Livestock and poultry vaccination management method and system based on Internet of Things

Abstract

The invention discloses a livestock and poultry vaccination management method and system based on the Internet of Things. The method comprises the steps that electronic ear tag information of livestock and poultry is acquired, attribute data of the livestock and poultry are combined, a personalized vaccination knowledge graph is established, a vaccination scheme is generated, and the vaccination time, dosage and part of each livestock and poultry are determined; according to the vaccination scheme, intelligent vaccination equipment is controlled to execute precise administration; vaccination process data is collected and uploaded to a cloud database in real time, and if it is found that vaccination data of a certain batch is abnormal, an early warning mechanism is started; carrying out statistical analysis on the vaccination process data, judging the immune failure risk, and marking high-risk individuals; a livestock and poultry epidemic disease prediction and early warning model is constructed, epidemic disease high-incidence periods and epidemic trends of livestock and poultry of different varieties and day ages are analyzed according to prediction results, a vaccination plan is automatically planned, and an inoculation strategy is dynamically adjusted. The stability and pertinence of the immune effect of livestock and poultry are improved, and the risk of epidemic diseases is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of livestock and poultry breeding management, and in particular to a livestock and poultry vaccination management method and system based on the Internet of Things. Background Art

[0002] In the livestock and poultry breeding process, since livestock and poultry of different breeds and different growth stages have different immune characteristics, it is necessary to develop personalized vaccination plans. However, in actual operations, farms usually raise livestock and poultry of multiple breeds and different ages. Large-scale group vaccination is difficult to take into account the specific conditions of each livestock and poultry, and it is easy to miss vaccinations, make mistakes, and repeat vaccinations, which affects the immune effect. At the same time, traditional manual vaccination methods are inefficient.

[0003] Livestock and poultry farms are in urgent need of an intelligent and information-based vaccination management system. The system needs to have the following functions: First, based on the Internet of Things technology, the identity information of each livestock and poultry is accurately identified by electronic ear tags and biometrics; second, personalized vaccination plans are automatically generated based on livestock and poultry breeds, age and other factors; third, the timing, quantitative and location of vaccine administration is achieved through intelligent vaccination equipment; fourth, vaccination data is uploaded to the cloud in real time and connected to the vaccine traceability system to facilitate vaccine quality traceability; fifth, the system must have abnormal situation monitoring and early warning functions, such as immune antibody level monitoring, to promptly detect individuals with immunization failure.

[0004] The realization of the above-mentioned intelligent vaccination system involves many key technologies such as IoT perception, big data analysis, automatic control, and remote communication, and the system integration is difficult. At the same time, the physiological characteristics of livestock and poultry vary greatly, and the immune mechanism is complex. The formulation of personalized immunization plans requires a large amount of experimental data support and expert experience guidance, and real-time optimization with changes in breeding varieties and feeding environments, which places high demands on intelligent algorithms. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a livestock and poultry vaccination management method and system based on the Internet of Things, which improves the stability and pertinence of livestock and poultry immunization effects, reduces the risk of epidemics, and provides new ideas for intelligent and refined modern animal husbandry.

[0006] On the one hand, to achieve the above-mentioned purpose, the present invention provides a livestock and poultry vaccination management method based on the Internet of Things, comprising:

[0007] Obtain livestock and poultry electronic ear tag information, combine livestock and poultry attribute data, establish a personalized vaccination knowledge map, generate vaccination plans, and determine the vaccination time, dosage, and site for each livestock and poultry;

[0008] According to the vaccination plan, controlling the smart vaccination device to perform precise drug administration;

[0009] Collect vaccination process data and upload it to the cloud database in real time. If abnormal data of a certain batch of vaccination is found, the early warning mechanism will be activated;

[0010] Performing statistical analysis on the vaccination process data to determine the risk of immunization failure and marking high-risk individuals;

[0011] Build a livestock and poultry disease prediction and early warning model, analyze the peak incidence periods and epidemic trends of diseases in livestock and poultry of different breeds and age groups based on the prediction results, automatically plan vaccination plans, and dynamically adjust vaccination strategies.

[0012] On the other hand, to achieve the above purpose, the present invention provides a livestock and poultry vaccination management system based on the Internet of Things, comprising:

[0013] Livestock and poultry electronic ear tag information collection module, used to obtain livestock and poultry electronic ear tag information;

[0014] A personalized vaccination knowledge graph construction module is used to combine livestock and poultry attribute data to build a personalized vaccination knowledge graph and generate a vaccination plan;

[0015] An intelligent vaccination control module, for controlling the intelligent vaccination device to perform precise drug administration according to the vaccination scheme;

[0016] The vaccination process data management module is used to collect vaccination process data and upload it to the cloud database in real time. If a batch of vaccination data is found to be abnormal, the early warning mechanism will be activated;

[0017] The livestock and poultry disease prediction and early warning model construction module is used to build a livestock and poultry disease prediction and early warning model, analyze the peak incidence and epidemic trends of diseases in livestock and poultry of different breeds and age groups based on the prediction results, automatically plan vaccination plans, and dynamically adjust vaccination strategies.

