Animal epidemic disease propagation prediction method and system based on big data analysis, electronic equipment and storage medium
Through big data analysis methods, integrating and mining animal disease data and building an LSTM model, solving the shortcomings of traditional prediction methods, and achieving accurate prediction and scientific prevention and control of the spread of epidemics.
Patent Information
- Application Number
- CN202510341253.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-21
- Publication Date
- 2025-07-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional animal disease prediction methods rely on empirical judgment and limited historical data statistics, making it difficult to accurately and timely predict the spread trend and scope of the disease, and cannot effectively integrate heterogeneous data, resulting in low prediction accuracy and inability to adapt to a dynamically changing environment.
Using big data analysis method, through adaptive data transformation, data cleaning, association integration and mining analysis, an LSTM model is constructed to predict disease transmission, identify spatiotemporal aggregation patterns and association rules, and generate structured data sets.
Accurate and efficient prediction of the spread of animal disease, provide scientific basis to support prevention and control decisions, and improve the accuracy and reliability of predictions.
Smart Images
Figure CN120280177A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of animal disease prevention, and particularly to an animal epidemic disease transmission prediction method, system, electronic device and storage medium based on big data analysis. Background Art
[0002] In the field of animal epidemic disease prevention and control, traditional prediction methods mainly rely on empirical judgment and limited historical data statistical analysis, and it is difficult to accurately and timely predict the transmission trend and scope of epidemic diseases. With the acceleration of the globalization process and the continuous expansion of the scale of animal breeding and transportation, the transmission speed and complexity of animal epidemic diseases have increased significantly, posing a huge challenge to public health safety and the animal breeding industry. In the prior art, although there are some prediction methods based on statistical models, these methods often ignore the correlation between multi-dimensional data, such as the impact of factors such as time, location, and animal species on the transmission of epidemic diseases, resulting in low prediction accuracy and inability to adapt to the dynamically changing environment. In addition, traditional data processing methods are difficult to effectively integrate heterogeneous data from different platforms and formats, and cannot make full use of big data resources to improve prediction capabilities. Summary of the Invention
[0003] In order to solve the above technical problems, the present invention aims to provide an animal epidemic disease transmission prediction method that can comprehensively consider the correlation of multi-dimensional data, the influence of dynamic factors, and make full use of big data analysis technology to achieve accurate and efficient epidemic disease transmission prediction and prevention and control decision support.
[0004] To achieve the above object, the present invention provides an animal epidemic disease transmission prediction method based on big data analysis, the method comprising:
[0005] Collect historical data related to the transmission of animal epidemic diseases;
[0006] Preprocess the historical data to obtain processed data;
[0007] Based on the processed data, perform correlation integration according to the dimensions of time, location, and animal species to generate an integrated data set;
[0008] Based on the data set, construct a prediction model and use the prediction model to complete the transmission of animal epidemic diseases.
[0009] Preferably, after the historical data is collected, for different data formats, an adaptive data conversion algorithm is adopted to uniformly convert the data into a structured format; according to the characteristics of the data source, determine the data mode and metadata information of each data source, and construct a unified metadata mapping table; for each data source, according to the metadata mapping table, convert the original heterogeneous data into an intermediate data format to eliminate data heterogeneity.
[0010] Preferably, duplicate data and outliers in the historical data are removed through preset data cleaning rules, and a data standardization method is used to process the cleaned epidemic disease dataset to eliminate differences between data from different sources and improve data consistency.
[0011] Preferably, after generating the dataset, mining analysis is performed on the associated data set to obtain the association patterns and rules between different dimensional attributes; the steps of data mining include:
[0012] The DBSCAN algorithm based on density is used to cluster the historical data to identify the spatio-temporal aggregation patterns of epidemic disease transmission. By setting the neighborhood radius and the minimum number of samples, regions with similar transmission characteristics are divided into the same cluster to reveal potential high-risk transmission regions; afterwards, the Apriori algorithm is used to mine the strong association rules between epidemic disease transmission and animal species and environmental factors; the final division results include:
[0013] Low-risk category: low density, high vaccination rate, temperature < 25 °C.
[0014] Medium-risk category: medium density, medium vaccination rate, large humidity fluctuations.
[0015] High-risk category: high density, low vaccination rate, temperature > 30 °C and humidity > 80%.
