Animal epidemic prevention information management system
Through the integration of a multi-module animal epidemic prevention information management system, the problem of inefficiency of traditional methods is solved, real-time data collection and analysis is realized, interactive learning and decision-making support is provided, the efficiency and user experience of epidemic prevention work is improved, and the system is ensured. stability and security.
Patent Information
- Application Number
- CN202411138287.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-15
AI Technical Summary
Traditional animal epidemic prevention information management methods are inefficient and cannot update information in real time. The existing system has limited data processing and analysis capabilities, insufficient user experience and interactivity, making it difficult to provide timely and accurate decision-making support for animal epidemic prevention.
Designed a multi-module animal epidemic prevention information management system that integrates mobile applications, Internet of Things, data storage and analysis, user interaction, management and maintenance to realize real-time data viewing and entry, automatic data collection, data analysis and prediction, and provide interactive Learning materials and online support ensure data security and system stability.
It greatly reduces manual data entry errors, improves the convenience and efficiency of epidemic prevention work, provides timely and accurate decision-making support, improves users' epidemic prevention knowledge and skills, and ensures the stable operation of the system and data security.
Smart Images

Figure CN118969280A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of animal epidemic prevention information management, in particular to an animal epidemic prevention information management system. Background Art
[0002] Traditional management methods can no longer meet the growing needs of epidemic prevention. On the one hand, traditional information recording methods often use paper records or simple spreadsheets. This method is not only inefficient, but also prone to errors. It is impossible to update animal epidemic prevention information in real time, and it is difficult to provide timely and accurate decision-making support for animal epidemic prevention.
[0003] On the other hand, with the development of Internet of Things technology, although some animal epidemic prevention information management systems have begun to try to introduce Internet of Things devices to collect animal health data and location information, the existing systems have limited processing and analysis capabilities for these data, and often only stay at the simple data storage and query level. They are unable to deeply explore the potential value of the data and provide more accurate predictions and early warnings for animal epidemic prevention.
[0004] In addition, the existing animal epidemic prevention information management system also has shortcomings in user experience and interactivity. When users learn epidemic prevention knowledge and obtain epidemic prevention information, they often need to spend a lot of time and energy on screening and organizing information. They are unable to obtain the required information quickly and accurately, and it is difficult to meet the diverse needs of users.
[0005] Therefore, in view of the deficiencies and shortcomings of the prior art, the present invention proposes an animal epidemic prevention information management system to solve the above problems. Summary of the invention
[0006] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide an animal epidemic prevention information management system, which can realize the comprehensive management of animal health data, location information and vaccination records by integrating mobile applications, the Internet of Things, data storage and analysis, user interaction, and management and maintenance modules. It not only provides real-time data viewing, entry and modification functions, but also provides decision support for epidemic prevention work through data analysis and prediction. The user interaction module and learning database enhance the user's epidemic prevention knowledge and skills, while the management and maintenance module ensures the stable operation of the system and data security.
[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: an animal epidemic prevention information management system, the system comprises the following components: Mobile application module: provides an operation interface for farmers, veterinarians and epidemic prevention personnel, supports real-time viewing of animal health data, location information and vaccination records, and allows users to enter, modify and query data; Internet of Things module: Automatically collects animal health data and location information through Internet of Things devices, and uploads these data to the module in real time. It is responsible for device connection management and ensures the accuracy and real-time guarantee of data collection; Data storage and analysis module: responsible for storing and managing uploaded data, and also has data analysis functions, predicting and warning the health status of animals based on historical data and real-time data, and providing decision-making support for epidemic prevention work; User interaction module: Provides interactive learning materials and online support services to help users improve their knowledge and skills in epidemic prevention. It also provides online support services to answer questions users encounter during the epidemic prevention process. Management and maintenance module: Design a flexible permission management system to ensure data security and privacy protection, implement monitoring and logging functions to facilitate problem troubleshooting and performance optimization, provide remote update and maintenance functions, and be able to continuously adapt to new business needs and technological developments.