[0018] Compared with the prior art, the present invention has the following advantages and technical effects:

[0019] The present invention discloses a livestock and poultry vaccination management method and system based on the Internet of Things. The method obtains livestock and poultry electronic ear tag information and breeding environment parameters through the Internet of Things sensing technology, combines livestock and poultry breeds, growth stages and other attribute data, uses machine learning algorithms to establish personalized immunization knowledge graphs, automatically generates and dynamically adjusts vaccination plans, and controls intelligent devices to perform precise vaccination. The present invention also collects vaccination process data, performs statistical analysis on vaccination data, calculates immunization coverage and antibody levels, uses machine learning algorithms to determine the risk of immunization failure, and pushes early warning information to high-risk individuals. By continuously collecting livestock and poultry immune response data, using deep learning algorithms to continuously optimize personalized immunization knowledge graphs, and establishing livestock and poultry disease prediction and early warning models, the vaccination plan is automatically planned and dynamically adjusted to achieve precise prevention of diseases. The present invention improves the stability and pertinence of livestock and poultry immunization effects, reduces the risk of diseases, and provides new ideas and technical support for intelligent and refined modern animal husbandry. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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:

[0021] Figure 1 This is a flow chart of a livestock and poultry vaccination management method based on the Internet of Things according to an embodiment of the present invention;

[0022] Figure 2 This is a structural schematic diagram of a livestock and poultry vaccination management system based on the Internet of Things in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] 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.

[0027] At present, my country's animal vaccine market is mainly divided into two categories: compulsory immunization and non-compulsory immunization. Compulsory immunization vaccines are mainly purchased by the government through bidding and then distributed free of charge to farmers, supplemented by point-to-point sales to farms by vaccine manufacturers; non-compulsory immunization vaccines are all purchased on the market. In terms of major product types, vaccines such as foot-and-mouth disease, highly pathogenic avian influenza, and peste des petits ruminants are the main products on the market. The demand for these vaccines is affected by many factors such as the scale of animal husbandry, the prevalence of diseases, and farmers' awareness of epidemic prevention. In addition, with the continuous expansion of the pet market, pet vaccines have gradually become an important category in the market. The research and development of new vaccines and the optimization of production processes are important trends in the field of animal vaccines. For example, new vaccine technologies such as mRNA vaccines and viral vector vaccines continue to emerge, bringing new growth points to the veterinary vaccine market. These new vaccines not only improve the immune effect of vaccines, but also extend the protection period, further promoting the expansion of the market. However, the field of animal vaccines also faces some challenges. First, the research and development and production of vaccines require high investment and a long cycle, which limits the speed of research and development and market promotion of new vaccines. Secondly, the storage and transportation of vaccines require strict conditions. If the conditions are not met, the vaccine may become ineffective or have reduced effectiveness. In addition, farmers’ awareness and acceptance of vaccines are also important factors affecting market development. Some farmers are cautious about the use of vaccines due to lack of awareness of epidemic prevention or concerns about stress reactions caused by vaccines.

[0028] Animal husbandry is one of the largest demanders of animal vaccines. With the growth of the global population and the increasing demand for animal protein, the scale of animal husbandry continues to expand, and the demand for the prevention and control of animal diseases has also increased. Animal vaccines, as an important means of preventing and controlling animal diseases, play a vital role in animal husbandry. In order to ensure the healthy growth of livestock and poultry and the safety of their products, livestock and poultry breeding companies, cooperatives, and individual breeders in the animal husbandry industry will regularly vaccinate livestock and poultry.

[0029] In summary, the current livestock and poultry vaccine technology field shows a trend of expanding market scale, increasingly rich product types, continuous improvement of policies and regulations, and continuous technological innovation. However, it also faces challenges such as long R&D cycle, strict storage and transportation conditions, and farmers' cognitive acceptance. In the future, with the continuous advancement of science and technology and the continuous changes in market demand, the livestock and poultry vaccine field will usher in more development opportunities and challenges.

