Blockchain-based animal epidemic prevention processing method and system

Abstract

The application discloses a kind of animal epidemic prevention processing method and system based on blockchain, method includes: establishing farm basic database, and combining animal species characteristics and geographical location climate condition, formulates epidemic prevention schedule, determines the epidemic prevention time node of farm;Real-time acquisition of farm environment data, animal health data and epidemic prevention operation record is carried out through Internet of Things equipment, generates epidemic prevention execution data stream;Epidemic prevention execution data stream is compared with the preset epidemic prevention measure execution list, and the implementation of epidemic prevention measure is judged by setting threshold and rule;According to the implementation of epidemic prevention measure and epidemic prevention execution data stream, the effect of epidemic prevention is analyzed using random forest algorithm, and an epidemic prevention effect evaluation report is generated;Epidemic prevention effect evaluation report and epidemic situation early warning information are encrypted and stored and shared by blockchain, to provide data support for epidemic prevention decision-making.The application realizes the intelligentization, precision and traceability of farm epidemic prevention management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information processing, in particular to an animal epidemic prevention processing method and system based on a blockchain. BACKGROUND

[0002] In the process of animal breeding, due to the scattered geographical location of breeding sites, the variety of animals being raised, and the uneven level of feeding management, the problem of low efficiency and difficulty in animal epidemic prevention is increasingly prominent.

[0003] The traditional animal epidemic prevention mode mainly relies on manual inspection and regular immunization, and there are problems such as non-uniform epidemic prevention time, non-implementation of epidemic prevention measures, and difficulty in evaluating the effect of epidemic prevention. At the same time, there is a lack of effective information sharing and coordination mechanism among breeding farms, and the epidemic information transmission is not timely and accurate, which increases the risk of epidemic spread. In addition, the massive data generated in the process of epidemic prevention lacks effective management and analysis means, and the data authenticity and security are difficult to guarantee, and the epidemic prevention decision lacks data support.

[0004] Therefore, it is urgent to develop a new animal epidemic prevention mode that can effectively integrate breeding farms, epidemic prevention stations and other parties, realize the credibility and controllability of the whole process of epidemic prevention, data security sharing, intelligent analysis and decision-making, so as to improve the efficiency of animal epidemic prevention and protect the healthy and sustainable development of the breeding industry. SUMMARY

[0005] To solve the above technical problems in the prior art, the present application provides an animal epidemic prevention processing method and system based on a blockchain, which realizes the intelligentization, precision and traceability of breeding farm epidemic prevention management, improves the epidemic prevention efficiency and decision-making level, and provides strong support for the healthy and sustainable development of the animal husbandry industry.

[0006] On the one hand, in order to achieve the above-mentioned purpose, the present application provides an animal epidemic prevention processing method based on a blockchain, comprising:

[0007] Establish a breeding farm basic database, and according to the breeding farm basic database, combined with the characteristics of animal species and geographical and climatic conditions, formulate an epidemic prevention schedule and determine the epidemic prevention time node of the breeding farm;

[0008] Real-time collection of breeding farm environmental data, animal health data and epidemic prevention operation records through Internet of Things devices to generate epidemic prevention execution data flow;

[0009] Comparing the epidemic prevention execution data flow with the preset epidemic prevention measure execution list, and judging the implementation of the epidemic prevention measures by setting threshold and rules;

[0010] According to the epidemic prevention execution data flow and the implementation of the epidemic prevention measures, the random forest algorithm is used to analyze the epidemic prevention effect, and an epidemic prevention effect evaluation report is generated.

[0011] The epidemic prevention effect evaluation report and epidemic early warning information are encrypted and stored and shared through the blockchain, thereby providing data support for epidemic prevention decision-making.

[0012] In another aspect, to achieve the above-mentioned object, the application further provides an animal epidemic prevention processing system based on a blockchain, comprising:

[0013] A basic database construction module is configured to construct a farm basic database.

[0014] An epidemic prevention schedule formulation module is configured to formulate an epidemic prevention schedule according to the farm basic database, in combination with animal species characteristics and geographical location climate conditions, to determine epidemic prevention time nodes of each farm.

[0015] A data acquisition module is configured to acquire farm environment data, animal health data and epidemic prevention operation records in real time through Internet of Things devices, to generate epidemic prevention execution data flow.

[0016] An epidemic prevention measure comparison module is configured to compare the epidemic prevention execution data flow with a preset epidemic prevention measure execution list, to judge the implementation of epidemic prevention measures by setting a threshold and rules.