[0008] Furthermore, the mobile application module provides a simple and intuitive user interface to ensure that users can easily get started, assign different permissions according to user roles, collect data from multiple sensors, aggregate them into unified health indicators in real time, use the GPS function to track the animal's location information in real time, and based on the animal's vaccination history and recommended vaccination schedule, the application will remind users when to get the next vaccination to ensure that the animal is vaccinated on time. When entering data, regular expression methods are used to verify the integrity and accuracy of the data, and cluster analysis is used to analyze the animal's health data and location information, providing valuable insights for farmers, veterinarians and epidemic prevention personnel. When abnormal animal health data or location information is detected, an alarm notification is automatically sent to relevant personnel.
[0009] Furthermore, the IoT module uses a unique device identifier and authentication mechanism to identify and authenticate connected devices, and regularly detects the connection status of devices. When multiple IoT devices upload data at the same time, a load balancing algorithm is used to distribute the load of the server to ensure the stability and performance of the system. For data from multiple sensors or devices, a data fusion algorithm is used to integrate and optimize the data to improve the accuracy and reliability of the data. For each device, a Z-score is used to detect and exclude outliers to ensure that the collected data is representative. During data transmission, an encryption algorithm is used to encrypt the data to ensure the security of the data during transmission.
[0010] Furthermore, the Z-score is used to detect and exclude outliers, and the mean of the data set provided by each sensor is calculated. The mathematical expression of the mean is: ,in: is the ith data point, n is the total number of data points, and the standard deviation of the data set is calculated. The standard deviation indicates the degree of dispersion of the data points. The mathematical expression of the standard deviation is: , calculate its Z-score, which represents the distance of the data point relative to the mean. The mathematical expression of Z-score is: ,in: is the Z-score of the ith data point, is the value of the data point, is the mean, s is the standard deviation, and a threshold is set based on historical data to define which Z-score values are abnormal. For each data point’s Z-score, check whether it exceeds the set threshold and perform interpolation on the abnormal values.
[0011] Furthermore, the data storage and analysis module uses a relational database to store data according to the type, scale and access frequency of the data, compresses the original data to save storage space, designs and implements data backup and recovery strategies to prevent data loss, converts data into a unified format and unit for subsequent analysis, uses linear regression analysis to explore the inherent laws of the data, applies decision trees to train prediction models, predicts the health status of animals based on historical data, provides early warnings, sets thresholds for health indicators, and triggers an early warning mechanism when the predicted value exceeds these thresholds, builds an early warning system, and notifies relevant personnel of the early warning information via SMS, email, or APP push.
[0012] Furthermore, the linear regression analysis based on the health index and the environmental factors that can affect health is performed. The environmental factors closely related to the animal health index are selected as independent variables, and the relevant data sets are obtained from the data storage module. The data are preprocessed and standardized. The mathematical expression of the linear regression model is: ,in: It is a health indicator. is the influencing factor of the independent variable, is the regression coefficient, is the error term, uses the least squares algorithm to estimate the parameters of the model, evaluates the goodness of fit of the model, uses the linear regression model to make predictions, and explains the relationship between the variables. Uses sample data to calculate the actual value of the test statistic, determines the critical value based on the selected significance level, and determines whether the null hypothesis is true based on the value of the test statistic and the critical value, and gives corresponding conclusions.
[0013] Furthermore, the application of decision tree training prediction model predicts the health status of animals based on historical data, selects features related to the health status of animals, pre-processes and standardizes the data to divide the data into training set and test set, traverses each feature, calculates its information gain, and selects the best split attribute by information gain rate. The information gain formula is: ,in: is the training data set, Is a feature, Values yes All possible values of yes middle A subset of samples, and Respectively and The number of samples, Entropy yes The entropy of, the entropy calculation formula is: ,in: is the number of categories, It is Categories in The probability of appearing in the tree is calculated, and the above process is repeated for each child node until the number of samples contained in the child node is less than the predetermined threshold. In order to prevent overfitting, the decision tree can be pruned, and the accuracy of the decision tree model can be calculated using the test set to evaluate the decision tree model. The trained decision tree model can be used to predict new animal health data.