[0030] Based on the above technical status in the field, the present invention proposes a livestock and poultry vaccination management method based on the Internet of Things, such as Figure 1 ,include:

[0031] S101. Obtain livestock and poultry electronic ear tag information through Internet of Things sensing technology, combine it with attribute data such as livestock and poultry breeds and growth stages, use machine learning algorithms to establish a personalized immunization knowledge map, automatically generate targeted vaccination plans, and determine the vaccination time, dosage and site for each livestock and poultry.

[0032] The information of the electronic ear tags worn by livestock and poultry can be obtained through the Internet of Things sensing technology. This process can be achieved by installing a small RFID (radio frequency identification) tag on the ears of livestock and poultry. This tag can store the unique identification code of livestock and poultry, and when the livestock and poultry are close to the reader, the reader can automatically scan and read the information.

[0033] Access the pre-established livestock and poultry basic attribute database, and obtain the corresponding livestock and poultry breed, growth stage and other attribute data according to the unique livestock and poultry identification; input the obtained livestock and poultry attribute data into the pre-built personalized immunization knowledge graph system for matching, and the knowledge graph system uses a machine learning algorithm to intelligently generate a vaccination plan according to the livestock and poultry attributes; extract parameters such as vaccination time, vaccination dose and vaccination site from the generated vaccination plan, associate them with the livestock and poultry identification, and store them in the livestock and poultry immunization plan database; according to the current date, query the livestock and poultry identification, vaccine variety, vaccination dose and vaccination site that need to be immunized from the livestock and poultry immunization plan database; send the livestock and poultry identification, vaccine variety, vaccination dose and vaccination site that need to be vaccinated to the Internet of Things terminal device, prompting the breeder to vaccinate; after the vaccination is completed, collect the vaccination information through the Internet of Things terminal device, including the vaccinated livestock and poultry identification, vaccination time, vaccination vaccine, vaccination dose, vaccination site, etc., and transmit the collected vaccination information back to the system to update the livestock and poultry immunization record.

[0034] As an embodiment of the present invention, taking a beef cattle as an example, firstly, its unique identification code is obtained through the Internet of Things sensing technology, such as RFID electronic ear tag. Then, the pre-established livestock and poultry basic attribute database is accessed, and the breed (such as Angus cattle), growth stage (such as fattening period), health status (such as no disease record) and other information of the beef cattle are obtained according to the identification code. These data provide the necessary basic information for the formulation of subsequent vaccination programs. The acquired beef cattle attribute data is input into the pre-built personalized vaccination knowledge graph system. The knowledge graph system matches the vaccination rules in the knowledge graph according to the attributes such as the breed, growth stage and health status of the beef cattle through a rule-based reasoning algorithm. There are rules in the system that Angus cattle in the fattening period need to be vaccinated with specific respiratory disease vaccines. If the match is successful, the system will obtain the vaccination plan corresponding to the current beef cattle attributes from the knowledge graph, including the type of vaccine, vaccination time and dosage.

[0035] S102. According to the vaccination plan, control the smart vaccination equipment to perform precise drug administration.

[0036] According to the preset vaccination plan, determine the initial vaccination dose and vaccination time, and input them into the intelligent vaccination device. Obtain the physiological characteristic parameters and breeding environment parameters of livestock and poultry to determine whether they exceed the preset threshold. If they exceed the threshold, trigger the real-time adjustment of the vaccination plan. Input the physiological characteristic parameters and breeding environment parameters of livestock and poultry into the knowledge graph reasoning model, and obtain the updated vaccination dose and vaccination time through knowledge graph reasoning. Transmit the updated vaccination dose and vaccination time to the intelligent vaccination device, and perform precise drug administration according to the updated vaccination plan. Obtain the physiological reaction data of livestock and poultry after vaccination, input it into the machine learning model for analysis, and determine whether the vaccination effect meets expectations. If the vaccination effect does not meet expectations, input the physiological reaction data of livestock and poultry into the knowledge graph, obtain the optimized vaccination plan through knowledge graph reasoning, and update it to the intelligent vaccination device. According to the optimized vaccination plan, the intelligent vaccination device performs precise drug administration again until the vaccination effect meets expectations, completing the entire intelligent vaccination process.

