresponding defect processing, standardizing the comprehensive data of the animal epidemic prevention system after the judgment processing, and constructing an animal epidemic prevention system database;

[0101] Step S12: dividing the comprehensive data of the animal epidemic prevention system according to the data modality type to obtain text modality data and image modality data, inputting the text modality data into a text encoder to obtain text modality data features, inputting the image modality data into a convolution module to obtain image modality data features, inputting the text modality data features and the image modality data features into a Bayesian network to obtain data correlations between different modality data and correlations between single modality data features and key data features, so as to screen and obtain key data of the animal epidemic prevention system according to the correlation;

[0102] Step S13: According to the preset animal epidemic prevention capability classification standard, human, financial and material resource allocation capability data, administrative management capability data, supervision and quarantine capability data and disease prevention and control capability data are divided to obtain multi-category animal epidemic prevention system key data;

[0103] Step S14: Obtain the data features of each type of epidemic prevention capability in the key data of the multi-category animal epidemic prevention system and perform standardization processing, and randomly select K Cluster centers are obtained by dividing according to the K-MEANS clustering algorithm K A single epidemic prevention capability grading assessment data set will be K The single-item epidemic prevention capability grading evaluation data set is input into the corresponding K In a random forest classifier, the data in the corresponding single epidemic prevention capability grading evaluation data set is divided into the first-level animal epidemic prevention system key data to the fifth-level animal epidemic prevention system key data according to the random forest classification algorithm, so as to obtain the multi-level animal epidemic prevention system key data;

[0104] Step S15: Upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data release.

[0105] In summary, according to the above-mentioned regional animal epidemic prevention system evaluation method based on big data, the Bayesian network algorithm is used to perform correlation analysis on the comprehensive data of the animal epidemic prevention system in the region. While screening out non-critical data, the data of different modes and different data types are linked, avoiding the problem of unclear data categories when the epidemic prevention capacity is subsequently classified according to the preset animal epidemic prevention capacity classification standards, thereby improving the efficiency and accuracy of epidemic prevention capacity classification, and then using the random forest classification algorithm to perform epidemic prevention capacity classification, automatically and accurately evaluate the epidemic prevention capacity in the region, and upload the evaluation results and data to the visual human-computer interaction platform for data publication, realizing automatic and intelligent regional animal epidemic prevention system evaluation, greatly improving the efficiency and accuracy of regional animal epidemic prevention system evaluation. Specifically, the comprehensive data of the animal epidemic prevention system in the area is collected and preprocessed to build an animal epidemic prevention system database, the quality of the data is preliminarily processed, the efficiency and accuracy of subsequent classification and grading operations are improved, the preprocessed comprehensive data of the animal epidemic prevention system in the animal epidemic prevention system database is called, and the preprocessed comprehensive data of the animal epidemic prevention system is analyzed for correlation according to the Bayesian network algorithm to screen and obtain the key data of the animal epidemic prevention system, and while filtering out non-critical data, data of different modes and different data types are linked to avoid the problem of unclear data categories when the epidemic prevention capacity is subsequently classified according to the preset animal epidemic prevention capacity classification standard. The problem is solved, thereby improving the efficiency and accuracy of epidemic prevention capability classification. The key data of the animal epidemic prevention system are classified according to the preset animal epidemic prevention capability classification standards to obtain multi-category animal epidemic prevention system key data. The multi-category animal epidemic prevention system key data are graded according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data, and the epidemic prevention capabilities in the region are automatically and accurately evaluated. The multi-level animal epidemic prevention system key data are uploaded to the visual human-computer interaction platform to complete the data publication, thereby realizing automatic and intelligent regional animal epidemic prevention system evaluation, which greatly improves the efficiency and accuracy of regional animal epidemic prevention system evaluation.