[0016] Preferably, after generating the dataset, a long short-term memory neural network is used to construct the prediction model:
[0017] f t = σ(W f · [h t-1 , x t + b f )
[0018] i t = σ(W i · [h t-1 , x t + b i )
[0019]
[0020] o t = σ(W o · [h t-1 , x t + b o )
[0021] h t = o t ⊙ tanh(C t )
[0022] Among them, f t represents the forget gate; i t represents the input gate; o t represents the output gate; h t represents the output at time step t; C t represents the cell state; represents the candidate cell state; σ represents the Sigmoid function; ⊙ represents element-wise multiplication; W f 、W i 、W C 、W o all represent weight matrices; b f 、b i 、b C 、b o all represent bias terms.
[0023] The present invention also provides an animal epidemic disease transmission prediction system based on big data analysis. The system is used to implement the above method and includes: a collection module, a processing module, an integration module, and a prediction module;
[0024] The collection module is used to collect historical data on animal epidemic disease transmission;
[0025] The processing module is used to preprocess the historical data to obtain processed data;
[0026] The integration module is used to perform correlation integration based on the processed data according to the dimensions of time, location, and animal species to generate an integrated data set;
[0027] The prediction module is used to construct a prediction model based on the data set and use the prediction model to complete the transmission of animal epidemic diseases.
[0028] Preferably, the working process of the collection module includes: after the historical data is collected, for different data formats, an adaptive data conversion algorithm is used to uniformly convert the data into a structured format; according to the characteristics of the data source, the data mode and metadata information of each data source are determined, and a unified metadata mapping table is constructed; for each data source, according to the metadata mapping table, the original heterogeneous data is converted into an intermediate data format to eliminate data heterogeneity.
[0029] Preferably, the working process of the processing module includes: removing duplicate data and outliers in the historical data through preset data cleaning rules, and using a data standardization method to process the cleaned epidemic disease data set to eliminate the differences between data from different sources and improve the consistency of the data.
[0030] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the above-mentioned method is implemented.
[0031] The present invention also provides a computer-readable storage medium storing a computer program, which when executed, implements the above-mentioned method.
[0032] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0033] The present invention can generate a comprehensive and structured data set, providing a richer and more accurate data basis for epidemic transmission prediction. The present invention can also effectively identify the spatio-temporal aggregation patterns and key association rules of epidemic transmission, thereby providing a scientific basis for risk level classification and further improving the accuracy and reliability of prediction. In summary, the present invention can effectively capture the time series characteristics of epidemic transmission, achieve accurate prediction of future epidemic trends, and provide strong support for epidemic prevention and control decision-making. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions of the present invention, the following briefly introduces the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0035] Figure 1 It is a schematic flowchart of the method according to an embodiment of the present invention;
[0036] Figure 2 It is a schematic diagram of data acquisition according to an embodiment of the present invention;
[0037] Figure 3 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
[0038] Description of the reference numerals:
[0039] 1010, processor; 1020, memory; 1030, input / output interface; 1040, communication interface; 1050, bus. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.
[0041] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the ordinary meanings understood by those of ordinary skill in the field to which the present disclosure pertains. The "first", "second" and similar terms used in the embodiments of the present disclosure do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.
[0042] To make the above objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0043] Embodiment 1
[0044] As can be seen from the background art, traditional data processing methods are difficult to effectively integrate heterogeneous data from different platforms and formats, and cannot fully utilize big data resources to improve prediction capabilities.
[0045] Based on this, the embodiments of the present invention provide a method for predicting the spread of animal diseases based on big data analysis. The steps include:
[0046] S1. Collect historical data related to the spread of animal diseases.
[0047] Collect historical data of major diseases in each region. For different data formats, adopt an adaptive data conversion algorithm to uniformly convert the historical data into a structured format. According to the characteristics of the data source, determine the data schema and metadata information of each data source, and construct a unified metadata mapping table; for each data source, according to the metadata mapping table, convert the original heterogeneous data into an intermediate data format to eliminate data heterogeneity.
[0048] The purpose of this step is to obtain dynamic and static data related to the spread of animal diseases from multi-dimensional and multi-modal data sources. The specific classification is as Figure 2 shown:
[0049] S2. Preprocess the historical data to obtain processed data.
[0050] For the complex characteristics of dimensions of structured data, through preset data cleaning rules, duplicate data and outliers are removed, keyword fields related to the spread of diseases are extracted, and potentially valuable information is retained to generate a cleaned dataset.
