Intelligent epidemic prevention method and system for livestock breeding

Abstract

The invention discloses an intelligent epidemic prevention method and system for livestock breeding. The epidemic prevention method comprises the following steps: constructing a livestock electronic archive database; collecting livestock characteristic data, evaluating the livestock health condition in combination with a livestock electronic archive database, and obtaining an evaluation result; according to an evaluation result, a machine learning algorithm is adopted to generate a personalized epidemic prevention scheme, and the personalized epidemic prevention scheme is pushed to epidemic prevention personnel for execution through the mobile terminal; epidemic prevention personnel perform epidemic prevention according to the corresponding personalized epidemic prevention scheme and upload epidemic prevention process data to a data center; and the data center stores and analyzes the epidemic prevention process data, and intelligently generates an epidemic disease emergency plan in combination with the actual condition of the farm. According to the invention, each livestock is endowed with a unique identity label, and livestock growth and development data and the like are collected in real time in combination with the Internet of Things equipment, so that a personalized epidemic prevention scheme is formulated in a targeted manner.

Description

Technical Field

[0001] The present invention belongs to the field of information processing technology, and in particular relates to an intelligent epidemic prevention method and system for animal husbandry. Background Art

[0002] In large-scale livestock farms, due to the large number and variety of livestock, it is difficult for managers to carry out fine management and traceability of the growth and development status, vaccination history, medication records, etc. of each livestock. The extensive management model currently used can only provide unified immunization and treatment for livestock in a general manner, and cannot meet the personalized epidemic prevention needs of livestock at different growth stages and in different health conditions. At the same time, due to the lack of digital information management methods, it is difficult for farm managers to grasp the epidemic prevention status of each livestock in a timely and accurate manner. Once an epidemic occurs, it is difficult to quickly lock the source of infection and take effective isolation and control measures, which can easily cause the epidemic to spread over a large area in the farm. Therefore, there is an urgent need for an intelligent epidemic prevention method and system for animal husbandry. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes an intelligent epidemic prevention method and system for animal husbandry. By giving each livestock a unique identity, combining the Internet of Things devices to collect livestock growth and development data in real time, a personalized epidemic prevention plan is formulated in a targeted manner, and the entire epidemic prevention process is digitally recorded and intelligently managed, thereby curbing the spread of the disease at the source and maximizing the biosafety of the farm.

[0004] The present invention provides an intelligent epidemic prevention method for animal husbandry, comprising:

[0005] Constructing electronic livestock archive database;

[0006] Collect livestock characteristic data, evaluate livestock health status in combination with the livestock electronic archive database, and obtain evaluation results;

[0007] Based on the evaluation results, a machine learning algorithm is used to generate a personalized epidemic prevention plan, and the plan is pushed to epidemic prevention personnel for execution via a mobile terminal;

[0008] The epidemic prevention personnel carry out epidemic prevention according to the corresponding personalized epidemic prevention plan, and upload the epidemic prevention process data to the data center;

[0009] The data center stores and analyzes the epidemic prevention process data, and intelligently generates an epidemic emergency plan based on the actual situation of the farm.

[0010] Optionally, building an electronic livestock archive database includes:

[0011] Collect the unique identification information of livestock through RFID electronic tags, and transmit the collected identification information to the database system for storage;

[0012] The livestock's growth and development data, livestock's vaccination history data, and livestock's medication record data are obtained, and the obtained data are associated with the livestock's unique identity identifier and stored in the corresponding electronic file in the database.

[0013] Optionally, collecting livestock characteristic data and evaluating livestock health status in combination with the livestock electronic archive database includes:

[0014] Use IoT devices to collect data on livestock growth environment parameters and behavioral characteristics;

[0015] Comprehensively analyze the environmental parameters and behavioral characteristics data collected in real time with the historical data in the livestock electronic archive database to build a livestock health assessment model;

[0016] Using a machine learning algorithm to train the livestock health assessment model to score the health status of the livestock based on environmental parameters, behavioral characteristics, and historical data;

[0017] When the score is lower than a threshold, it is determined that the livestock health condition is abnormal and a warning message is generated.

[0018] Optionally, based on the evaluation results, a machine learning algorithm is used to generate a personalized epidemic prevention plan, which is pushed to epidemic prevention personnel through a mobile terminal for execution, including:

[0019] Obtain relevant data and pre-process them according to livestock breed, growth stage and health status factors to obtain a standardized data set;

[0020] The decision tree algorithm is used to train the data set, and the decision tree model is obtained through feature selection and classification rule generation;

[0021] The support vector machine algorithm is used to train the data set, and the support vector machine model is obtained by finding the optimal classification hyperplane;

[0022] The decision tree model and the support vector machine model are integrated and a weighted average method is adopted to obtain an integrated learning model;

[0023] Based on the integrated learning model and combined with the characteristic data of individual livestock, the category to which they belong is determined and a personalized epidemic prevention plan is determined.