[0106] See also Figure 3 , which is a schematic diagram of the structure of a regional animal epidemic prevention system evaluation system based on big data proposed in the third embodiment of the present invention, and the system includes:

[0107] The data collection module 10 is used to collect and pre-process the comprehensive data of the animal epidemic prevention system in the area to build an animal epidemic prevention system database;

[0108] The association analysis module 20 is used to call the pre-processed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database, and perform association analysis on the pre-processed animal epidemic prevention system comprehensive data according to the Bayesian network algorithm to screen and obtain key data of the animal epidemic prevention system;

[0109] A capability classification module 30 is used to classify the key data of the animal epidemic prevention system according to a preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system;

[0110] A capability grading module 40 is used to grade the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to a random forest classification algorithm to obtain multi-level animal epidemic prevention system key data;

[0111] The data interaction module 50 is used to upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data publication.

[0112] The present invention also proposes a computer storage medium on which one or more programs are stored, and when the program is executed by a processor, the above-mentioned regional animal epidemic prevention system evaluation method based on big data is implemented.

[0113] The present invention also proposes a computer device, comprising a memory and a processor, wherein the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to implement the above-mentioned regional animal epidemic prevention system evaluation method based on big data.

[0114] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain storage, communication, propagation or transmission of a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0115] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0116] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0117] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0118] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for evaluating regional animal epidemic prevention system based on big data, characterized in that: include: Collect and pre-process the comprehensive data of the animal epidemic prevention system in the region to build an animal epidemic prevention system database; The step of collecting the comprehensive data of the animal epidemic prevention system in the area and preprocessing it to build an animal epidemic prevention system database specifically includes: Collect comprehensive data on the animal epidemic prevention system in the region, including data on compulsory immunization for major animal diseases, animal disease monitoring and epidemiological survey data, animal epidemic emergency response data, animal health supervision and management data, livestock and poultry slaughtering industry management data, major animal disease regional prevention and control data, and veterinary system core capacity building data; Performing data integrity judgment on the comprehensive data of the animal epidemic prevention system. If it is determined that the comprehensive data of the animal epidemic prevention system is missing, locating the missing data value of the comprehensive data of the animal epidemic prevention system, performing interpolation processing on the comprehensive data of the animal epidemic prevention system to replace the missing data value, and performing data integrity judgment again; If it is determined that the comprehensive data of the animal epidemic prevention system is in a complete state, then a data outlier judgment is performed on the comprehensive data of the animal epidemic prevention system; if it is determined that the comprehensive data of the animal epidemic prevention system has a data outlier, then the data outlier of the comprehensive data of the animal epidemic prevention system is located, and an outlier conversion process is performed on the comprehensive data of the animal epidemic prevention system to replace the data outlier, and the data outlier judgment is performed again; If it is determined that the comprehensive data of the animal epidemic prevention system does not contain data abnormal values, then the comprehensive data of the animal epidemic prevention system is judged to have duplicate values; if it is determined that the comprehensive data of the animal epidemic prevention system has data duplicate values, then the data duplicate values ​​of the comprehensive data of the animal epidemic prevention system are located, and the comprehensive data of the animal epidemic prevention system is sorted and de-duplicated to delete the data duplicate values, and then the duplicate value judgment is performed again; If it is determined that the comprehensive data of the animal epidemic prevention system does not have duplicate values, the comprehensive data of the animal epidemic prevention system is standardized to construct an animal epidemic prevention system database; Calling the pre-processed comprehensive data of the animal epidemic prevention system in the animal epidemic prevention system database, and performing a correlation analysis on the pre-processed comprehensive data of the animal epidemic prevention system according to a Bayesian network algorithm, so as to screen and obtain key data of the animal epidemic prevention system; The step of calling the pre-processed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database and performing a correlation analysis on the pre-processed animal epidemic prevention system comprehensive data according to the Bayesian network algorithm to screen