[0051] Through data cleaning rules, it is judged whether there is duplicate data and outliers in the data. If so, these invalid data are removed. The data standardization method is used to process the cleaned disease dataset to eliminate the differences between data from different sources and improve the data consistency. The standardized disease dataset is used as the input for subsequent disease analysis and spread prediction, providing data support for disease prevention and control decisions.
[0052] S3. Based on the processed data, perform correlation integration according to the dimensions of time, location, and animal species to generate an integrated dataset.
[0053] Obtain the cleaned dataset, and perform correlation integration processing on the dataset according to the preset dimension attributes of time, location, and animal species. By analyzing the time attribute of the dataset, the timestamp information of the data is extracted, and the data is divided into different time periods according to the timestamp. For the data in each time period, the location attribute of the data is extracted, and the data is divided into different location groups according to the location information. Within each location group, the animal species attribute of the data is extracted, and the data is divided into different animal species subsets according to the animal species. According to the preset data integration rules, the divided time periods, location groups, and animal species subsets are combined and correlated to generate a multi-dimensional correlated data set. Mine and analyze the correlated data set to discover the correlation patterns and rules between different dimension attributes. Apply the mined correlation patterns and rules to subsequent data analysis tasks to provide data support and reference basis for relevant decisions.
[0054] First, extract the timestamp information of the data according to the time attribute. For example, in an animal disease spread dataset, through the timestamp, the data can be divided into different time periods, such as by day, week, or month. Such a division helps to observe the time trend of disease spread. Then, extract the location attribute of the data. In animal disease spread, the location information may include provinces, cities, or even specific farms or wildlife habitats. Through this information, the data can be divided into different geographical regions, which helps to analyze the spread of diseases in different areas. Then, extract the animal species attribute. In the disease spread data, this may include poultry (such as chickens, ducks), livestock (such as pigs, cows), or wild animals (such as bats, deer). Through this attribute, the roles and susceptibilities of different animal species in disease spread can be studied. Combining these dimension attributes can generate a multi-dimensional correlated data set.
[0055] This multi-dimensional correlation can help to comprehensively understand the patterns of epidemic disease transmission. For example, in some regions, when the temperature rises, the transmission speed of a certain animal disease accelerates. Or, there is a seasonal pattern in the transmission of a certain disease among different animal species. The associated patterns and rules of these findings can be applied to subsequent data analysis tasks. The steps of the above data mining include:
[0056] Use the density-based DBSCAN algorithm to cluster historical data and identify the spatio-temporal aggregation patterns of epidemic disease transmission. By setting the neighborhood radius (Eps) and the minimum number of samples (MinPts), regions with similar transmission characteristics are divided into the same cluster to reveal potential high-risk transmission regions.
[0057] After that, use the Apriori algorithm to mine the strong association rules between epidemic disease transmission and animal species, environmental factors (such as temperature, humidity). Set the minimum support and confidence thresholds, and extract rules such as "a certain animal species is significantly correlated with the high incidence of epidemic disease in a specific season" to provide a basis for risk level classification. The Apriori algorithm mines association rules by generating item sets and calculating support and confidence:
[0058] The support of item set X is the proportion of transactions in the dataset that contain X:
[0059]
[0060] Among them, Support(X) represents the support of item set X; Count(X) represents the number of transactions in the dataset that contain item set X; N represents the total number of transactions.
[0061] The rule The confidence of is:
[0062]
[0063] In the formula, both X and Y represent item sets.
[0064] Through the above steps, three types of transmission patterns are divided:
[0065] Low-risk category: low density, high vaccination rate, temperature < 25°C.
[0066] Medium-risk category: medium density, medium vaccination rate, large humidity fluctuations.
[0067] High-risk category: high density, low vaccination rate, temperature > 30°C and humidity > 80%.
[0068] S4. Based on the dataset, construct a prediction model and use the prediction model to complete the transmission of animal epidemic diseases.