[0024] Optionally, based on the integrated learning model and combined with the characteristic data of individual livestock, the category to which the livestock belongs is determined, and a personalized epidemic prevention plan is determined, including:

[0025] Obtain characteristic data of individual livestock;

[0026] Using machine learning models, the characteristic data of individual livestock are trained to obtain an integrated learning model;

[0027] Input the individual characteristic data of livestock to be determined into the trained integrated learning model, and combine the prediction results of multiple models to obtain the determination result of the category to which the corresponding livestock individual belongs;

[0028] Determine the category to which the individual livestock belongs based on the determination result, and obtain the corresponding personalized epidemic prevention plan from the pre-established knowledge base of epidemic prevention plans for each category;

[0029] The vaccine type, vaccination time and dosage information in the personalized epidemic prevention plan are extracted to generate a vaccination plan for the corresponding livestock individuals.

[0030] Optionally, the epidemic prevention personnel performs epidemic prevention according to the corresponding personalized epidemic prevention plan, and uploads epidemic prevention process data to the data center, including:

[0031] According to the livestock's electronic tag information and the corresponding personalized epidemic prevention plan, determine the epidemic prevention operations that need to be performed on the corresponding livestock;

[0032] If vaccination is included in the epidemic prevention plan, the type and dosage of the vaccine to be vaccinated should be recorded using a mobile terminal according to the standard process, and the vaccination data should be uploaded to the data center;

[0033] If the epidemic prevention plan includes drug treatment, the type and dosage of the drug should be recorded using a mobile terminal according to standard procedures, and the medication data should be uploaded to the data center.

[0034] Optionally, the data center stores and analyzes the epidemic prevention process data, and intelligently generates an epidemic emergency plan based on the actual situation of the farm, including:

[0035] Based on the collected livestock disease-related data, a disease knowledge graph is constructed to associate and integrate disease symptoms, causes, transmission routes, and prevention and control measures to form a structured disease knowledge base;

[0036] Through semantic analysis and association mining of the disease knowledge graph, the correlation and distinction between different diseases are identified. Based on the actual situation of the farm, knowledge reasoning technology is used to infer the possibility and potential risks of the disease and predict the trend of the epidemic.

[0037] Based on the predicted epidemic trend, targeted epidemic emergency plans are automatically generated.

[0038] The present invention also provides an intelligent epidemic prevention system for animal husbandry, comprising: a database construction module, a monitoring and evaluation module, a personalized epidemic prevention program generation module, an epidemic prevention operation module and a data analysis module;

[0039] The database construction module is used to construct an animal husbandry electronic archive database;

[0040] The monitoring and evaluation module is used to collect livestock characteristic data and evaluate the livestock health status in combination with the livestock electronic archive database;

[0041] The personalized epidemic prevention plan generation module is used to generate a personalized epidemic prevention plan using a machine learning algorithm and push it to the epidemic prevention personnel for execution through a mobile terminal;

[0042] The epidemic prevention operation module is used to perform epidemic prevention according to the corresponding personalized epidemic prevention plan and upload epidemic prevention process data to the data center;

[0043] The data analysis module is used to store and analyze the epidemic prevention process data, and intelligently generate an epidemic emergency plan based on the actual situation of the farm.

[0044] Compared with the prior art, the present invention has the following advantages and technical effects: the present invention assigns a unique identity to each livestock through an RFID electronic tag, constructs an electronic archive database for livestock, and realizes digital management and traceability of information. The Internet of Things devices are used to collect livestock growth environment parameters and behavioral characteristics data in real time, and a comprehensive analysis is performed in combination with electronic archives to evaluate the health status of livestock. A machine learning algorithm is used to automatically generate a personalized epidemic prevention plan, and the plan is pushed to the epidemic prevention personnel for execution through a mobile terminal application. The epidemic prevention process data is uploaded to the data center in real time for analysis, and an epidemic prevention work report is generated. When the symptoms of the epidemic are monitored, the present invention automatically warns and prompts to take emergency measures, uses graph database technology to analyze the epidemic transmission chain, and guides precise isolation and disinfection. By constructing an epidemic knowledge map, an emergency plan is intelligently generated to guide the epidemic disposal work. The present invention realizes the intelligent and precise management of livestock epidemic prevention work, effectively improves the efficiency of epidemic prevention, reduces the risk of epidemics, and ensures the biosafety of farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 It is a flow chart of an intelligent epidemic prevention method for animal husbandry according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0048] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0049] The professional terms involved in the embodiments are explained below:

[0050] Animal husbandry technology involves many aspects, including feed management, disease prevention and control, environmental control, and specific breeding techniques and methods.