[0017] An epidemic prevention effect analysis module is configured to analyze the epidemic prevention effect according to the epidemic prevention execution data flow and the implementation of the epidemic prevention measures, to generate an epidemic prevention effect evaluation report by using a random forest algorithm.

[0018] A data encryption storage module is configured to encrypt and store and share the epidemic prevention effect evaluation report and epidemic early warning information through a blockchain technology.

[0019] Compared with the prior art, the application has the following advantages and technical effects:

[0020] The application constructs a farm basic database, formulates a unified epidemic prevention schedule in combination with animal characteristics and geographical climate conditions. Internet of Things devices are used to acquire environment, animal health and epidemic prevention operation data in real time, to form epidemic prevention execution data flow. The execution data are compared with a preset list to judge the implementation of epidemic prevention measures. A random forest algorithm is used to analyze the epidemic prevention effect to generate an evaluation report. Finally, a blockchain technology is used to encrypt and store and share epidemic prevention data, evaluation reports and early warning information, to ensure data authenticity and security. The application realizes intelligent, precise and traceable farm epidemic prevention management, improves epidemic prevention efficiency and decision-making level, and provides strong support for the healthy and sustainable development of the animal husbandry industry. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings, which form a part of the present application, are included to provide a further understanding of the application, and are incorporated in and constitute a part of this application. The embodiments of the present application, and their

[0022] Figure 1 A flow chart of an animal epidemic prevention processing method based on a blockchain according to an embodiment of the present application;

[0023] Figure 2 A structure schematic diagram of an animal epidemic prevention processing system based on a blockchain according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flow chart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0026] The present application provides an animal epidemic prevention processing method based on a blockchain, which comprises the following steps: Figure 1 , comprising:

[0027] Establishing a breeding farm basic database, and formulating an epidemic prevention schedule according to the breeding farm basic database, combining animal species characteristics and geographical location and climate conditions, and determining epidemic prevention time nodes of the breeding farm;

[0028] Collecting breeding farm environment data, animal health data and epidemic prevention operation records in real time through Internet of Things devices, and generating epidemic prevention execution data flow;

[0029] Comparing the epidemic prevention execution data flow with a preset epidemic prevention measure execution list, and judging the implementation of the epidemic prevention measures by setting a threshold and a rule;

[0030] According to the epidemic prevention execution data flow and the implementation of the epidemic prevention measures, analyzing the epidemic prevention effect by using a random forest algorithm, and generating an epidemic prevention effect evaluation report;

[0031] Encrypting and storing the epidemic prevention effect evaluation report and epidemic situation early warning information through a blockchain, and sharing the same, so as to provide data support for epidemic prevention decision-making.

[0032] Further, the breeding farm basic database comprises the following steps:

[0033] Obtaining geographical position information of the breeding farm, and determining specific position coordinates of the breeding farm;

[0034] acquire the animal species information of the farm, determine the animal species raised by the farm;

[0035] acquire the animal quantity information of the farm, determine the quantity of different animal species;

[0036] classify and organize the geographic location information, animal species information and animal quantity information of the farm, and establish structured data records;

[0037] import the structured data records into a database system, and establish the farm basic database.

[0038] Specifically, the geographic location information of the farm is acquired, and the specific location coordinates of the farm are determined through GPS positioning or map labeling. The animal species information of the farm is acquired, and the animal species raised by the farm are determined through on-site investigation or data provided by the farm. The animal quantity information of the farm is acquired, and the quantity of various animals is determined through on-site counting or statistical data provided by the farm. The acquired geographic location information, animal species information and animal quantity information of the farm are classified and organized, and structured data records are established. The classified and organized farm information is imported into a database system, and a farm basic information database is established. According to the animal species and quantity data of the farm, statistical methods are used for data analysis, and statistical indexes such as the quantity and density of various animals are obtained. According to the geographic location data of the farm, a spatial clustering algorithm is used to divide the farm into regions, and the spatial distribution characteristics of the farms in different regions are determined.