[0069] Specifically, constructing feature vectors by extracting dataset information can lay a foundation for subsequent analysis. For example, the risk level distribution in a certain area is as follows: 3 high-risk areas, 8 medium-risk areas, and 20 low-risk areas, which can be converted into a feature vector of [3, 8, 20]. This representation method facilitates model processing and analysis. Time series analysis of historical epidemic data is crucial for predicting future trends. Taking a certain area as an example, record the daily number of new cases, the spread range (number of streets involved), and the severity (severe case rate) in the past 30 days to form a 30×3 matrix. This structured data helps capture the time pattern of epidemic development. Dynamic factors such as climate environment and human mobility have a significant impact on epidemic transmission. For example, indicators such as temperature, humidity, population density, and traffic flow can be used to construct a feature vector of dynamic factors. The average daily temperature in a certain city is 25°C, the relative humidity is 60%, the population density is 8,000 people per square kilometer, and the average daily passenger flow is 500,000 person-times, which can be represented as a vector of [25, 60, 8000, 500000]. Feature fusion is a key step in improving prediction accuracy. Combining risk levels, historical data, and dynamic factors can comprehensively reflect the epidemic situation. For example, splicing the above three types of features to obtain a comprehensive feature vector of [3, 8, 20, 100, 5, 0.02, 25, 60, 8000, 500000], where 100 represents the daily number of new cases, 5 represents the number of streets involved, and 0.02 represents the severe case rate.
[0070] Adopt a long short-term memory neural network (LSTM) model, using the comprehensive feature vector as the input to train a time series prediction model. The LSTM model structure is as follows:
[0071] f t = σ(W f · [h t-1 , x t + b f )
[0072] i t = σ(W i · [h t-1 , x t + b i )
[0073]
[0074] o t = σ(W o · [h t-1 , x t + b o )
[0075] h t = o t ⊙ tanh(C t )
[0076] Among them, f t represents the forget gate; i t represents the input gate; o t represents the output gate; h t represents the output at time step t; C t represents the cell state; represents the candidate cell state; σ represents the Sigmoid function; ⊙ represents element-wise multiplication; W f 、W i 、W C 、W o all represent weight matrices; b f 、b i 、b C 、b o all represent bias terms.
[0077] When predicting the future epidemic trend, the comprehensive feature vector of the current state is input into the trained LSTM model. The model may output the daily prediction values for the next 7 days, including the number of new cases, the spread range, and the severity. These prediction results provide a quantitative basis for prevention and control decisions. The transmission trend report generated based on the prediction results should include the change trends of key indicators, potential risk points, and recommended measures.
[0078] The present invention can generate a comprehensive and structured data set, providing a richer and more accurate data basis for epidemic transmission prediction. The present invention can also effectively identify the spatio-temporal aggregation patterns and key association rules of epidemic transmission, thereby providing a scientific basis for risk level classification and further improving the accuracy and reliability of prediction. In summary, the present invention can effectively capture the time series characteristics of epidemic transmission, achieve accurate prediction of future epidemic trends, and provide strong support for epidemic prevention and control decisions.
[0079] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server, etc. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In this distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiments of the present disclosure, and these multiple devices will interact with each other to complete the described method.
[0080] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention. The actions or steps recited in the claims may be executed in a different order from those in the above embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0081] Embodiment 2
[0082] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides an animal epidemic disease transmission prediction system based on big data analysis, including: a collection module, a processing module, an integration module, and a prediction module; the collection module is used to collect historical data related to the transmission of animal epidemic diseases; the processing module is used to preprocess the historical data to obtain processed data; the integration module is used to perform correlation integration based on the processed data according to the dimensions of time, location, and animal species to generate an integrated data set; the prediction module is used to build a prediction model based on the data set and use the prediction model to complete the prediction of the transmission of animal epidemic diseases.
[0083] Next, in combination with this embodiment, it will be described in detail how the present invention solves technical problems in real life.
[0084] First, use the collection module to collect historical data related to the transmission of animal epidemic diseases.
[0085] Collect historical data of large-scale epidemic diseases in each region from different platforms. For different data formats, adopt an adaptive data conversion algorithm to uniformly convert the historical data into a structured format. According to the characteristics of the data source, determine the data schema and metadata information of each data source, and construct a unified metadata mapping table; for each data source, according to the metadata mapping table, convert the original heterogeneous data into an intermediate data format to eliminate data heterogeneity.
[0086] The purpose of this step is to obtain dynamic and static data related to the transmission of animal epidemic diseases from multi-dimensional and multi-modal data sources, and its specific classification is as Figure 2 shown:
[0087] After that, the processing module preprocesses the historical data to obtain processed data.