[0051] Feed management:

[0052] Feed management is a very important part in animal husbandry. For growing and fattening pigs, feed costs account for 70% of the total expenditure, so it is crucial to select and manage feed properly. A nutritionally complete feed ratio can ensure that pigs get enough nutrition and avoid problems such as low immunity. The all-in, all-out feeding management model can effectively control infectious diseases. By maintaining a reasonable stocking density and strengthening ventilation, the incidence of diseases can be effectively reduced, thereby improving economic benefits.

[0053] Disease prevention and control:

[0054] Disease prevention and control is an important part of animal husbandry. Maintaining a reasonable stocking density and ventilation can effectively reduce the occurrence of respiratory diseases. In addition, reasonable medication methods are also an important means of disease prevention and control. It is necessary to abide by national laws and regulations, avoid the use of banned drugs, and ensure the health of pigs.

[0055] Environmental Control:

[0056] Environmental control is crucial to the success of animal husbandry. Maintaining a reasonable stocking density, strengthening ventilation, cooling measures (such as water curtain cooling, roof spraying, etc.) and ensuring sufficient drinking water can improve the comfort of pigs, reduce stress reactions, and thus improve production efficiency.

[0057] Specific breeding techniques:

[0058] Fermentation bed ecological breeding technology: By building a fermentation bed, beneficial microbial flora are used to synthesize nutrients from bedding and feces, enhancing the disease resistance of livestock and promoting healthy growth. This technology can not only eliminate odors, but also inhibit pests and pathogens. It is an environmentally friendly and efficient breeding method.

[0059] Early weaning technology: Through scientific sow preventive health care, early piglet feeding and scientific weaning methods, weaning stress and diarrhea can be reduced, and the survival rate and growth rate of piglets can be improved.

[0060] All-in, all-out: By introducing and eliminating livestock at the same time, diseases are prevented from spreading within the herd, improving overall health.

[0061] Smart epidemic prevention technologies mainly include the following:

[0062] Artificial Intelligence (AI) Technology:

[0063] Intelligent Voice Assistant: Develop an intelligent outbound calling platform to reduce the risk of door-to-door screening by primary care staff and improve prevention and control efficiency.

[0064] Intelligent medical assistance robots: Deliver meals, daily necessities and medical supplies in isolation wards to reduce the burden on medical staff.

[0065] Cleaning and disinfection robot: autonomously locates the hospital environment, avoids crowded areas, and completes cleaning tasks.

[0066] Drone: used for aerial disinfection to improve disinfection efficiency.

[0067] Big Data Technologies:

[0068] 5G Technology:

[0069] 5G Telemedicine Cart: Experts from outside the province diagnose patients in quarantine areas through the telemedicine system.

[0070] 5G medical temperature measurement patrol robot: used for infrared temperature measurement screening and prevention and control command.

[0071] Robotics:

[0072] Food delivery robot: provides catering services to quarantine points 24 hours a day.

[0073] Unmanned delivery vehicle: responsible for delivering goods and reducing human contact.

[0074] IoT Technology:

[0075] Smart access control system: contactless access is achieved through mobile phone APP, reducing human contact.

[0076] Garbage overflow recognition system: uses cameras and background algorithms to identify garbage overflow and clean it up in a timely manner.

[0077] These technologies not only improve the efficiency and accuracy of epidemic prevention work, but also greatly reduce the risk of cross-infection.

[0078] This embodiment proposes an intelligent epidemic prevention method for animal husbandry, such as Figure 1 As shown, the specific steps include:

[0079] Constructing electronic livestock archive database;

[0080] Collect livestock characteristic data, evaluate livestock health status in combination with the livestock electronic archive database, and obtain evaluation results;

[0081] Based on the evaluation results, a machine learning algorithm is used to generate a personalized epidemic prevention plan, which is then pushed to epidemic prevention personnel for execution via mobile terminals;

[0082] Epidemic prevention personnel carry out epidemic prevention according to the corresponding personalized epidemic prevention plan and upload the epidemic prevention process data to the data center;

[0083] The data center stores and analyzes the epidemic prevention process data, and intelligently generates epidemic emergency plans based on the actual situation of the farms.