and obtain key data of the animal epidemic prevention system specifically includes: Calling the preprocessed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database, and dividing the preprocessed animal epidemic prevention system comprehensive data according to the data modality type to obtain text modality data and image modality data; The text modality data is input into a text encoder to obtain text modality data features. The formula for obtaining text modality data features is as follows: in, Represents the text modality data features, , represents the feature dimension, represents the fully connected layer, represents a text encoder, Represents text modal data, Indicates the data ordinal number; The image modality data is input into the convolution module to obtain the image modality data features. The formula for obtaining the image modality data features is as follows: in, Represents the image modality data features, represents the dimension conversion function, represents the convolution kernel, Represents image modality data; The text modality data features and the image modality data features are input into a Bayesian network to obtain the data correlation between different modality data and the correlation between single modality data features and key data features. The algorithm of the Bayesian network is as follows: in, Indicates data association. Represents key data characteristics, represents the probability function; Screen key data based on the data relevance to obtain key data of the animal epidemic prevention system; Classify the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system; The step of classifying the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system specifically includes: Extract the veterinary work institution data, veterinary staff quantity data, veterinary staff professional ability data, veterinary staff continuing education data, veterinary work institution funding data, veterinary work institution office facilities and equipment data, and veterinary work institution professional facilities and equipment data from the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capacity classification standards, so as to divide the human, financial and material resource allocation capacity data; According to the preset animal epidemic prevention capacity classification standards, the veterinary work agency administrative regulations enforcement data, veterinary work agency daily management data, veterinary work agency emergency management data, veterinary work agency coordination management data, veterinary work agency risk warning data and veterinary work agency service data in the key data of the animal epidemic prevention system are extracted to divide the administrative management capacity data; According to the preset animal epidemic prevention capacity classification standards, animal health supervision data, animal quarantine data, quarantine supervision and law enforcement connection data, harmless disposal supervision data of dead livestock and poultry, and identification and traceability data are extracted from the key data of the animal epidemic prevention system to divide the supervision and quarantine capacity data; According to the preset animal epidemic prevention capacity classification standards, animal disease monitoring and epidemiological survey data, veterinary laboratory testing and diagnosis data, veterinary laboratory quality assurance data, animal epidemic report data and technical guidance and training data from the key data of the animal epidemic prevention system are extracted to divide the disease prevention and control capacity data; Obtain key data of multi-category animal epidemic prevention systems based on the human, financial and material resource allocation capacity data, administrative management capacity data, division of supervision and quarantine capacity data and disease prevention and control capacity data; Classifying the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data; The step of grading the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to the random forest classification algorithm to obtain the multi-level animal epidemic prevention system key data specifically includes: Obtain the data characteristics of each type of epidemic prevention capability in the key data of multi-category animal epidemic prevention system and perform standardized processing; Randomly select from the data features of each type of epidemic prevention capability K Cluster centers are obtained by dividing according to the K-MEANS clustering algorithm K A single epidemic prevention capability grading evaluation data set, the loss function of the K-MEANS clustering algorithm is as follows: in, Indicates loss, A sample representing the characteristics of the data, represents the cluster center, , represents the clustering judgment value, represents the sample ordinal number, represents the number of samples, K is a hyperparameter, represents the cluster center ordinal number, Represents the Euclidean distance from the data sample to the cluster center; The K The single-item epidemic prevention capability grading evaluation data set is input into the corresponding K In the random forest classifiers, each of the random forest classifiers includes five classification judgment layers, and each of the classification judgment layers is respectively provided with a corresponding preset single epidemic prevention capability level standard; The classification judgment layer divides the data in the corresponding single-item epidemic prevention capability grading assessment data set into first-level animal epidemic prevention system key data to fifth-level animal epidemic prevention system key data according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data; Upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data release.