[0014] Furthermore, in the user interaction module, after the user enters the system, he can see a list or classification of various epidemic prevention learning materials, and choose video tutorials, graphic tutorials, and online courses according to his needs. The system will display the corresponding learning material content according to the user's choice, analyze the user's learning history and interest preferences, and use cosine similarity to recommend relevant epidemic prevention knowledge and learning materials to the user. It will use NLP technology to parse the questions raised by the user, understand their intentions and keywords, build a knowledge graph in the field of epidemic prevention, store relevant knowledge, questions and answers, provide support for intelligent question and answer, and retrieve matching answers from the knowledge graph or generate corresponding replies according to the question type and keywords.
[0015] Furthermore, the cosine similarity is used to recommend relevant epidemic prevention knowledge and learning materials to users, extract key features from the user's learning history and interest preferences, and represent each user as an n-dimensional vector, where n is the number of features. Suppose the vector of user A is represented as , the vector of user B is expressed as , where n is the number of features, the mathematical expression of cosine similarity is: ,in: is the dot product of two vectors, and are the moduli of two vectors respectively. For each user, calculate the cosine similarity between it and all other users, sort the users according to the similarity score, select the user with the highest similarity as the target user, analyze the learning history and interest preferences of the target users, find out the epidemic prevention knowledge and learning materials that they have learned but the target users have not learned, and use them as recommended content. Filter the recommended content and sort it according to certain strategies.
[0016] Furthermore, the management and maintenance module assigns specific data access rights, operation rights, and configuration rights to each role. When accessing sensitive operations and important data, it is necessary to verify the user's identity and permissions to ensure that only authorized users can perform the corresponding operations, monitor the system's operating status in real time, detect key events and abnormal information during operation, and send alarm notifications to relevant personnel when abnormal situations occur for timely processing. It provides remote update functions, allowing administrators to update the system without interrupting system services. It regularly collects and analyzes new business needs and technological development trends, evaluates the impact on the system and changes in demand, and transforms and upgrades the system based on the results of the demand analysis to meet new business needs and technological development.
[0017] Compared with the prior art, this animal epidemic prevention information management system has the following beneficial effects: 1. The present invention automatically collects the health data and location information of animals through the Internet of Things module and uploads it to the system in real time, which greatly reduces the tediousness and errors of manual data entry. The data storage and analysis module can quickly process and analyze a large amount of data, predict and warn the health status of animals, and provide timely and accurate decision-making support for epidemic prevention work. The mobile application module allows users to view and manage the health data of animals anytime and anywhere, further improving the convenience and efficiency of epidemic prevention work.
[0018] 2. The present invention provides rich learning materials and online support services through the user interaction module. Users can select learning materials according to their needs and obtain answers online. This interactive learning method can not only help users quickly master epidemic prevention knowledge and skills, but also recommend relevant learning materials based on the user's learning history and preferences, thereby further improving the user's learning effect. The remote update and maintenance functions ensure the timeliness and effectiveness of learning materials and support services, and provide users with continuous learning support.
[0019] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0021] Figure 1 The present invention is a flow chart of an animal epidemic prevention information management system. DETAILED DESCRIPTION
[0022] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0023] Embodiment 1: This embodiment provides an animal epidemic prevention information management system. Through the Internet of Things module, it can collect animal health and location data in real time to ensure the accuracy and real-time nature of the data. The data storage and analysis module is responsible for cleaning, integrating and analyzing the data, building a prediction model, and providing real-time early warning functions to help users prevent and control epidemics in advance. The user interaction module provides rich epidemic prevention learning materials to help users improve their epidemic prevention knowledge and skills. The management and maintenance module ensures the stable operation of the system and data security, and responds to abnormal conditions in a timely manner. It not only improves the efficiency and quality of animal epidemic prevention, but also provides strong support for farmers, veterinarians and epidemic prevention personnel, and promotes the healthy development of animal husbandry.
[0024] Mobile application module: Design a simple and intuitive interface so that users can get started easily. Different permissions and interface display content are assigned according to user roles (such as farmers, veterinarians, and epidemic prevention personnel). Integrate temperature sensors and motion sensors to collect animal health data in real time. Use GPS function to track animal location information in real time. Aggregate the collected health data into a unified health indicator in real time for user convenience. Record the animal's vaccination history and automatically remind users when to get the next vaccination based on the recommended vaccination schedule. When entering data, use regular expression methods to verify the integrity and accuracy of the data. Use cluster analysis methods to analyze animal health data and location information to provide valuable insights. When abnormal animal health data or location information is detected, an alarm notification is automatically sent to relevant personnel.