[0039] Collecting latitude and longitude coordinates through GPS positioning devices or using satellite maps for labeling. For example, a pig farm is located at 30°15'36" north latitude and 120°10'48" east longitude. This precise positioning helps subsequent spatial analysis and regional planning. Animal species information is usually obtained through field investigation or by consulting the information provided by the breeding farm. A typical breeding farm may raise multiple animals, such as pigs, broilers, laying hens, etc. Accurate knowledge of animal species is crucial for disease prevention and control and production management. Animal quantity information can be obtained through on-site counting or statistical data provided by the breeding farm. For example, a breeding farm may raise 5000 pigs and 20000 broilers. These data reflect the production scale and operating conditions of the breeding farm. Organize the collected information into structured data records. It can be organized according to geographical location, animal species, quantity, etc. dimensions to form a data structure that is easy to query and analyze. This structured data facilitates the import of database systems and the establishment of a breeding farm basic information database. Based on the animal species and quantity data of the breeding farm, statistical analysis can be performed. For example, calculate the number of animals of each type and the stocking density. The pig stocking density in a certain area may be 100 per square kilometer, which can be used to assess the breeding intensity and environmental carrying capacity. Using the geographical location data of the breeding farm, spatial clustering algorithms can be used for regional division. K-means clustering is one of the commonly used methods, which can divide the breeding farms into several groups according to the degree of geographical proximity. This division helps to understand the spatial distribution characteristics of the breeding industry and provides a basis for regional planning and disease prevention and control. Through these steps, a comprehensive breeding farm information system can be constructed. This system not only records basic data, but also supports in-depth statistical analysis and spatial analysis.

[0040] Further, determining the epidemic prevention time node of the breeding farm, comprising:

[0041] According to the animal species and geographical location information in the breeding farm basic database, obtaining the animal characteristics and climate condition data of each breeding farm;

[0042] By clustering analysis on the animal species characteristic data, the animal species with similar characteristics are divided into several categories, and a unified epidemic prevention schedule is formulated for each animal category;

[0043] According to the geographical location of the breeding farm, obtaining the historical climate condition data of the location, and through time series analysis, predicting the climate change trend of the region in the preset time period;

[0044] Matching the epidemic prevention schedule of the animal species with the climate prediction data of the geographical location of the breeding farm, obtaining the epidemic prevention time node suitable for different breeding farms.

[0045] Specifically, according to the animal species and geographical location information in the farm database, the animal characteristics and climate condition data of each farm are obtained. By clustering analysis on the animal species characteristic data, animal species with similar characteristics are divided into several categories, and a unified epidemic prevention schedule is formulated for each category of animal species. According to the geographical location of the farm, the historical climate condition data of the location is obtained, and through time series analysis, the climate change trend in the future period is predicted. The epidemic prevention schedule of the animal species is matched with the climate prediction data of the geographical location of the farm to obtain the epidemic prevention time node suitable for each farm. The decision tree algorithm is used to generate the judgment rule of the epidemic prevention time node with animal species, climate condition, etc. as the decision factor. The judgment rule is applied to the actual situation of each farm to automatically determine the specific epidemic prevention time arrangement of the farm. The epidemic prevention schedule and epidemic prevention node are visualized for the convenience of the farm managers to check and execute, and the epidemic prevention reminder information is pushed to the relevant personnel to ensure that the epidemic prevention work is carried out on time.

[0046] Animal characteristic data such as the growth cycle of pigs and the egg laying period of chickens are obtained, which affect the selection of epidemic prevention time. Climate condition data includes temperature, humidity, precipitation, etc., which are closely related to disease transmission. Cluster analysis can classify similar characteristic animals, such as large mammals such as pigs and cows into one category, and poultry such as chickens and ducks into another category. A unified epidemic prevention schedule is formulated for each category of animals, such as vaccinating large mammals against foot-and-mouth disease once a quarter and conducting avian influenza detection on poultry once a month. Time series analysis predicts climate change trends, such as increasing average summer temperature and humidity in a certain area, which may lead to an increased risk of certain infectious diseases. Match the epidemic prevention schedule with the climate prediction, such as increasing disinfection frequency in months with high humidity and advancing vaccine inoculation in seasons with high temperature. The decision tree algorithm generates epidemic prevention time node judgment rules. Animal species, age, weight, environmental temperature, etc. are used as decision factors to build a judgment tree. For example, if it is a growing pig and the environmental temperature exceeds 30°C, the vaccine inoculation is advanced by one week. Apply these rules to each farm to automatically generate specific epidemic prevention arrangements. Visualize the epidemic prevention schedule, such as using a Gantt chart to display the time arrangement of various epidemic prevention tasks, and different colors represent different types of epidemic prevention measures. Push epidemic prevention reminders, such as through SMS, App notifications, etc. to remind managers of upcoming epidemic prevention tasks.