[0037] Specifically, the initial vaccination dose and time are set first, which is usually based on the type, age and health status of livestock and poultry. For example, for an adult broiler, 5 ml of influenza vaccine may be preset and scheduled for vaccination on the 30th day of the breeding cycle. Subsequently, the system monitors the physiological characteristic parameters of livestock and poultry, such as body temperature and heart rate, as well as breeding environment parameters such as temperature and humidity. If these parameters exceed the preset safety threshold, such as abnormally high body temperature, it may indicate that the livestock and poultry are in a diseased state, which will trigger real-time adjustment of the vaccination plan. During the adjustment process, these physiological and environmental parameters are input into the knowledge graph reasoning model. The model intelligently infers the most suitable vaccination dose and time for the current situation by analyzing historical data and current data. For example, if the current ambient temperature is high, the model may recommend reducing the vaccine dose or postponing the vaccination time to avoid reduced vaccine effectiveness or livestock and poultry health risks caused by environmental factors. The updated vaccination plan is transmitted to the smart vaccination device via a wireless network, and the device automatically adjusts the dose and time according to the new plan to accurately control the injection of the vaccine. After vaccination, the equipment continues to monitor the physiological reactions of livestock and poultry, such as redness and swelling at the vaccination site or changes in body temperature. These data are input into the machine learning model again for effect analysis. If the analysis results show that the vaccination effect does not meet expectations, such as persistent abnormal body temperature, the system will adjust the vaccination plan again. In this way, the vaccination strategy can be adjusted in real time to ensure that each livestock and poultry can be vaccinated under the most suitable conditions, maximize the effect of the vaccine and protect the health of livestock and poultry. The application of this system not only improves breeding efficiency, but also reduces livestock and poultry diseases and mortality caused by improper vaccination. For breeders, this means higher economic benefits and production safety.

[0038] S103, collect vaccination process data and upload it to the cloud database in real time. If a batch of vaccination data is found to be abnormal, activate the early warning mechanism;

[0039] Specifically, the vaccination process data, including livestock and poultry number, vaccination time, vaccine batch and other information, is collected and uploaded to the cloud database in real time through the wireless communication module. If a batch of vaccination data is found to be abnormal, the early warning mechanism will be activated and the relevant livestock and poultry will be monitored.

[0040] By wearing electronic tags with unique identification codes on livestock and poultry, accurate identification and numbering of each livestock and poultry can be achieved. Obtain the timestamp information when livestock and poultry are vaccinated, associate it with the livestock and poultry number, and form a complete vaccination time record. Scan the QR code on the vaccine package to obtain key information such as the vaccine batch number, and upload it to the cloud database together with the livestock and poultry number and vaccination time. Use the Internet of Things communication module to transmit livestock and poultry vaccination data to the cloud in real time through the wireless network to ensure the timeliness and integrity of the data. Build a big data analysis platform in the cloud to perform statistical analysis on the received livestock and poultry vaccination data to determine whether there is abnormal data. If an abnormal deviation is found in the vaccination data of a batch of vaccines, the early warning mechanism is triggered and a warning message is sent to the farm manager. According to the early warning information, the farm manager marks the relevant batches of livestock and poultry, strengthens health monitoring, and adjusts feeding management measures.

[0041] After all vaccination data is uploaded to the cloud, the big data analysis platform will perform statistical analysis on the data. For example, the platform can count the average immune effect of a batch of vaccines. Assuming that the expected immune effect of a batch of avian influenza vaccines is 95%, but the actual monitoring data shows that the immune effect of this batch of vaccines is only 80%, the system will trigger the early warning mechanism and send a warning message to the farm managers, indicating that there may be problems with this batch of vaccines. The early warning information assists managers to take measures. After receiving the early warning information, the farm managers can mark the livestock and poultry vaccinated with this batch of vaccines according to the prompt information, such as adding special marks to the electronic ear tags, and strengthen the health monitoring of these livestock and poultry, such as measuring body temperature more frequently and observing mental state. At the same time, the feeding management measures can also be adjusted, such as improving feed nutrition and strengthening environmental disinfection, to reduce the risk of disease. For chickens vaccinated with problematic batches of vaccines, the vitamin content in the feed is increased to improve the immunity of the chickens. These measures together constitute a complete intelligent vaccination management system, which realizes the monitoring and management of the entire vaccination process, helps to ensure the health of livestock and poultry and improve the efficiency of breeding.

[0042] S104. Conduct statistical analysis on vaccination process data to determine the risk of immunization failure and mark high-risk individuals.

[0043] Specifically, the vaccination data is statistically analyzed to calculate the immunization coverage and antibody levels of livestock and poultry of various breeds and age groups. When the immunization coverage is lower than the preset threshold, or the antibody level fluctuates abnormally, the machine learning algorithm is used to determine the risk of immunization failure, automatically mark high-risk individuals, and generate early warning information to push to the farm.