[0084] Furthermore, each livestock is given a unique identity through RFID electronic tags, and the identity is associated with the livestock's growth and development data, vaccination history, medication records and other information to build an electronic livestock archive database to achieve digital management and traceability of livestock information;

[0085] Use IoT devices such as temperature and humidity sensors, cameras, etc. to collect data on livestock growth environment parameters and behavioral characteristics in real time, transmit them to the data center via wireless networks, and conduct comprehensive analysis in combination with the livestock electronic archive database to assess livestock health and detect abnormal conditions in a timely manner;

[0086] Based on factors such as livestock breed, growth stage, and health status, machine learning algorithms such as decision trees and support vector machines are used to automatically generate personalized epidemic prevention plans, including vaccine type, vaccination time, and dosage, and push them to epidemic prevention personnel for execution through mobile terminal applications;

[0087] Epidemic prevention personnel use mobile terminal applications to scan livestock electronic tags, retrieve corresponding personalized epidemic prevention plans, carry out immunization, drug treatment and other epidemic prevention operations according to standard procedures, and upload epidemic prevention process data to the data center in real time;

[0088] The data center stores and analyzes epidemic prevention process data, uses big data technology and visualization tools to generate epidemic prevention work reports, intuitively displays the completion status of various epidemic prevention indicators, and provides data support for farm management decisions;

[0089] If the system detects disease symptoms in livestock in a certain area, it will automatically issue an alert and prompt management personnel to take emergency measures. Based on the electronic tag information of the sick livestock, it will quickly identify livestock that have close contact with the disease, use graph database technology to analyze the epidemic transmission chain, guide precise isolation and disinfection work, and prevent the further spread of the disease.

[0090] By constructing a livestock disease knowledge graph, integrating information such as disease symptoms, causes, transmission routes, and prevention and control measures, using knowledge reasoning technology and combining the actual conditions of the farms, we can intelligently generate disease emergency plans to guide emergency response work, minimize the impact of diseases on livestock production, and ensure the biosafety of farms.

[0091] Furthermore, the construction of the livestock electronic archive database includes:

[0092] Collect the unique identification information of livestock through RFID electronic tags, and transmit the collected identification information to the database system for storage;

[0093] The livestock's growth and development data, livestock's vaccination history data, and livestock's medication record data are obtained, and the obtained data are associated with the livestock's unique identity identifier and stored in the corresponding electronic file in the database.

[0094] Specifically, the unique identification information of livestock is collected through RFID electronic tags, and the collected identification information is transmitted to the database system for storage. The growth and development data of livestock, including information such as weight, body shape, and health status, are obtained, and the obtained data is associated with the unique identification of livestock, and stored in the corresponding electronic file in the database. The vaccination history data of livestock is obtained, including information such as vaccine type, vaccination time, and vaccination dosage, and the obtained data is associated with the unique identification of livestock, and stored in the corresponding electronic file in the database. The medication record data of livestock is obtained, including information such as drug name, medication time, and medication dosage, and the obtained data is associated with the unique identification of livestock, and stored in the corresponding electronic file in the database. According to the unique identification of livestock, the electronic file information of the livestock is obtained from the database, and the obtained information is digitized to generate digital management information such as livestock growth and development curves, vaccination timelines, and medication record reports. The data mining algorithm is used to analyze the livestock electronic file data, and information such as livestock growth and development laws, epidemic trends, and medication effect evaluation are mined to provide data support for livestock breeding management. Based on the unique identity of livestock, a livestock traceability tracking system is built to realize traceability query of livestock growth process, vaccination, medication status and other information to ensure the quality and safety of livestock products.

[0095] Furthermore, livestock characteristic data is collected and combined with the livestock electronic archive database to assess livestock health status, including:

[0096] Use IoT devices to collect data on livestock growth environment parameters and behavioral characteristics;

[0097] Comprehensively analyze the environmental parameters and behavioral characteristics data collected in real time with the historical data in the livestock electronic archive database to build a livestock health assessment model;

[0098] Using machine learning algorithms to train livestock health assessment models to score livestock health based on environmental parameters, behavioral characteristics, and historical data;

[0099] When the score is lower than the threshold, it is judged that the livestock health status is abnormal and an early warning message is generated.