[0047] Further, after generating the epidemic prevention execution data stream, including:

[0048] Preprocess the epidemic prevention execution data stream to eliminate abnormal data and obtain standardized epidemic prevention execution data;

[0049] According to the preset environmental parameter threshold and the animal health index threshold, it is judged whether the current farm environment is suitable and the animal health condition is normal, and if the threshold is exceeded, a warning is triggered;

[0050] The normalized epidemic prevention execution data is analyzed by using a machine learning method to obtain an evaluation result of the epidemic prevention management status of the farm;

[0051] The farm environment monitoring data and the animal health monitoring data and the epidemic prevention management status evaluation result are analyzed to identify the epidemic prevention management risk points existing in the farm;

[0052] For the epidemic prevention management risk points, an epidemic prevention management optimization suggestion is automatically generated and pushed to the farm management personnel;

[0053] The improvement of the epidemic prevention management of the farm is continuously tracked, the execution effect of the epidemic prevention management optimization suggestion is evaluated by comparing the historical data and the current data, and an epidemic prevention management closed loop is formed.

[0054] Specifically, real-time environmental data such as temperature, humidity, ammonia concentration, and animal health data such as body temperature, heart rate, and activity level are collected. These data form the epidemic prevention execution data stream, providing a basis for subsequent analysis. For example, a pig farm's temperature sensor records temperature every hour, and a body temperature detection device measures the body temperature of each pig every day. Data preprocessing is a key step to ensure analysis quality. Abnormal data may be caused by equipment failure or human error and need to be identified and removed through statistical methods. For example, if the humidity data of a chicken farm suddenly jumps from 60% to 99%, it may be an abnormal value caused by sensor failure and should be removed. Pre-set thresholds are used to discover potential problems in a timely manner. For example, if the temperature in the chicken coop exceeds 35°C or falls below 15°C, an early warning is triggered, reminding the management personnel to take measures. Similarly, if the body temperature of multiple chickens exceeds 42°C, the system will issue an epidemic warning. Machine learning algorithms such as support vector machines or random forests can be used to analyze epidemic prevention execution data and assess the current situation of epidemic prevention management. The algorithm can learn patterns in historical data, such as the correlation between certain environmental parameter combinations and disease outbreaks, to make assessments on the current situation. Correlation analysis helps identify risk points in epidemic prevention management. For example, through analysis, it is found that if the duck farm does not adjust the feeding environment in time when the temperature drops suddenly, the incidence of avian influenza will increase significantly. This correlation can help management personnel take preventive measures in advance. Based on the identified risk points, the system can automatically generate optimization suggestions. For example, it suggests turning on the heating equipment 24 hours before the temperature drops and increasing the frequency of disinfection. These suggestions are pushed to the management personnel through a mobile application to ensure timely execution. Continuous tracking and evaluation are key to forming a closed loop of epidemic prevention management. For example, after implementing a new disinfection scheme, the system compares the disease incidence before and after implementation. If the new scheme reduces the disease incidence by 20%, it proves to be effective. This continuous evaluation and improvement process helps continuously optimize epidemic prevention management strategies and improve the overall epidemic prevention level of the farm. Through these steps, the farm can establish a data-driven intelligent epidemic prevention system. This not only improves the efficiency of epidemic prevention but also reduces the risk of human judgment errors. In the long run, this method can significantly improve the production efficiency and animal welfare of the farm, providing strong support for the sustainable development of the farming industry.

[0055] Further, the risk points in the epidemic prevention management of the farm are identified, including:

[0056] Obtaining environmental monitoring data of the farm, including temperature, humidity, and air quality, and using the environmental monitoring data of the farm as a basis for determining whether the environment of the farm is suitable for animal growth;

[0057] Obtaining animal health monitoring data, including the growth of animals, immune status, and disease occurrence, and using the animal health monitoring data as an index for evaluating the health status of animals;

[0058] obtain the evaluation result of the epidemic prevention management status of the farm, including the epidemic prevention facility equipment situation, the epidemic prevention system implementation situation, and the personnel training situation, and use the evaluation result of the epidemic prevention management status of the farm as a basis for judging the epidemic prevention management level;

[0059] perform correlation analysis on the farm environment monitoring data, the animal health monitoring data, and the evaluation result of the epidemic prevention management status, and use a data mining algorithm to identify the correlation between the indicators;

[0060] According to the correlation analysis result, determine the weak link and risk point existing in the epidemic prevention management of the farm, and according to the identified risk point, use expert system technology, combine the preset epidemic prevention management knowledge base, generate epidemic prevention management measure suggestion, and provide the epidemic prevention management measure suggestion to the farm management personnel.