[0088] For the complex dimensional characteristics of structured data, through preset data cleaning rules, duplicate data and outliers are removed, keyword fields related to the spread of diseases are extracted, and potentially valuable information is retained to generate a cleaned dataset.
[0089] Through data cleaning rules, it is judged whether there is duplicate data and outliers in the data. If so, these invalid data are removed. The data standardization method is used to process the cleaned disease dataset to eliminate the differences between data from different sources and improve data consistency. The standardized disease dataset is used as the input for subsequent disease analysis and transmission prediction, providing data support for disease prevention and control decisions.
[0090] The integration module is based on the processed data and is associated and integrated according to the dimensions of time, location, and animal species to generate an integrated dataset.
[0091] Obtain the cleaned dataset and perform associated integration processing on the dataset according to the preset time, location, and animal species dimension attributes. By analyzing the time attribute of the dataset, the timestamp information of the data is extracted, and the data is divided into different time periods according to the timestamp. For the data in each time period, the location attribute of the data is extracted, and the data is divided into different location groups according to the location information. Within each location group, the animal species attribute of the data is extracted, and the data is divided into different animal species subsets according to the animal species. According to the preset data integration rules, the divided time periods, location groups, and animal species subsets are combined and associated to generate a multi-dimensional associated data set. The associated data set is mined and analyzed to discover the association patterns and rules between different dimension attributes. The mined association patterns and rules are applied to subsequent data analysis tasks to provide data support and reference for relevant decisions.
[0092] First, the timestamp information of the data is extracted according to the time attribute. For example, in an animal disease transmission dataset, through the timestamp, the data can be divided into different time periods, such as by day, week, or month. Such a division helps to observe the time trend of disease transmission. Then, the location attribute of the data is extracted. In animal disease transmission, the location information may include provinces, cities, or even specific farms or wildlife habitats. Through this information, the data can be divided into different geographical regions, which helps to analyze the spread of diseases in different areas. Then, the animal species attribute is extracted. In the disease transmission data, this may include poultry (such as chickens, ducks), livestock (such as pigs, cows), or wild animals (such as bats, deer). Through this attribute, the roles and susceptibilities of different animal species in disease transmission can be studied. Combining these dimension attributes can generate a multi-dimensional associated data set.
[0093] Such multi-dimensional associations can help in a more comprehensive understanding of the patterns of disease transmission. For example, in certain regions, when the temperature rises, the transmission rate of a certain animal disease accelerates. Or, there are seasonal patterns in the transmission of a certain disease among different animal species. The associated patterns and regularities discovered can be applied to subsequent data analysis tasks. The steps of the above data mining include:
[0094] Use the density-based DBSCAN algorithm to cluster historical data and identify the spatio-temporal aggregation patterns of disease transmission. By setting the neighborhood radius (Eps) and the minimum number of samples (MinPts), regions with similar transmission characteristics are divided into the same cluster to reveal potential high-risk transmission areas.
[0095] After that, use the Apriori algorithm to mine the strong association rules between disease transmission and animal species, environmental factors (such as temperature, humidity). Set the minimum support and confidence thresholds, and extract rules such as "a certain animal species is significantly associated with a high incidence of disease in a specific season" to provide a basis for risk level classification. The Apriori algorithm mines association rules by generating item sets and calculating support and confidence:
[0096] The support of item set X is the proportion of transactions in the dataset that contain X:
[0097]
[0098] Among them, Support(X) represents the support of item set X; Count(X) represents the number of transactions in the dataset that contain item set X; N represents the total number of transactions.
[0099] The rule The confidence of is:
[0100]
[0101] In the formula, both X and Y represent item sets.
[0102] Through the above steps, three types of transmission patterns are classified:
[0103] Low-risk category: low density, high vaccination rate, temperature < 25°C.
[0104] Medium-risk category: medium density, medium vaccination rate, large humidity fluctuations.
[0105] High-risk category: high density, low vaccination rate, temperature > 30°C and humidity > 80%.
[0106] Finally, the prediction module constructs a prediction model based on the dataset and uses the prediction model to complete the transmission of animal diseases.