[0044] Obtain the vaccination data of livestock and poultry, including livestock and poultry breeds, ages, immunization information, etc., and store them in the database. According to the vaccination data, group livestock and poultry according to their breeds and age groups, and calculate the immunization coverage of each group. Obtain the antibody level test result data of livestock and poultry, and associate it with the immunization coverage data. Through the time series analysis algorithm, judge the fluctuation of the antibody levels of each group of livestock and poultry to determine whether there are any abnormalities. Use the support vector machine algorithm to train the immunization failure risk prediction model with immunization coverage and antibody levels as features. Use the trained model to predict the immunization failure risk of each group of livestock and poultry and mark high-risk individuals. If the immunization coverage of a group of livestock and poultry is lower than the preset threshold, or is predicted to be high-risk, a warning message will be pushed to the farm managers to prompt them to strengthen immunization.

[0045] As an embodiment of the present invention, a farm has three kinds of livestock and poultry, namely, pigs, cattle and chickens, and each kind of livestock and poultry has different age groups. The age groups of pigs are divided into 0-30 days, 31-60 days and 61-90 days, the age groups of cattle are divided into 0-45 days, 46-90 days and 91-135 days, and the age groups of chickens are divided into 0-14 days, 15-28 days and 29-42 days. When each livestock and poultry is vaccinated, the system will record its breed, age, vaccine type, vaccination time and other information, and store these data in the database. This can ensure the integrity and traceability of the data, and facilitate subsequent analysis and early warning. According to the vaccination data, the livestock and poultry are grouped according to the breed and age group, and the immunization coverage of each group is calculated. Assuming that there are 100 pigs in the pigs in the 0-30 age group, 80 of which have been vaccinated, then the immunization coverage of the group is 80%. In this way, the immunization of livestock and poultry of different breeds and age groups can be clearly understood, providing a basis for the subsequent adjustment of immunization strategies. Obtain the antibody level test result data of livestock and poultry and associate it with the immunization coverage data. For example, the antibody level of pigs aged 0-30 days was tested, and it was found that the antibody level of 60 pigs met the standard. Combined with the data of 80% immunization coverage, the actual performance of the immunization effect can be analyzed. This association analysis helps to evaluate the effectiveness of vaccines and the rationality of immunization procedures. Through the time series analysis algorithm, the fluctuation of the antibody level of each group of livestock and poultry is judged to determine whether there is an abnormality. The antibody level of pigs aged 0-30 days was tested for three consecutive weeks. It was found that the antibody level reached the standard rate of 60% in the first week, 55% in the second week, and 50% in the third week, showing a downward trend. Through time series analysis, it can be judged whether this fluctuation is beyond the normal range, so as to timely discover potential problems. The support vector machine algorithm is used to train the immunization failure risk prediction model with immunization coverage and antibody level as features. Specifically: collect the immunization coverage and antibody level data of the past year, use them as training samples, and use the support vector machine algorithm to train the model. In this way, a model that can predict the risk of immunization failure can be constructed to improve the accuracy of early warning. The trained model is used to predict the risk of immune failure in each group of livestock and poultry, and to mark high-risk individuals.

[0046] The model prediction results show that 10 pigs in the 0-30 day age group have a high risk of immunization failure, and the system will automatically mark these pigs as high-risk individuals. This can help farm managers strengthen monitoring and intervention in a targeted manner. If the immunization coverage of a group of livestock and poultry is lower than the preset threshold, or is predicted to be high-risk, an early warning message will be pushed to the farm managers to prompt them to strengthen immunization. The threshold of immunization coverage is set at 75%. When the immunization coverage of pigs in the 0-30 day age group is only 70%, the system will automatically send an early warning message to the managers, indicating that the immunization coverage of this group of pigs is insufficient and immunization measures need to be strengthened. At the same time, if the model predicts that there are high-risk individuals in this group of pigs, an early warning message will also be pushed. Through these steps and technical means, comprehensive monitoring and early warning of the immunization status of livestock and poultry can be achieved, the risk of immunization failure can be discovered and resolved in a timely manner, and the epidemic prevention level of the farm can be improved. The correlation analysis of immunization coverage and antibody level, combined with time series analysis and support vector machine algorithm, can evaluate the immunization effect in multiple dimensions to ensure the healthy growth of livestock and poultry. This comprehensive data analysis and management method not only improves the scientificity and accuracy of epidemic prevention work, but also provides strong guarantees for the sustainable development of farms.

[0047] As another real-time method of the present invention, it also includes: continuously collecting livestock and poultry immune response data, which includes immune stress status, antibody duration, etc., combining breeding environment factors, and continuously optimizing personalized vaccination knowledge graphs through deep learning algorithms, so that it can adapt to livestock and poultry breed updates, breeding model changes, etc., to improve the stability of the immune effect.