[0100] Specifically, IoT devices such as temperature and humidity sensors and cameras are deployed in livestock breeding sites to collect livestock growth environment parameters and behavioral characteristics data in real time. The collected environmental parameters and behavioral characteristics data are transmitted to the data center in real time through wireless network devices deployed in the breeding sites. An electronic livestock archive database is established in the data center to store historical data such as basic information of livestock, growth and development records, and immunization and epidemic prevention records. The environmental parameters and behavioral characteristics data collected in real time are comprehensively analyzed with the historical data in the livestock electronic archive database to construct a livestock health assessment model. The livestock health assessment model is trained using machine learning algorithms such as support vector machines and random forests to score the health status of livestock based on environmental parameters, behavioral characteristics and historical data. A threshold for livestock health scores is set. When the score is lower than the threshold, it is judged that the livestock health status is abnormal and an early warning message is generated. The livestock health status assessment results and abnormal early warning information are pushed to the breeding staff in real time to facilitate timely response measures to ensure livestock health.

[0101] Furthermore, based on the evaluation results, a machine learning algorithm is used to generate a personalized epidemic prevention plan, which is pushed to epidemic prevention personnel through mobile terminals for execution, including:

[0102] Obtain relevant data and pre-process them according to livestock breed, growth stage and health status factors to obtain a standardized data set;

[0103] The decision tree algorithm is used to train the data set, and the decision tree model is obtained through feature selection and classification rule generation;

[0104] The support vector machine algorithm is used to train the data set, and the support vector machine model is obtained by finding the optimal classification hyperplane;

[0105] The decision tree model and the support vector machine model are integrated and a weighted average method is adopted to obtain an integrated learning model;

[0106] Based on the integrated learning model and combined with the characteristic data of individual livestock, the category to which they belong is determined and a personalized epidemic prevention plan is determined.

[0107] Specifically, according to factors such as livestock breed, growth stage and health status, relevant data is obtained and preprocessed to obtain a standardized data set. The decision tree algorithm is used to train the data set, and the decision tree model is obtained through feature selection and classification rule generation. The support vector machine algorithm is used to train the data set, and the support vector machine model is obtained by finding the optimal classification hyperplane. The decision tree model and the support vector machine model are integrated, and the weighted average method is used to obtain an integrated learning model. According to the integrated learning model, combined with the characteristic data of individual livestock, the category to which it belongs is judged, and a personalized epidemic prevention plan is determined, including vaccine type, vaccination time and dosage. The generated personalized epidemic prevention plan is pushed to epidemic prevention personnel through mobile terminal applications, and a visual operation interface is provided for epidemic prevention personnel to view and execute. During the implementation of the epidemic prevention plan, the health status data of livestock is continuously collected, and the model is optimized and updated through the feedback mechanism to continuously improve the accuracy and effectiveness of the epidemic prevention plan.

[0108] Furthermore, based on the integrated learning model, combined with the characteristic data of individual livestock, the category to which they belong is determined, and the personalized epidemic prevention plan is determined, including:

[0109] Obtain characteristic data of individual livestock;

[0110] Using machine learning models, the characteristic data of individual livestock are trained to obtain an integrated learning model;

[0111] Input the individual characteristic data of livestock to be determined into the trained integrated learning model, and combine the prediction results of multiple models to obtain the determination result of the category to which the corresponding livestock individual belongs;

[0112] Determine the category to which the individual livestock belongs based on the determination result, and obtain the corresponding personalized epidemic prevention plan from the pre-established knowledge base of epidemic prevention plans for each category;

[0113] Extract information such as vaccine type, vaccination time and dosage from the personalized epidemic prevention plan to generate a vaccination plan for the corresponding livestock individuals.

[0114] Specifically, based on the integrated learning model and combined with the characteristic data of individual livestock, the category to which they belong is determined and a personalized epidemic prevention plan is determined, including the type of vaccine, vaccination time and dosage.

[0115] The characteristic data of individual livestock, including age, weight, health status and other information, are obtained as the input of the integrated learning model. Multiple machine learning models such as random forest, support vector machine and neural network are used to train and test the characteristic data of individual livestock to obtain the integrated learning model. The characteristic data of the individual livestock to be judged are input into the trained integrated learning model, and the prediction results of multiple models are combined to obtain the judgment result of the category to which the individual livestock belongs. According to the judgment result, the category to which the individual livestock belongs is determined, and the personalized epidemic prevention plan corresponding to the category is obtained from the pre-established knowledge base of epidemic prevention plans for each category. The information such as vaccine type, vaccination time and dosage in the personalized epidemic prevention plan is extracted to generate a vaccination plan for the individual livestock. If the characteristics such as the health status of the individual livestock are significantly different from the typical characteristics of the category to which it belongs, the personalized epidemic prevention plan is appropriately adjusted, such as adjusting the vaccine dosage or vaccination time. The formulated vaccination plan is sent to the vaccination personnel, and the information such as the personalized epidemic prevention plan is entered into the livestock health record database for subsequent health management and effect tracking analysis.