[0107] Specifically, constructing feature vectors by extracting dataset information can lay a foundation for subsequent analysis. For example, the risk level distribution in a certain area is as follows: 3 high-risk areas, 8 medium-risk areas, and 20 low-risk areas, which can be converted into a feature vector of [3, 8, 20]. This representation method facilitates model processing and analysis. Time series analysis of historical epidemic data is crucial for predicting future trends. Taking a certain area as an example, record the daily new case numbers, the spread range (number of streets involved), and the severity (severe case rate) in the past 30 days to form a 30×3 matrix. This structured data helps to capture the time patterns of epidemic development. Dynamic factors such as climate environment and human mobility have a significant impact on epidemic transmission. For example, indicators such as temperature, humidity, population density, and traffic flow can be used to construct feature vectors of dynamic factors. The average daily temperature in a certain city is 25°C, the relative humidity is 60%, the population density is 8,000 people per square kilometer, and the average daily passenger flow is 500,000 person-times, which can be represented as a vector of [25, 60, 8000, 500000]. Feature fusion is a key step in improving prediction accuracy. Combining risk levels, historical data, and dynamic factors can comprehensively reflect the epidemic situation. For example, by splicing the above three types of features, a comprehensive feature vector [3, 8, 20, 100, 5, 0.02, 25, 60, 8000, 500000] is obtained, where 100 represents the daily new case number, 5 represents the number of streets involved, and 0.02 represents the severe case rate.
[0108] Adopt a long short-term memory neural network (LSTM) model, use the comprehensive feature vector as the input, and train a time series prediction model. The LSTM model structure is as follows:
[0109] f t =σ(W f ·[h t-1 ,x t +b f )
[0110] i t =σ(W i ·[h t-1 ,x t +b i )
[0111]
[0112] o t =σ(W o ·[h t-1 ,x t +b o )
[0113] h t =o t ⊙tanh(C t )
[0114] Among them, f t represents the forget gate; i t represents the input gate; o t represents the output gate; h t represents the output at time step t; C t represents the cell state; represents the candidate cell state; σ represents the Sigmoid function; ⊙ represents element-wise multiplication; W f 、W i 、W C 、W o all represent weight matrices; b f 、b i 、b C 、b o all represent bias terms.
[0115] When predicting the future trend of animal diseases, the comprehensive feature vector of the current state is input into the trained LSTM model. The model may output the daily prediction values for the next 7 days, including the number of new cases, the scope of transmission, and the severity. These prediction results provide a quantitative basis for prevention and control decisions. The transmission trend report generated based on the prediction results should include the change trends of key indicators, potential risk points, and recommended measures.
[0116] The system of the above embodiment is used to implement the corresponding animal disease transmission prediction method based on big data analysis in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.
[0117] It should be noted that the above animal disease transmission prediction system based on big data analysis is embodied in the form of functional units. The term "module" here can be implemented in the form of software and / or hardware, and no specific limitation is made thereto.
[0118] For example, the "module" can be a software program, a hardware circuit, or a combination of both that implements the above functions. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor, or a group of processors, etc.) for executing one or more software or firmware programs, and a memory, a merged logic circuit, and / or other suitable components that support the described functions.
[0119] Embodiment III
[0120] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method for predicting the spread of animal diseases based on big data analysis described in any one of the above embodiments.
[0121] Figure 3 FIG. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.
[0122] The processor 1010 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.
[0123] The memory 1020 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.
[0124] The input / output interface 1030 is used to connect to the input / output module to achieve information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.
[0125] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to achieve communication and interaction between this device and other devices. The communication module can achieve communication through wired means (such as USB (Universal Serial Bus), network cable, etc.) or through wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).
[0126] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).
[0127] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification, and does not necessarily include all the components shown in the figure.
[0128] The system of the above embodiments is used to implement the corresponding animal epidemic disease transmission prediction method based on big data analysis in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.
[0129] Embodiment Four
[0130] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the animal epidemic disease transmission prediction method based on big data analysis as described in any of the foregoing embodiments.
[0131] The computer-readable medium of this embodiment includes both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
[0132] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the animal disease transmission prediction method based on big data analysis described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.
[0133] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present disclosure as described above, and they are not provided in detail for the sake of brevity.
[0134] In addition, for the sake of simplicity of description and discussion, and in order not to make the embodiments of the present disclosure difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. In addition, the device may be shown in block diagram form to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be completely within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe the exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiments of the present disclosure can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0135] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.
[0136] Thus, the units of the examples described in the embodiments of the present application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A person skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.