2. The regional animal epidemic prevention system evaluation method based on big data according to claim 1 is characterized in that: The random forest classification algorithm specifically includes: The single epidemic prevention capability hierarchical assessment data set is input into the classification judgment layer of the random forest classifier, and the classification judgment layer determines whether the single epidemic prevention capability hierarchical assessment data set meets the preset single epidemic prevention capability level standard of the current classification judgment layer; If the single epidemic prevention capability hierarchical assessment data set meets the preset single epidemic prevention capability level standard of the current classification judgment layer, it is classified as key data of the animal epidemic prevention system of the corresponding level of the current classification judgment layer; If the single epidemic prevention capability hierarchical assessment data set does not meet the preset single epidemic prevention capability level standard of the current classification judgment layer, the single epidemic prevention capability hierarchical assessment data set is sent to the next classification judgment layer; The random forest classifier is defined as follows: in, Indicates the capability level of the final output, Represents the weight of each classification judgment layer, The output result of each classification judgment layer is Indicates the number of classification judgment layers, (1,2,3,4,5).

3. The regional animal epidemic prevention system evaluation method based on big data according to claim 1 is characterized in that: The step of uploading the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data publication specifically includes: Upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform, which includes a regional distribution module, an assessment announcement module, and a trend analysis module; The regional distribution module marks the location of animal disease discovery, the scope of animal disease impact and the location of the epidemic prevention agency on the map of the current area based on the key data of the multi-level animal epidemic prevention system; The assessment and publication module publishes the assessment results of the epidemic prevention agencies marked by the regional distribution module according to the key data of the multi-level animal epidemic prevention system, and the assessment results include the epidemic prevention capability information of the epidemic prevention agencies and the level information of the corresponding epidemic prevention capabilities; The trend analysis module produces epidemic data charts and epidemic prevention capacity charts based on key data of the multi-level animal epidemic prevention system, and conducts comparative analysis to publish comprehensive trend charts.