[0116] Furthermore, the epidemic prevention personnel carry out epidemic prevention according to the corresponding personalized epidemic prevention plan, and upload the epidemic prevention process data to the data center including:

[0117] According to the livestock's electronic tag information and the corresponding personalized epidemic prevention plan, determine the epidemic prevention operations that need to be performed on the corresponding livestock;

[0118] If vaccination is included in the epidemic prevention plan, the type and dosage of the vaccine to be vaccinated should be recorded using a mobile terminal according to the standard process, and the vaccination data should be uploaded to the data center;

[0119] If the epidemic prevention plan includes drug treatment, the type and dosage of the drug should be recorded using a mobile terminal according to standard procedures, and the medication data should be uploaded to the data center.

[0120] Specifically, according to the electronic tag information of the livestock, the personalized epidemic prevention plan of the livestock is obtained from the data center to determine which epidemic prevention operations the livestock needs to perform. If the epidemic prevention plan includes immunization, the type and dosage of the vaccine for immunization are recorded using a mobile terminal according to the standard process, and the vaccination data is uploaded to the data center. If the epidemic prevention plan includes drug treatment, the type and dosage of the drug are recorded using a mobile terminal according to the standard process, and the drug use data is uploaded to the data center. According to the data collected during the epidemic prevention process, the health status of the livestock is evaluated using a machine learning algorithm to obtain a health score. According to the health score, the decision tree algorithm is used to determine whether the livestock needs to be isolated for observation or further treatment, and the decision results are pushed to the epidemic prevention personnel. According to the epidemic prevention process data and health assessment results, the association rule mining algorithm is used to analyze the correlation between different epidemic prevention measures and optimize the personalized epidemic prevention plan. The optimized personalized epidemic prevention plan is uploaded to the data center for reference in subsequent epidemic prevention work, and the epidemic prevention plan is continuously iterated and optimized based on new epidemic prevention data.

[0121] Furthermore, the data center stores and analyzes the epidemic prevention process data, and based on the actual situation of the farm, intelligently generates an epidemic emergency plan including:

[0122] Based on the collected livestock disease-related data, a disease knowledge graph is constructed to associate and integrate information such as disease symptoms, causes of disease, transmission routes, and prevention and control measures to form a structured disease knowledge base;

[0123] Through semantic analysis and association mining of the disease knowledge graph, the correlation and distinction between different diseases are identified. Based on the actual situation of the farm, knowledge reasoning technology is used to infer the possibility and potential risks of the disease and predict the trend of the epidemic.

[0124] Based on the predicted epidemic trend, targeted epidemic emergency plans are automatically generated.

[0125] Specifically, according to the epidemic prevention process of the farm, relevant epidemic prevention data is obtained and stored in the data center. The epidemic prevention data stored in the data center is cleaned and preprocessed to remove noise data and ensure data quality. The preprocessed epidemic prevention data is analyzed using big data technology, including cluster analysis, association analysis, etc., to mine the hidden patterns and laws in the data. Through machine learning algorithms such as decision trees and support vector machines, an epidemic prevention index prediction model is established to predict the completion of epidemic prevention indicators in the future. Natural language processing technology is used to understand and analyze the decision-making needs of farm managers, and an epidemic prevention data analysis report that meets the management decision needs is automatically generated. Using visualization technology, the epidemic prevention data analysis results are presented in intuitive forms such as charts and maps, and epidemic prevention reports are generated to facilitate managers to quickly understand the completion of epidemic prevention work. The epidemic prevention report and related data analysis results are integrated into the farm management decision support system to provide managers with real-time and comprehensive data support to assist scientific decision-making.