[0061] Specifically, the farm environment monitoring data, including temperature, humidity, air quality and other index data, are obtained as one of the bases for judging whether the environment of the farm is suitable for the growth of animals. The animal health monitoring data, including the growth of animals, immune status, disease occurrence, etc., are obtained as important indicators for evaluating the health status of animals. The evaluation result of the epidemic prevention management status of the farm, including the epidemic prevention facility equipment situation, the epidemic prevention system implementation situation, and the personnel training situation, is obtained as a basis for judging the epidemic prevention management level. The farm environment monitoring data, animal health monitoring data and epidemic prevention management status evaluation result are correlated and analyzed, and a data mining algorithm such as association rule mining algorithm is used to identify the correlation between the indicators. According to the correlation analysis result, the weak link and risk point existing in the epidemic prevention management of the farm are determined, such as substandard environmental conditions, low animal immunity, and imperfect epidemic prevention system implementation. For the identified risk points, expert system technology is used, combined with the preset epidemic prevention management knowledge base, to generate targeted epidemic prevention management measure suggestions, such as improving environmental conditions, strengthening animal immunity, and perfecting epidemic prevention system. The generated epidemic prevention management measure suggestions are provided to the farm management personnel, and the epidemic prevention management status and improvement direction of the farm are visually displayed through visualization technology such as dashboard, report, etc., to provide decision support for the optimization of epidemic prevention management of the farm.

[0062] Further, the epidemic prevention implementation data stream is compared with the preset epidemic prevention measure implementation list, and the implementation of the epidemic prevention measures is judged by setting threshold and rules, including:

[0063] The epidemic prevention implementation data stream and the epidemic prevention measure implementation list are compared using a text similarity algorithm to obtain a similarity score;

[0064] According to the preset threshold, it is judged whether the similarity score exceeds the threshold. If the similarity score exceeds the threshold, it is determined that the epidemic prevention measures are implemented in place. If the similarity score does not exceed the threshold, it is determined that the epidemic prevention measures are not implemented in place.

[0065] By setting rules, the implementation of several epidemic prevention measures is comprehensively judged to determine the implementation degree of the overall epidemic prevention measures.

[0066] According to the judgment result, the implementation report of the epidemic prevention measures is output.

[0067] Specifically, when judging the implementation of the epidemic prevention measures, the importance of different measures needs to be considered. Different epidemic prevention measures can be assigned weights, for example, vaccination may be more important than daily disinfection, so it can be given a higher weight. Through weighted average, the implementation degree of the overall epidemic prevention measures can be obtained. The generation of the implementation report is the last step of the whole process and the most important output. This report not only lists the implementation of each measure, but also should include analysis and suggestions. For example, if it is found that an important measure has not been implemented for many times in a row, the report should highlight and analyze the possible reasons, such as complex operation process, insufficient personnel training, etc., and give corresponding improvement suggestions. This data-driven epidemic prevention management method has many advantages. First, it improves the accuracy and efficiency of epidemic prevention management and reduces the subjectivity of human judgment. Second, through continuous data collection and analysis, weaknesses in epidemic prevention management can be found in time, which helps to continuously optimize epidemic prevention strategies. Finally, this method can also provide an important basis for epidemic warning. By analyzing historical data, a prediction model can be established to identify potential epidemic risks in advance. However, some problems need to be paid attention to in the implementation process. For example, the guarantee of data quality is crucial, and the data collection equipment needs to be calibrated and maintained regularly. In addition, the special situation of different breeding farms needs to be considered, and the judgment standard and weight need to be adjusted appropriately to ensure the universality and effectiveness of the system. Through continuous practice and optimization, this intelligent epidemic prevention management system will provide strong support for the healthy development of the breeding industry.

[0068] Further, an epidemic prevention effect evaluation report is generated, including:

[0069] Obtain the epidemic prevention execution data stream and the epidemic prevention measure implementation situation data, preprocess the data to obtain a standardized data set;

[0070] According to the epidemic prevention effect evaluation index system, select relevant features from the standardized data set to construct a training data set of the random forest model;

[0071] The random forest algorithm is used to train the training data set, the model parameters are optimized by cross-validation method, and the optimal random forest model is obtained;

[0072] inputting the epidemic prevention execution data stream and real-time data of implementation of the epidemic prevention measures into the optimal random forest model, predicting and evaluating the epidemic prevention effect, and outputting a prediction result;

[0073] According to the prediction result, it is judged whether the epidemic prevention effect reaches the expected target. If not, the key factors affecting the epidemic prevention effect are analyzed, suggestions for improving the epidemic prevention measures are put forward, and the suggestions are fed back to the relevant departments to optimize the epidemic prevention execution scheme;

[0074] According to the evaluation result of the random forest model and the improvement suggestion, the epidemic prevention effect evaluation report is generated.