[0025] IoT module: Uses device unique identifiers and predefined authentication mechanisms to identify and authenticate connected devices, and regularly detects the connection status of connected devices, including the device's online status and data transmission rate. When multiple IoT devices upload data at the same time, the IoT module uses a load balancing algorithm to distribute the server's load, and makes dynamic adjustments based on server performance, network bandwidth, and device upload frequency to ensure system stability and performance. For data from multiple sensors or devices, the IoT module uses a data fusion algorithm to integrate and optimize the data. The algorithm can perform weighted processing based on the source, type, and quality factors of the data to improve the accuracy and reliability of the data. For each data set provided by the sensor, the IoT module first calculates its mean (μ): , then calculate the standard deviation (s) of the data set: , and then calculate the Z-score of each data point ( ): , set a threshold (, for each data point's Z-score, check whether it exceeds the set threshold. If the data point's Z-score exceeds the threshold, the data point is considered an outlier and interpolation is performed. During data transmission, the IoT module uses an encryption algorithm to encrypt data to ensure data security during transmission and prevent data from being stolen or tampered with.
[0026] Data storage and analysis module: According to the type, scale and access frequency of data, a relational database is selected for data storage, and the raw data is compressed to save storage space. A data backup and recovery strategy is designed and implemented. Data is backed up regularly and can be quickly restored when needed to prevent data loss. Data from the IoT module is converted into a unified format and unit for subsequent analysis. Data is cleaned to remove duplicate, erroneous or missing data. Environmental factors closely related to animal health indicators are selected as independent variables. Relevant data sets are obtained from the data storage module, and the data are preprocessed and standardized. A linear regression model is constructed, and its mathematical expression is: , use the least squares algorithm to estimate the parameters of the model, evaluate the goodness of fit of the model, use the linear regression model to make predictions, and explain the relationship between variables, perform hypothesis testing, use sample data to calculate the actual value of the test statistic, determine the critical value based on the selected significance level, judge whether the null hypothesis is true, and give corresponding conclusions, select features related to animal health status, divide the data into training sets and test sets, and use the information gain rate to select the best split attribute. The information gain formula is: , where: Entropy yes The entropy of, the entropy calculation formula is: , repeat the above process for each child node until the number of samples contained in the child node is less than the predetermined threshold. In order to prevent overfitting, the decision tree can be pruned, such as using pre-pruning or post-pruning methods. The accuracy index is calculated using the test set, and the decision tree model is evaluated. The trained decision tree model is used to predict new animal health data and output the prediction results. The thresholds of health indicators are set according to historical data. When the predicted value or actual value of the linear regression model or decision tree model exceeds these thresholds, the early warning mechanism is triggered, and an early warning system is built to notify relevant personnel of the early warning information by SMS, email, and APP push so that timely measures can be taken.
[0027] User interaction module: After entering the system, users see a list or classification of various epidemic prevention learning materials. They select the corresponding learning material type according to their needs. By analyzing the user's learning history and interest preferences, the cosine similarity algorithm is used to recommend relevant epidemic prevention knowledge and learning materials to the user. Key features are extracted from the user's learning history and interest preferences, and each user is represented as an n-dimensional vector, where n is the number of features. Suppose the vector representation of user A is , the vector of user B is expressed as , the mathematical expression of cosine similarity is: For each user, the system calculates the cosine similarity between it and all other users, and sorts the users according to the similarity score, selects the user with the highest similarity as the target user, analyzes the target user's learning history and interest preferences, finds out the epidemic prevention knowledge and learning materials they have learned but the current user has not learned, and uses them as recommended content. The recommended content is filtered to remove duplicate or inappropriate content, and sorted according to the similarity score, and finally displayed to the current user. The questions raised by the user are parsed using NLP technology to understand their intentions and keywords, build a knowledge graph in the field of epidemic prevention, store relevant knowledge, questions and answers, and provide support for intelligent question and answer. According to the question type and keywords, the matching answers are retrieved from the knowledge graph or the corresponding replies are generated. If there is no direct matching answer in the knowledge graph, try to search and integrate to provide a more accurate answer.