[0048] Specifically, obtain the immune response data of livestock and poultry, including indicators such as immune stress status and antibody duration, and store the data in the database. Obtain the data of breeding environment factors, including indicators such as temperature, humidity, and stocking density, and store the data in the database. According to the attributes such as livestock and poultry breeds and breeding patterns, obtain the corresponding personalized vaccination plan from the knowledge graph. Associate the immune response data and breeding environment data with the personalized vaccination plan to construct a training data set. Use a deep learning algorithm to learn the training data set to obtain an optimized personalized vaccination knowledge graph model. If there is an update to the livestock and poultry breed or a change in the breeding pattern, obtain the corresponding data and input it into the knowledge graph model, and retrain the model to adapt it to the new situation. Apply the optimized personalized vaccination knowledge graph to actual production, dynamically adjust the vaccination plan, and improve the stability of the immune effect.

[0049] S105. Construct a prediction and early warning model for livestock and poultry diseases, analyze the peak periods and epidemic trends of diseases in livestock and poultry of different breeds and age groups based on the prediction results, automatically plan vaccination plans, and dynamically adjust vaccination strategies.

[0050] Specifically, according to the livestock and poultry breeds and age groups, the morbidity, mortality and other indicators of various diseases are statistically analyzed to determine the peak period and epidemic trend of the disease. Using time series analysis and association rule mining algorithms, a livestock and poultry disease prediction and early warning model is established to predict the probability of occurrence and epidemic trend of various diseases in the future. If the prediction results show that the probability of a certain type of disease is high or shows an epidemic trend, the corresponding vaccination plan, including vaccination time, vaccination type and vaccination dose, will be automatically generated before the peak period of the disease. In the actual vaccination process, the growth and health data of livestock and poultry are collected in real time through IoT devices, and the data is transmitted to the cloud platform for analysis. If a batch of livestock and poultry is found to have disease symptoms or abnormal conditions, the vaccination strategy of the batch of livestock and poultry will be adjusted immediately, the vaccination frequency will be increased or the vaccine type will be changed, and the disease prediction and early warning model will be updated at the same time. According to the disease prediction and early warning model and real-time monitoring data, the vaccination plan and vaccination strategy will be continuously optimized and improved, and the precise prevention and intelligent management of livestock and poultry diseases will be finally achieved.

[0051] In animal husbandry, accurate prevention and intelligent management of diseases are the key to improving breeding efficiency and ensuring animal health. First, by collecting historical data on livestock and poultry vaccination, such as breed, age group, and type of vaccination, data cleaning and preprocessing are performed to ensure data accuracy and availability. For example, for a batch of broilers, each vaccination information from birth to market is recorded, including the type of vaccine such as Newcastle disease vaccine, vaccination time, and dosage. After cleaning, these data can be used for subsequent analysis and model building. Next, according to different livestock and poultry breeds and age groups, the incidence and mortality of the disease are statistically analyzed to determine the peak period and epidemic trend of the disease. For example, by analyzing the data over the years, it may be found that a certain breed of pigs may be more susceptible to swine fever during the high temperature period in summer. This cyclical epidemic trend is crucial for formulating preventive measures. Using time series analysis and association rule mining algorithms, a livestock and poultry disease prediction and early warning model can be established. Time series analysis helps understand the changing laws of the disease in the time dimension, while association rule mining reveals the relationship between different factors. The model may show that the probability of a certain disease increases by 30% after three consecutive days of high temperature. Based on these prediction results, the system can automatically generate a vaccination plan. If the probability of a certain disease occurring in a certain period is predicted to be high, the system will arrange for the corresponding vaccination in advance before the peak period. If the prediction results show that July is the peak period for a certain viral disease, the system will arrange for booster vaccination in June. In the actual vaccination process, the application of IoT devices enables the growth, development and health status data of livestock and poultry to be collected in real time and transmitted to the cloud platform. These real-time data are very important for monitoring the vaccination effect and animal health status.

[0052] By monitoring the body temperature and activity after vaccination, it is possible to preliminarily determine whether the vaccination is successful. If real-time monitoring data shows that a batch of livestock and poultry has an abnormality, such as an abnormally high body temperature, the system will immediately adjust the vaccination strategy, which may be to increase the vaccination dose or change the type of vaccine, and at the same time update the disease prediction and early warning model to adapt to the new situation. Through this series of steps, not only can accurate prevention of livestock and poultry diseases be achieved, but also the health management level and economic benefits of the entire breeding industry can be improved through intelligent management. The application of this method enables farmers to conduct more accurate disease management and decision-making based on scientific data and models, thereby reducing economic losses and improving animal welfare.