[0075] Specifically, in the evaluation of the epidemic prevention effect, the random forest can effectively process multi-dimensional features and give the importance ranking of each feature. For example, the model may find that in a certain area, the vaccination rate has the greatest impact on the epidemic prevention effect, followed by the nucleic acid detection coverage. Cross-validation is an important method for optimizing model parameters. By dividing the data set into multiple subsets and repeatedly training and validating, the best combination of model parameters can be found. In the evaluation of the epidemic prevention effect, parameters such as the depth of the decision tree and the number of feature selection may need to be adjusted. Through cross-validation, model overfitting can be avoided, and its generalization ability on new data can be improved. Inputting real-time data into the trained random forest model can dynamically evaluate the epidemic prevention effect. For example, the model may predict the trend of the number of new cases in the next week under the current epidemic prevention measures. If the prediction result shows that the epidemic may rebound, the prevention and control strategy needs to be adjusted in time. Analyzing the key factors affecting the epidemic prevention effect is an important basis for optimizing the epidemic prevention measures. The random forest model can give the contribution of each feature to the prediction result. For example, if the model finds that the poor epidemic prevention effect in a certain area is mainly due to the low nucleic acid detection coverage, then it can be suggested to increase the detection points and improve the detection frequency. The improvement suggestions based on the model evaluation results need to consider the actual feasibility. For example, if the model suggests to increase the vaccination rate, the relevant departments can develop targeted propaganda strategies or take convenient measures such as setting up temporary vaccination points. The implementation effect of these suggestions can be verified through continuous monitoring and model prediction. The epidemic prevention effect evaluation report is an important tool for decision-making support. The report should include quantitative indicators of the current epidemic prevention effect, future trend prediction, key influencing factor analysis and specific improvement suggestions. Such a report can help decision-makers quickly understand the epidemic situation and make scientific and timely decisions, so as to more effectively control the spread of the epidemic.

[0076] Further, the epidemic prevention effect evaluation report and the epidemic warning information are encrypted and stored and shared through the blockchain, including:

[0077] The epidemic prevention data is preprocessed, and according to the preset epidemic early warning index system, a machine learning algorithm is used to model and analyze the epidemic prevention data to generate epidemic early warning information.

[0078] The epidemic prevention effect evaluation report and the epidemic early warning information are formatted according to the preset data standard, a data fingerprint is generated through a hash algorithm, and the data is encrypted and stored by using a blockchain technology;

[0079] An epidemic prevention data sharing mechanism based on a blockchain is established, data interfaces of various related departments are connected, data access permissions are controlled through a smart contract, and safe data sharing across departments and regions is realized.

[0080] Specifically, the related data for epidemic prevention is preprocessed to identify and process missing values, outliers, etc., to improve data quality and reliability and lay a foundation for subsequent analysis. According to the preset epidemic early warning index system, a machine learning algorithm such as support vector machine or random forest is used to model and analyze the epidemic prevention data, to monitor the epidemic risk in real time and generate epidemic early warning information in a timely manner. The epidemic prevention data, epidemic early warning information, etc. are formatted according to certain data standards, a data fingerprint is generated through a hash algorithm, and the data is encrypted and stored by using a blockchain technology, to ensure the integrity and non-tamperability of the data. An epidemic prevention data sharing mechanism based on a blockchain is established, data interfaces of various related departments are connected, data access permissions are controlled through a smart contract, and safe data sharing across departments and regions is realized, to improve the efficiency of collaborative epidemic prevention. The characteristics of the blockchain such as non-tamperability and traceability are used to record and evidence the whole process of epidemic prevention data and decision-making process, to ensure the openness and transparency of the decision-making process, to accept social supervision, and to improve the credibility of epidemic prevention work. The epidemic prevention data platform based on a blockchain is interconnected with various business systems, the processes of epidemic monitoring and early warning, data analysis, and epidemic prevention decision-making are connected, a closed loop is formed, the whole process of data flow and business flow is visualized, and the precision and timeliness of epidemic prevention are improved.

[0081] The embodiment also provides an animal epidemic prevention processing system based on a blockchain, which comprises: Figure 2 , including:

[0082] A basic database construction module is configured to construct a farm basic database;

[0083] An epidemic prevention schedule formulation module is configured to formulate an epidemic prevention schedule according to the farm basic database, in combination with animal species characteristics and geographical location and climate conditions, to determine epidemic prevention time nodes of each farm;

[0084] A data acquisition module is configured to acquire farm environment data, animal health data, and epidemic prevention operation records in real time through Internet of Things devices, to generate epidemic prevention execution data flow;

[0085] The epidemic prevention measure comparison module is configured to compare the epidemic prevention execution data stream with a preset epidemic prevention measure execution list, and determine the implementation of the epidemic prevention measures by setting a threshold and a rule.