[0028] Management and maintenance module: define different roles and assign specific responsibilities and business scope to each role, assign specific data access rights, operation rights and configuration rights to each role. When a user tries to access sensitive operations or important data, the system will require the user to authenticate, such as entering a username and password or using biometric technology. The system monitors the operating status in real time and detects key events and abnormal information during operation. When the system detects an abnormal situation or reaches a preset threshold, such as data access abnormalities or the system response time is too long, an alarm notification will be sent immediately to relevant personnel. Administrators can propose system update requirements based on the actual system operation and new business needs, regularly collect and analyze new business needs and technological development trends, evaluate the impact of new business needs and technological development on the system and changes in demand, and transform and upgrade the system based on the results of the demand analysis.
[0029] Embodiment 2: An animal epidemic prevention information management system in this embodiment particularly emphasizes the Internet of Things module: The IoT module uses the device's unique identifier and authentication mechanism to identify and authenticate the connected device. When a device attempts to access the system, the IoT module verifies its unique identifier and authentication information to ensure that only legitimate devices can access the system. The IoT module regularly detects the device's connection status to ensure smooth communication between the device and the system. If it detects that the device connection is interrupted or the communication is abnormal, the IoT module will try to re-establish the connection or trigger the corresponding alarm. When multiple IoT devices upload data at the same time, the IoT module uses a load balancing algorithm to distribute the server's load, and dynamically adjusts the target server for data transmission according to the device's upload speed, data volume, and server load factors to ensure system stability and performance. For data from multiple sensors or devices, the IoT module uses a data fusion algorithm to integrate and optimize the data. The data fusion algorithm can comprehensively analyze and process the data based on the source, type, and timestamp factors of the data to improve the accuracy and reliability of the data. The IoT module uses the Z-score algorithm to detect and exclude outliers. It sets a threshold based on historical data to define which Z-score values are abnormal. For each data point's Z-score, it checks whether it exceeds the set threshold. If it exceeds the threshold, the data point is considered an outlier. For outliers, the IoT module performs interpolation processing. Interpolation processing can use the average value of adjacent data points and linear interpolation methods to estimate the reasonable value of the outlier. During data transmission, the IoT module uses an encryption algorithm to encrypt data to ensure the security of data during transmission. The encrypted data can only be restored to the original data through the corresponding decryption algorithm, thereby protecting the confidentiality and integrity of the data.
[0030] Embodiment three: Based on the first and second embodiments, the modules of the system are summarized as follows: (1) Mobile application module: It provides a simple and intuitive user interface that is easy to use, assigns different permissions based on user roles, collects data from multiple sensors, aggregates health indicators in real time, detects abnormal data, and sends alarm notifications; (2) Internet of Things module: Use device unique identifiers and authentication mechanisms to ensure device security, load balancing algorithms to handle data uploaded by multiple devices at the same time, use Z-score to detect and exclude outliers, and encrypt data transmission to ensure security; (3) Data storage and analysis module: Use relational database to store data, save storage space, standardize data format and units for easy analysis, use linear regression analysis and decision trees for health prediction and early warning, build an early warning system and notify relevant personnel; (4) User interaction module: Provides classification and selection of epidemic prevention learning materials, displays corresponding learning materials according to user selection, recommends relevant content based on learning history and interests, uses NLP technology to build knowledge graphs, and supports intelligent question and answer; (5) Management and maintenance module: Assign specific data and operation permissions to each role, monitor the system's operating status and abnormal information in real time, provide remote update functions to facilitate system upgrades, regularly evaluate business needs and technology development trends, and transform and upgrade the system.
[0031] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. A data processing system for processing a large amount of data, characterized in that: The system consists of the following components: Mobile application module: provides an operation interface for farmers, veterinarians and epidemic prevention personnel, supports real-time viewing of animal health data, location information and vaccination records, and allows users to enter, modify and query data; Internet of Things module: Automatically collects animal health data and location information through Internet of Things devices, and uploads these data to the module in real time. It is responsible for device connection management and ensures the accuracy and real-time guarantee of data collection; Data storage and analysis module: responsible for storing and managing uploaded data, and also has data analysis functions, predicting and warning the health status of animals based on historical data and real-time data, and providing decision-making support for epidemic prevention work; User interaction module: Provides interactive learning materials and online support services to help users improve their knowledge and skills in epidemic prevention. It also provides online support services to answer questions users encounter during the epidemic prevention process. Management and maintenance module: Design a flexible permission management system to ensure data security and privacy protection, implement monitoring and logging functions to facilitate problem troubleshooting and performance optimization, provide remote update and maintenance functions, and be able to continuously adapt to new business needs and technological developments.