[0053] This embodiment also provides a livestock and poultry vaccination management system based on the Internet of Things, which is applied to a livestock and poultry vaccination management method based on the Internet of Things, including:

[0054] Livestock and poultry electronic ear tag information collection module, used to obtain livestock and poultry electronic ear tag information;

[0055] A personalized vaccination knowledge graph construction module is used to combine livestock and poultry attribute data to build a personalized vaccination knowledge graph and generate a vaccination plan;

[0056] An intelligent vaccination control module, for controlling the intelligent vaccination device to perform precise drug administration according to the vaccination scheme;

[0057] The vaccination process data management module is used to collect vaccination process data and upload it to the cloud database in real time. If a batch of vaccination data is found to be abnormal, the early warning mechanism will be activated;

[0058] The livestock and poultry disease prediction and early warning model construction module is used to build a livestock and poultry disease prediction and early warning model, analyze the peak incidence and epidemic trends of diseases in livestock and poultry of different breeds and age groups based on the prediction results, automatically plan vaccination plans, and dynamically adjust vaccination strategies.

[0059] 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. A livestock and poultry vaccination management method based on the Internet of Things, characterized in that: include: Obtain livestock and poultry electronic ear tag information, combine livestock and poultry attribute data, establish a personalized vaccination knowledge map, generate vaccination plans, and determine the vaccination time, dosage, and site for each livestock and poultry; According to the vaccination plan, controlling the smart vaccination device to perform precise drug administration; Collect vaccination process data and upload it to the cloud database in real time. If abnormal data of a certain batch of vaccination is found, the early warning mechanism will be activated; Performing statistical analysis on the vaccination process data to determine the risk of immunization failure and marking high-risk individuals; Build a livestock and poultry disease prediction and early warning model, analyze the peak incidence periods and epidemic trends of diseases in livestock and poultry of different breeds and age groups based on the prediction results, automatically plan vaccination plans, and dynamically adjust vaccination strategies.

2. The livestock and poultry vaccination management method based on the Internet of Things according to claim 1, characterized in that: Generating the vaccination plan comprises: Obtain unique identification of livestock and poultry; Accessing a pre-established livestock and poultry basic attribute database, and obtaining the breed and growth stage attribute data of the corresponding livestock and poultry according to the livestock and poultry unique identification; The attribute data is input into a pre-built personalized vaccination knowledge graph system for matching, and a machine learning algorithm is used to intelligently generate a vaccination plan based on the livestock and poultry attribute data; The inoculation time, inoculation dosage and inoculation site parameters are extracted from the vaccination program, associated with livestock and poultry identifications, and stored in a livestock and poultry immunization program database.

3. The livestock and poultry vaccination management method based on the Internet of Things according to claim 2, characterized in that: The attribute data is input into a pre-built personalized immunization knowledge graph system for matching, including: The knowledge graph system uses a rule-based reasoning algorithm to match livestock and poultry attributes with vaccination rules in the knowledge graph; If the match is successful, the vaccination plan corresponding to the current livestock and poultry attributes is obtained from the knowledge graph; a case-based reasoning algorithm is used to retrieve vaccination cases similar to the current livestock and poultry attributes from the historical vaccination case library; the vaccination plan obtained by knowledge graph matching is integrated with the vaccination plan obtained by case reasoning to generate a personalized vaccination plan for the current livestock and poultry individuals; Among them, the attribute data include livestock and poultry types, growth stages, and health conditions.

4. The livestock and poultry vaccination management method based on the Internet of Things according to claim 1, characterized in that: According to the vaccination plan, the smart vaccination device is controlled to perform precise drug delivery, including: According to the vaccination plan, determining the initial vaccination dose and vaccination time, and inputting them into the smart vaccination device; Obtain the physiological characteristic parameters and breeding environment parameters of livestock and poultry to determine whether they exceed the preset threshold. If they exceed the threshold, the real-time adjustment of the vaccination plan is triggered; Input livestock and poultry physiological characteristic parameters and breeding environment parameters into the knowledge graph reasoning model, and obtain updated vaccination dosage and vaccination time through knowledge graph reasoning; The updated vaccination dosage and time are transmitted to the smart vaccination device, and precise drug administration is performed according to the updated vaccination plan.

5. The livestock and poultry vaccination management method based on the Internet of Things according to claim 4, characterized in that: Controlling smart vaccination devices to perform precise dosing also includes: Obtain the physiological response data of livestock and poultry after vaccination, and input it into the machine learning model for analysis to determine whether the vaccination effect has reached the expected level; If the vaccination effect does not meet expectations, the livestock and poultry physiological response data are input into the personalized vaccination knowledge graph, and the optimized vaccination plan is obtained through reasoning of the personalized vaccination knowledge graph, and updated to the smart vaccination device; According to the optimized vaccination plan, precise drug administration is performed again through the smart vaccination device until the vaccination effect reaches the expected level and the vaccination process is completed.