4. A regional animal epidemic prevention system evaluation system based on big data, characterized in that: include: The data collection module is used to collect and pre-process the comprehensive data of the animal epidemic prevention system in the region to build an animal epidemic prevention system database; The step of collecting the comprehensive data of the animal epidemic prevention system in the area and preprocessing it to build an animal epidemic prevention system database specifically includes: Collect comprehensive data on the animal epidemic prevention system in the region, including data on compulsory immunization for major animal diseases, animal disease monitoring and epidemiological survey data, animal epidemic emergency response data, animal health supervision and management data, livestock and poultry slaughtering industry management data, major animal disease regional prevention and control data, and veterinary system core capacity building data; Performing data integrity judgment on the comprehensive data of the animal epidemic prevention system. If it is determined that the comprehensive data of the animal epidemic prevention system is missing, locating the missing data value of the comprehensive data of the animal epidemic prevention system, performing interpolation processing on the comprehensive data of the animal epidemic prevention system to replace the missing data value, and performing data integrity judgment again; If it is determined that the comprehensive data of the animal epidemic prevention system is in a complete state, then a data outlier judgment is performed on the comprehensive data of the animal epidemic prevention system; if it is determined that the comprehensive data of the animal epidemic prevention system has a data outlier, then the data outlier of the comprehensive data of the animal epidemic prevention system is located, and an outlier conversion process is performed on the comprehensive data of the animal epidemic prevention system to replace the data outlier, and the data outlier judgment is performed again; If it is determined that the comprehensive data of the animal epidemic prevention system does not contain data abnormal values, then the comprehensive data of the animal epidemic prevention system is judged to have duplicate values; if it is determined that the comprehensive data of the animal epidemic prevention system has data duplicate values, then the data duplicate values ​​of the comprehensive data of the animal epidemic prevention system are located, and the comprehensive data of the animal epidemic prevention system is sorted and de-duplicated to delete the data duplicate values, and then the duplicate value judgment is performed again; If it is determined that the comprehensive data of the animal epidemic prevention system does not have duplicate values, the comprehensive data of the animal epidemic prevention system is standardized to construct an animal epidemic prevention system database; A correlation analysis module is used to call the pre-processed comprehensive data of the animal epidemic prevention system in the animal epidemic prevention system database, and perform correlation analysis on the pre-processed comprehensive data of the animal epidemic prevention system according to the Bayesian network algorithm to screen and obtain key data of the animal epidemic prevention system; The step of calling the pre-processed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database and performing a correlation analysis on the pre-processed animal epidemic prevention system comprehensive data according to the Bayesian network algorithm to screen and obtain key data of the animal epidemic prevention system specifically includes: Calling the preprocessed animal epidemic prevention system comprehensive data in the animal epidemic prevention system database, and dividing the preprocessed animal epidemic prevention system comprehensive data according to the data modality type to obtain text modality data and image modality data; The text modality data is input into a text encoder to obtain text modality data features. The formula for obtaining text modality data features is as follows: in, Represents the text modality data features, , represents the feature dimension, represents the fully connected layer, represents a text encoder, Represents text modal data, Indicates the data ordinal number; The image modality data is input into the convolution module to obtain the image modality data features. The formula for obtaining the image modality data features is as follows: in, Represents the image modality data features, represents the dimension conversion function, represents the convolution kernel, Represents image modality data; The text modality data features and the image modality data features are input into a Bayesian network to obtain the data correlation between different modality data and the correlation between single modality data features and key data features. The algorithm of the Bayesian network is as follows: in, Indicates data association. Represents key data characteristics, represents the probability function; Screen key data based on the data relevance to obtain key data of the animal epidemic prevention system; A capability classification module is used to classify the key data of the animal epidemic prevention system according to a preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system; The step of classifying the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capability classification standard to obtain multiple categories of key data of the animal epidemic prevention system specifically includes: Extract the veterinary work institution data, veterinary staff quantity data, veterinary staff professional ability data, veterinary staff continuing education data, veterinary work institution funding data, veterinary work institution office facilities and equipment data, and veterinary work institution professional facilities and equipment data from the key data of the animal epidemic prevention system according to the preset animal epidemic prevention capacity classification standards, so as to divide the human, financial and material resource allocation capacity data; According to the preset animal epidemic prevention capacity classification standards, the veterinary work agency administrative regulations enforcement data, veterinary work agency daily management data, veterinary work agency emergency management data, veterinary work agency coordination management data, veterinary work agency risk warning data and veterinary work agency service data in the key data of the animal epidemic prevention system are extracted to divide the administrative management capacity data; According to the preset animal epidemic prevention capacity classification standards, animal health supervision data, animal quarantine data, quarantine supervision and law enforcement connection data, harmless disposal supervision data of dead livestock and poultry, and identification and traceability data are extracted from the key data of the animal epidemic prevention system to divide the supervision and quarantine capacity data; According to the preset animal epidemic prevention capacity classification standards, animal disease monitoring and epidemiological survey data, veterinary laboratory testing and diagnosis data, veterinary laboratory quality assurance data, animal epidemic report data and technical guidance and training data from the key data of the animal epidemic prevention system are extracted to divide the disease prevention and control capacity data; Obtain key data of multi-category animal epidemic prevention systems based on the human, financial and material resource allocation capacity data, administrative management capacity data, division of supervision and quarantine capacity data and disease prevention and control capacity data; A capability grading module, used to grade the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to a random forest classification algorithm, so as to obtain multi-level animal epidemic prevention system key data; The step of grading the epidemic prevention capabilities of the multi-category animal epidemic prevention system key data according to the random forest classification algorithm to obtain the multi-level animal epidemic prevention system key data specifically includes: Obtain the data characteristics of each type of epidemic prevention capability in the key data of multi-category animal epidemic prevention system and perform standardized processing; Randomly select from the data features of each type of epidemic prevention capability K Cluster centers are obtained by dividing according to the K-MEANS clustering algorithm K A single epidemic prevention capability grading evaluation data set, the loss function of the K-MEANS clustering algorithm is as follows: in, Indicates loss, A sample representing the characteristics of the data, represents the cluster center, , represents the clustering judgment value, represents the sample ordinal number, represents the number of samples, K is a hyperparameter, represents the cluster center ordinal number, Represents the Euclidean distance from the data sample to the cluster center; The K The single-item epidemic prevention capability grading evaluation data set is input into the corresponding K In the random forest classifiers, each of the random forest classifiers includes five classification judgment layers, and each of the classification judgment layers is respectively provided with a corresponding preset single epidemic prevention capability level standard; The classification judgment layer divides the data in the corresponding single-item epidemic prevention capability grading assessment data set into first-level animal epidemic prevention system key data to fifth-level animal epidemic prevention system key data according to the random forest classification algorithm to obtain multi-level animal epidemic prevention system key data; The data interaction module is used to upload the key data of the multi-level animal epidemic prevention system to the visual human-computer interaction platform to complete the data publication.

5. A storage medium, characterized in that: The storage medium stores one or more programs, which, when executed by the processor, implement the regional animal epidemic prevention system evaluation method based on big data as described in any one of claims 1 to 3.

6. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, it implements the regional animal epidemic prevention system evaluation method based on big data as described in any one of claims 1-3.