[0137] Embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure shall be included within the protection scope of the present disclosure.
Claims
1. A method for predicting the spread of animal diseases based on big data analysis, characterized in that, The method includes: Collecting historical data on the spread of animal diseases; Preprocessing the historical data to obtain processed data; Based on the processed data, performing correlation integration according to the dimensions of time, location, and animal species to generate an integrated dataset; Based on the dataset, constructing a prediction model and using the prediction model to complete the spread of animal diseases.
2. The animal epidemic disease transmission prediction method based on big data analysis according to claim 1, characterized in that, After the historical data is collected, for different data formats, an adaptive data conversion algorithm is used to uniformly convert the data into a structured format; according to the characteristics of the data source, determine the data mode and metadata information of each data source, and construct a unified metadata mapping table; for each data source, according to the metadata mapping table, convert the original heterogeneous data into an intermediate data format to eliminate data heterogeneity. According to the characteristics of the data source, determine the data mode and metadata information of each data source, and construct a unified metadata mapping table; For each data source, according to the metadata mapping table, convert the original heterogeneous data into an intermediate data format to eliminate data heterogeneity.
3. The animal disease transmission prediction method based on big data analysis according to claim 1, wherein Through preset data cleaning rules, remove duplicate data and outliers in the historical data, and use data standardization methods to process the cleaned disease dataset to eliminate differences between data from different sources and improve data consistency.
4. The method for predicting the spread of animal diseases based on big data analysis according to claim 1, wherein After generating the dataset, perform mining analysis on the associated data set to obtain the association patterns and rules between different dimensional attributes; The steps of data mining include: Using the density-based DBSCAN algorithm to cluster the historical data to identify the spatio-temporal aggregation patterns of the spread of diseases; by setting the neighborhood radius and the minimum number of samples, divide the regions with similar spread characteristics into the same cluster to reveal potential high-risk spread regions; then, use the Apriori algorithm to mine the strong association rules between the spread of diseases and animal species and environmental factors; the final classification results include: Low-risk category: low density, high vaccination rate, temperature < 25°C; Medium-risk category: medium density, medium vaccination rate, large humidity fluctuations; High-risk category: high density, low vaccination rate, temperature > 30°C and humidity > 80%.
5. The method for predicting the spread of animal diseases based on big data analysis according to claim 1, wherein After generating the dataset, use a long short-term memory neural network to construct the prediction model: f t = σ(W f · [h t-1 , x t + b f ) i t = σ(W i · [h t-1 , x t + b i ) o t = σ(W o · [h t-1 , x t + b o ) h t = o t ☉tanh(C t ) Among them, f t represents the forget gate; i t represents the input gate; o t represents the output gate; h t represents the output at time step t; C t represents the cell state; represents the candidate cell state; σ represents the Sigmoid function; ⊙ represents element-wise multiplication; W f 、W i 、W C 、W o all represent weight matrices; b f 、b i 、b C 、b o all represent bias terms.
6. An animal epidemic disease transmission prediction system based on big data analysis, the system is used to implement the method described in any one of claims 1-5, and is characterized in that, Including: A collection module, a processing module, an integration module, and a prediction module; The collection module is used to collect historical data on the spread of animal diseases; The processing module is used to preprocess the historical data to obtain processed data; The integration module is used to perform correlation integration according to the dimensions of time, location, and animal species based on the processed data to generate an integrated dataset; The prediction module is used to construct a prediction model based on the dataset and use the prediction model to complete the spread of animal diseases.
7. The animal epidemic disease transmission prediction system based on big data analysis according to claim 6, characterized in that The working process of the collection module includes: after the historical data is collected, for different data formats, an adaptive data conversion algorithm is used to uniformly convert the data into a structured format; according to the characteristics of the data source, determine the data mode and metadata information of each data source, and construct a unified metadata mapping table; for each data source, according to the metadata mapping table, convert the original heterogeneous data into an intermediate data format to eliminate data heterogeneity.
8. The animal epidemic disease transmission prediction system based on big data analysis according to claim 6, characterized in that, The workflow of the processing module includes: removing duplicate data and outliers in the historical data through preset data cleaning rules, and processing the cleaned epidemic disease data set by using a data standardization method to eliminate differences between data from different sources and improve data consistency.
9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method according to any one of claims 1 to 5.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which when executed, implements the method according to any one of claims 1 to 5.