6. The livestock and poultry vaccination management method based on the Internet of Things according to claim 1, characterized in that: Collect vaccination process data and upload it to the cloud database in real time. If a batch of vaccination data is found to be abnormal, the early warning mechanism will be activated, including: Obtain the timestamp information when livestock and poultry are vaccinated, and associate the timestamp information with the livestock and poultry number to form a complete vaccination time record; Scan the QR code on the vaccine package to obtain the vaccine batch number, and upload the vaccine batch number together with the livestock and poultry number and vaccination time to the cloud database; The livestock and poultry vaccination data is transmitted to the cloud in real time via wireless network, and a big data analysis platform is built on the cloud to conduct statistical analysis on the received livestock and poultry vaccination data to determine whether there is any abnormal data; If abnormal deviations are found in the vaccination data of a certain batch of vaccines, the early warning mechanism will be triggered and a warning message will be sent to the farm managers.

7. The livestock and poultry vaccination management method based on the Internet of Things according to claim 1, characterized in that: Statistical analysis is performed on the vaccination process data to determine the risk of immunization failure and mark high-risk individuals, including: According to the vaccination process data, the livestock and poultry are grouped according to their breeds and age groups, and the immunization coverage rate of each group is calculated; Obtaining antibody level test result data of livestock and poultry, and correlating it with the immunization coverage rate; Through the time series analysis algorithm, the fluctuation of the antibody levels of each group of livestock and poultry is judged to determine whether there are any abnormalities; The support vector machine algorithm was used to train the immune failure risk prediction model based on the immune coverage rate and antibody level. The trained model was used to predict the immune failure risk of each group of livestock and poultry and mark high-risk individuals. If the immunization coverage rate of a group of livestock and poultry is lower than the preset threshold or is predicted to be high-risk, early warning information will be pushed to farm managers.

8. The livestock and poultry vaccination management method based on the Internet of Things according to claim 1, characterized in that: Construct the livestock and poultry disease prediction and early warning model, including: Obtain historical data on livestock and poultry vaccination, including livestock and poultry breeds, age groups, vaccine types, vaccination times, and vaccination doses, and perform data cleaning and preprocessing; Analyze the incidence and mortality of various diseases according to livestock and poultry breeds and age groups, and determine the peak period and epidemic trend of diseases; The livestock and poultry disease prediction and early warning model is established by using time series analysis and association rule mining algorithms.

9. The method for livestock and poultry vaccination management based on the Internet of Things according to claim 8, characterized in that: Analyze the peak periods and epidemic trends of diseases in livestock and poultry of different breeds and age groups, automatically plan vaccination plans, and dynamically adjust vaccination strategies, including: If the prediction result of the livestock and poultry disease prediction and early warning model shows that a certain type of disease has a high probability of occurrence or is showing an epidemic trend, a corresponding vaccination plan is automatically generated before the peak period of the disease, including the vaccination time, vaccination type and vaccination dosage; Collect the growth, development and health status data of livestock and poultry in real time, and transmit the data to the cloud platform for analysis. If a batch of livestock and poultry is found to have disease symptoms or abnormal conditions, immediately adjust the vaccination strategy of the batch of livestock and poultry, increase the vaccination frequency or change the type of vaccine, and update the disease prediction and early warning model at the same time; Based on disease prediction and early warning models and real-time monitoring data, vaccination plans and strategies are continuously optimized and improved.

10. A livestock and poultry vaccination management system based on the Internet of Things, characterized in that: include: Livestock and poultry electronic ear tag information collection module, used to obtain livestock and poultry electronic ear tag information; A personalized vaccination knowledge graph construction module is used to combine livestock and poultry attribute data to build a personalized vaccination knowledge graph and generate a vaccination plan; An intelligent vaccination control module, for controlling the intelligent vaccination device to perform precise drug administration according to the vaccination scheme; The vaccination process data management module is used to collect vaccination process data and upload it to the cloud database in real time. If a batch of vaccination data is found to be abnormal, the early warning mechanism will be activated; The livestock and poultry disease prediction and early warning model construction module is used to build a livestock and poultry disease prediction and early warning model, analyze the peak incidence and epidemic trends of diseases in livestock and poultry of different breeds and age groups based on the prediction results, automatically plan vaccination plans, and dynamically adjust vaccination strategies.

Images