[0126] By deploying sensors and monitoring equipment in livestock breeding areas, the physiological parameters and behavioral data of livestock are collected in real time. If abnormal data is found to exceed the preset threshold, an epidemic warning is triggered. According to the warning information, the system automatically sends an alarm notification to the management personnel, prompting them to take emergency measures. After receiving the alarm, the management personnel can remotely view the details of the epidemic and the information of sick livestock through the mobile app. The electronic tags worn by sick livestock record their individual ID, breeding area, other livestock they have contacted, and other information. By analyzing the electronic tag data, the system quickly locks the livestock that have close contact with the sick livestock. The electronic tag data is imported into the graph database, and the epidemic transmission relationship diagram is constructed with individual livestock as nodes and contact relationships as edges. The transmission path and transmission risk are analyzed through the graph algorithm to identify the key node livestock in the transmission chain. According to the analysis results of the epidemic transmission relationship diagram, the scope and priority of livestock that need to be isolated are determined. The electronic fence technology is used to accurately divide the isolation area, and the isolation instruction is issued to the intelligent breeding equipment. Comprehensive disinfection work is carried out in the isolation area to control the spread of the epidemic. The disinfection process is automatically performed by the intelligent disinfection robot, and RFID identification technology is used to ensure that each area is thoroughly disinfected. Continue to monitor the epidemic situation and adjust the isolation scope in a timely manner according to the isolation effect and new cases. Update the monitoring data and the graph database synchronously, continuously optimize the transmission chain analysis model, and provide support for the next step of prevention and control decision-making.

[0127] Based on the collected data on livestock diseases, a disease knowledge graph is constructed to associate and integrate information such as disease symptoms, causes of disease, transmission routes, and prevention and control measures to form a structured disease knowledge base. By performing semantic analysis and association mining on the disease knowledge graph, the correlation and distinction between different diseases are identified, revealing the inherent laws and evolution trends of the occurrence and development of diseases. Using knowledge reasoning technology, the possibility and potential risks of disease occurrence are inferred based on the actual situation of the farm, such as breeding varieties, scale, environment and other factors, and the trend of the epidemic is predicted. Based on the reasoning results, targeted disease emergency plans are automatically generated, including epidemic monitoring, blocking transmission, isolation of sick animals, drug prevention and control and other measures, forming a complete set of disease response plans. The emergency plan is converted into executable processes and instructions, and the biosafety status of the farm is monitored in real time through the intelligent epidemic emergency command system, and epidemic risks are discovered and warned in a timely manner. Once an epidemic occurs, the system can quickly activate the emergency response mechanism, automatically allocate resources and personnel according to the plan, coordinate various departments to carry out emergency response work, and control the spread of the epidemic. During the emergency response process, we continuously optimize and improve the epidemic knowledge map and emergency plan, continuously improve the intelligence and practicality of the system, build a long-term epidemic prevention and control system for farms, and maximize the safety of aquaculture production.

[0128] This embodiment also provides an intelligent epidemic prevention system for animal husbandry, including: a database construction module, a monitoring and evaluation module, a personalized epidemic prevention plan generation module, an epidemic prevention operation module and a data analysis module;

[0129] Database construction module, used to build livestock electronic archive database;

[0130] The monitoring and evaluation module is used to collect livestock characteristic data and evaluate the livestock health status in combination with the livestock electronic archive database;

[0131] A personalized epidemic prevention plan generation module is used to generate personalized epidemic prevention plans using machine learning algorithms and push them to epidemic prevention personnel for execution through mobile terminals;

[0132] The epidemic prevention operation module is used to carry out epidemic prevention according to the corresponding personalized epidemic prevention plan and upload the epidemic prevention process data to the data center;

[0133] The data analysis module is used to store and analyze epidemic prevention process data, and intelligently generate epidemic emergency plans based on the actual situation of the farm.

[0134] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent epidemic prevention method for animal husbandry, characterized in that: include: Constructing electronic livestock archive database; Collect livestock characteristic data, evaluate livestock health status in combination with the livestock electronic archive database, and obtain evaluation results; Based on the evaluation results, a machine learning algorithm is used to generate a personalized epidemic prevention plan, and the plan is pushed to epidemic prevention personnel for execution via a mobile terminal; The epidemic prevention personnel carry out epidemic prevention according to the corresponding personalized epidemic prevention plan, and upload the epidemic prevention process data to the data center; The data center stores and analyzes the epidemic prevention process data, and intelligently generates an epidemic emergency plan based on the actual situation of the farm.

2. The intelligent epidemic prevention method for animal husbandry according to claim 1, characterized in that: The construction of livestock electronic archive database includes: Collect the unique identification information of livestock through RFID electronic tags, and transmit the collected identification information to the database system for storage; The livestock's growth and development data, livestock's vaccination history data, and livestock's medication record data are obtained, and the obtained data are associated with the livestock's unique identity identifier and stored in the corresponding electronic file in the database.