[0086] The epidemic prevention effect analysis module is configured to analyze the epidemic prevention effect by using a random forest algorithm according to the epidemic prevention execution data stream and the implementation of the epidemic prevention measures, and generate an epidemic prevention effect evaluation report.

[0087] The data encryption storage module is configured to encrypt and store and share the epidemic prevention effect evaluation report and epidemic situation early warning information by using a block chain technology.

[0088] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A blockchain-based animal disease prevention and control method, characterized in that, include: Establish a basic database of farms; based on the basic database of farms, combined with the characteristics of animal species and geographical location and climate conditions, formulate a disease prevention schedule and determine the disease prevention time nodes of farms. The determination of the disease prevention timeline for the aforementioned farm includes: Based on the animal species and geographical location information in the basic database of the farms, obtain the animal characteristics and climate conditions data for each farm; By performing cluster analysis on animal species characteristic data, animal species with similar characteristics are divided into the same category, resulting in several groups. A unified epidemic prevention schedule is then developed for animals in the same group. Based on the geographical location of the farm, historical climate data of the farm's location is obtained. Through time series analysis, the climate change trend of the corresponding region of the farm's location is predicted within a preset time period. Based on the climate prediction data of the farm's location, the disease prevention schedule for animal species is adjusted in a personalized manner to obtain disease prevention time nodes suitable for different farms. Real-time data collection of farm environment, animal health, and disease prevention operation records is achieved through IoT devices, generating a data stream for disease prevention execution. The data stream of epidemic prevention implementation is compared with a preset list of epidemic prevention measures to determine the implementation status of the measures by setting thresholds and rules. Based on the epidemic prevention execution data stream and the implementation status of the epidemic prevention measures, the random forest algorithm is used to analyze the epidemic prevention effect, generate an epidemic prevention effect evaluation report, and generate epidemic early warning information based on the epidemic prevention execution data stream and threshold judgment results. The epidemic prevention effectiveness assessment report and epidemic early warning information are encrypted, stored, and shared using blockchain technology, providing data support for epidemic prevention decision-making.

2. The blockchain-based animal disease prevention and control method according to claim 1, characterized in that, Establish a basic database for livestock farms, including: Obtain the geographical location information of the farm and determine its specific location coordinates; Obtain information on the types of animals raised at the farm to determine the types of animals being raised at the farm. Obtain information on the number of animals in the farm and determine the number of different animal species. The geographical location, animal species, and quantity information of the aforementioned farms are classified and organized to establish structured data records; The structured data records are imported into the database system to establish the basic database of the farm.

3. The blockchain-based animal disease prevention and control method according to claim 1, characterized in that, After generating the aforementioned epidemic prevention execution data stream, it includes: The epidemic prevention execution data stream is preprocessed to remove abnormal data and obtain standardized epidemic prevention execution data; Based on preset environmental parameter thresholds and animal health indicator thresholds, determine whether the current farm environment is suitable and whether the animals' health status is normal. If the thresholds are exceeded, an early warning will be triggered. Machine learning methods were used to analyze the standardized epidemic prevention implementation data to obtain an assessment of the current status of epidemic prevention management in the farm. By correlating and analyzing the environmental monitoring data and animal health monitoring data of the farm with the assessment results of the current status of epidemic prevention and control, the risk points of epidemic prevention and control in the farm can be identified. For the aforementioned epidemic prevention and control risk points, the system automatically generates optimization suggestions for epidemic prevention and control and pushes them to the farm management personnel; Continuously track the improvement of epidemic prevention management in farms, evaluate the effectiveness of the implementation of epidemic prevention management optimization suggestions by comparing historical data and current data, and form a closed loop for epidemic prevention management.

4. The blockchain-based animal disease prevention and control method according to claim 3, characterized in that, Identify the disease prevention and control risks present in the farm, including: Obtain environmental monitoring data from the farm, including temperature, humidity, and air quality, and use this data as a basis for determining whether the farm environment is suitable for animal growth. Acquire animal health monitoring data, including animal growth, immune status, and disease occurrence, and use the animal health monitoring data as an indicator to assess animal health status; Obtain the assessment results of the current status of epidemic prevention management in farms, including the availability of epidemic prevention facilities, the implementation of epidemic prevention systems, and the training of personnel. Use the assessment results of the current status of epidemic prevention management in farms as the basis for judging the level of epidemic prevention management. The environmental monitoring data of the farm, the animal health monitoring data, and the assessment results of the current status of epidemic prevention and control are correlated and analyzed. Data mining algorithms are used to identify the correlation between various indicators. Based on the correlation analysis results, the weak links and risk points in the farm's epidemic prevention management were identified. For the identified risk points, expert system technology was used in conjunction with a pre-set epidemic prevention management knowledge base to generate suggestions for epidemic prevention management measures, which were then provided to the farm's management personnel.