3. The intelligent epidemic prevention method for animal husbandry according to claim 2, characterized in that: Collecting livestock characteristic data and evaluating livestock health status in combination with the livestock electronic archive database include: Use IoT devices to collect data on livestock growth environment parameters and behavioral characteristics; Comprehensively analyze the environmental parameters and behavioral characteristics data collected in real time with the historical data in the livestock electronic archive database to build a livestock health assessment model; Using a machine learning algorithm to train the livestock health assessment model to score the health status of the livestock based on environmental parameters, behavioral characteristics, and historical data; When the score is lower than a threshold, it is determined that the livestock health condition is abnormal and a warning message is generated.

4. The intelligent epidemic prevention method for animal husbandry according to claim 3, characterized in that: Based on the evaluation results, a machine learning algorithm is used to generate a personalized epidemic prevention plan, which is pushed to epidemic prevention personnel through mobile terminals for execution, including: Obtain relevant data and pre-process them according to livestock breed, growth stage and health status factors to obtain a standardized data set; The decision tree algorithm is used to train the data set, and the decision tree model is obtained through feature selection and classification rule generation; The support vector machine algorithm is used to train the data set, and the support vector machine model is obtained by finding the optimal classification hyperplane; The decision tree model and the support vector machine model are integrated and a weighted average method is adopted to obtain an integrated learning model; Based on the integrated learning model and combined with the characteristic data of individual livestock, the category to which they belong is determined and a personalized epidemic prevention plan is determined.

5. The intelligent epidemic prevention method for animal husbandry according to claim 4, characterized in that: Based on the integrated learning model, combined with the characteristic data of individual livestock, the category to which they belong is determined, and the personalized epidemic prevention plan is determined, including: Obtaining characteristic data of individual livestock; Using machine learning models, the characteristic data of individual livestock are trained to obtain an integrated learning model; Input the individual characteristic data of livestock to be determined into the trained integrated learning model, and combine the prediction results of multiple models to obtain the determination result of the category to which the corresponding livestock individual belongs; Determine the category to which the individual livestock belongs based on the determination result, and obtain the corresponding personalized epidemic prevention plan from the pre-established knowledge base of epidemic prevention plans for each category; The vaccine type, vaccination time and dosage information in the personalized epidemic prevention plan are extracted to generate a vaccination plan for the corresponding livestock individuals.

6. The intelligent epidemic prevention method for animal husbandry according to claim 5, characterized in that: The epidemic prevention personnel carry out epidemic prevention according to the corresponding personalized epidemic prevention plan, and upload the epidemic prevention process data to the data center, including: According to the livestock's electronic tag information and the corresponding personalized epidemic prevention plan, determine the epidemic prevention operations that need to be performed on the corresponding livestock; If vaccination is included in the epidemic prevention plan, the type and dosage of the vaccine to be vaccinated should be recorded using a mobile terminal according to the standard process, and the vaccination data should be uploaded to the data center; If the epidemic prevention plan includes drug treatment, the type and dosage of the drug should be recorded using a mobile terminal according to standard procedures, and the medication data should be uploaded to the data center.

7. The intelligent epidemic prevention method for animal husbandry according to claim 6, characterized in that: The data center stores and analyzes the epidemic prevention process data, and intelligently generates an epidemic emergency plan based on the actual situation of the farm, including: Based on the collected livestock disease-related data, a disease knowledge graph is constructed to associate and integrate information on disease symptoms, causes of disease, transmission routes, and prevention and control measures to form a structured disease knowledge base; Through semantic analysis and association mining of the disease knowledge graph, the correlation and distinction between different diseases are identified. Based on the actual situation of the farm, knowledge reasoning technology is used to infer the possibility and potential risks of the disease and predict the trend of the epidemic. Based on the predicted epidemic trend, targeted epidemic emergency plans are automatically generated.

8. An intelligent epidemic prevention system for animal husbandry, characterized in that: include: Database construction module, monitoring and evaluation module, personalized epidemic prevention plan generation module, epidemic prevention operation module and data analysis module; The database construction module is used to construct an animal husbandry electronic archive database; The monitoring and evaluation module is used to collect livestock characteristic data and evaluate the livestock health status in combination with the livestock electronic archive database; The personalized epidemic prevention plan generation module is used to generate a personalized epidemic prevention plan using a machine learning algorithm and push it to the epidemic prevention personnel for execution through a mobile terminal; The epidemic prevention operation module is used to perform epidemic prevention according to the corresponding personalized epidemic prevention plan and upload epidemic prevention process data to the data center; The data analysis module is used to store and analyze the epidemic prevention process data, and intelligently generate an epidemic emergency plan based on the actual situation of the farm.

Images