5. The blockchain-based animal disease prevention and control method according to claim 1, characterized in that, The data stream of epidemic prevention implementation is compared with a preset list of epidemic prevention measures to determine the implementation status of the measures by setting thresholds and rules, including: For the data stream of epidemic prevention implementation and the list of epidemic prevention measures, a text similarity algorithm is used for comparison to obtain a similarity score; Based on a preset threshold, it is determined whether the similarity score exceeds the threshold. If the similarity score exceeds the threshold, it is determined that the epidemic prevention measures have been implemented effectively. If the similarity score does not exceed the threshold, it is determined that the epidemic prevention measures have not been implemented effectively. By establishing rules and comprehensively assessing the implementation status of several epidemic prevention measures, the overall degree of implementation of epidemic prevention measures can be determined. Based on the assessment results, a report on the implementation of epidemic prevention measures will be generated.

6. The blockchain-based animal disease prevention and control method according to claim 1, characterized in that, The process of generating the epidemic prevention effectiveness evaluation report includes: Acquire data streams on epidemic prevention implementation and the status of epidemic prevention measures implementation, preprocess the data, and obtain a standardized dataset; Based on the evaluation index system for epidemic prevention effectiveness, relevant features are selected from the standardized dataset to construct the training dataset for the random forest model. The training dataset was trained using the random forest algorithm, and the model parameters were optimized using cross-validation to obtain the optimal random forest model. The data stream of epidemic prevention implementation and the real-time data on the implementation of epidemic prevention measures are input into the optimal random forest model to predict and evaluate the epidemic prevention effect and output the prediction results. Based on the prediction results, determine whether the epidemic prevention effect has achieved the expected goal. If not, analyze the key factors affecting the epidemic prevention effect, propose suggestions for improving the epidemic prevention measures, and provide feedback to relevant departments to optimize the epidemic prevention implementation plan. Based on the evaluation results and improvement suggestions of the random forest model, the epidemic prevention effectiveness evaluation report is generated.

7. The blockchain-based animal disease prevention and control method according to claim 1, characterized in that, The epidemic prevention effectiveness assessment report and epidemic early warning information are encrypted, stored, and shared using blockchain technology, including: The epidemic prevention data is preprocessed, and based on the preset epidemic early warning indicator system, machine learning algorithms are used to model and analyze the epidemic prevention data to generate epidemic early warning information. The epidemic prevention effect assessment report and epidemic early warning information are formatted according to preset data standards, data fingerprints are generated through hash algorithms, and encrypted storage is performed using blockchain technology; Establish a blockchain-based epidemic prevention data sharing mechanism, connect with the data interfaces of relevant departments, control data access permissions through smart contracts, and achieve secure data sharing across departments and regions.

8. A blockchain-based animal disease prevention and control system, characterized in that, include: The basic database construction module is used to build the basic database for the farm; The disease prevention schedule creation module is used to create a disease prevention schedule based on the farm's basic database, combined with the characteristics of animal species and geographical location and climate conditions, and to determine the disease prevention time nodes for each farm. The determination of the disease prevention timeline for the aforementioned farm includes: Based on the animal species and geographical location information in the basic database of the farms, obtain the animal characteristics and climate conditions data for each farm; By performing cluster analysis on animal species characteristic data, animal species with similar characteristics are divided into the same category, resulting in several groups. A unified epidemic prevention schedule is then developed for animals in the same group. Based on the geographical location of the farm, historical climate data of the farm's location is obtained. Through time series analysis, the climate change trend of the corresponding region of the farm's location is predicted within a preset time period. Based on the climate prediction data of the farm's location, the disease prevention schedule for animal species is adjusted in a personalized manner to obtain disease prevention time nodes suitable for different farms. The data acquisition module is used to collect farm environmental data, animal health data, and epidemic prevention operation records in real time through IoT devices, generate epidemic prevention execution data streams, and generate epidemic early warning information based on the epidemic prevention execution data streams and threshold judgment results. The epidemic prevention measures comparison module is used to compare the epidemic prevention execution data stream with a preset epidemic prevention measures execution list, and to determine the implementation status of the epidemic prevention measures by setting thresholds and rules. The epidemic prevention effect analysis module is used to analyze the epidemic prevention effect using a random forest algorithm based on the epidemic prevention execution data stream and the implementation status of the epidemic prevention measures, and generate an epidemic prevention effect evaluation report. The data encryption storage module is used to encrypt, store, and share the epidemic prevention effect assessment report and epidemic early warning information using blockchain technology.

Images