2. An animal epidemic prevention information management system according to claim 1, characterized in that: The mobile application module provides a simple and intuitive user interface to ensure that users can easily get started, assign different permissions according to user roles, collect data from multiple sensors, aggregate them into unified health indicators in real time, use the GPS function to track the animal's location information in real time, and based on the animal's vaccination history and recommended vaccination schedule, the application will remind users when to get the next vaccination to ensure that the animal is vaccinated on time. When entering data, regular expression methods are used to verify the integrity and accuracy of the data, and cluster analysis is used to analyze the animal's health data and location information, providing valuable insights for farmers, veterinarians and epidemic prevention personnel. When abnormal animal health data or location information is detected, an alarm notification is automatically sent to relevant personnel.
3. An animal epidemic prevention information management system according to claim 1, characterized in that: The IoT module uses a unique device identifier and authentication mechanism to identify and authenticate connected devices, and regularly detects the connection status of devices. When multiple IoT devices upload data at the same time, a load balancing algorithm is used to distribute the server load to ensure the stability and performance of the system. For data from multiple sensors or devices, a data fusion algorithm is used to integrate and optimize the data to improve the accuracy and reliability of the data. For each device, a Z-score is used to detect and exclude outliers to ensure that the collected data is representative. During data transmission, an encryption algorithm is used to encrypt the data to ensure the security of the data during transmission.
4. An animal epidemic prevention information management system according to claim 3, characterized in that: The Z-score is used to detect and exclude outliers, and the mean of the data set provided by each sensor is calculated. The mathematical expression of the mean is: ,in: is the ith data point, n is the total number of data points, and the standard deviation of the data set is calculated. The standard deviation indicates the degree of dispersion of the data points. The mathematical expression of the standard deviation is: , calculate its Z-score, which represents the distance of the data point relative to the mean. The mathematical expression of Z-score is: ,in: is the Z-score of the ith data point, is the value of the data point, is the mean, s is the standard deviation, and a threshold is set based on historical data to define which Z-score values are abnormal. For each data point’s Z-score, check whether it exceeds the set threshold and perform interpolation on the abnormal values.
5. The animal epidemic prevention information management system according to claim 1, characterized in that: The data storage and analysis module uses a relational database to store data according to the type, scale and access frequency of the data, compresses the original data to save storage space, designs and implements data backup and recovery strategies to prevent data loss, converts data into a unified format and unit for subsequent analysis, uses linear regression analysis to mine the inherent laws of the data, applies decision trees to train prediction models, predicts the health status of animals based on historical data, provides warnings, sets thresholds for health indicators, and triggers a warning mechanism when the predicted value exceeds these thresholds, builds a warning system, and notifies relevant personnel of the warning information by SMS, email, or APP push.
6. An animal epidemic prevention information management system according to claim 5, characterized in that: The linear regression analysis based on the health index and the environmental factors that can affect health is performed. The environmental factors closely related to the animal health index are selected as independent variables. The relevant data set is obtained from the data storage module, and the data is preprocessed and standardized. The mathematical expression of the linear regression model is: ,in: It is a health indicator. is the influencing factor of the independent variable, is the regression coefficient, is the error term, uses the least squares algorithm to estimate the parameters of the model, evaluates the goodness of fit of the model, uses the linear regression model to make predictions, and explains the relationship between the variables. Uses sample data to calculate the actual value of the test statistic, determines the critical value based on the selected significance level, and determines whether the null hypothesis is true based on the value of the test statistic and the critical value, and gives corresponding conclusions.
7. An animal epidemic prevention information management system according to claim 5, characterized in that: The application of decision tree training prediction model predicts the health status of animals based on historical data, selects features related to the health status of animals, preprocesses and standardizes the data to divide the data into training set and test set, traverses each feature, calculates its information gain, and selects the best split attribute by information gain rate. The information gain formula is: ,in: is the training data set, Is a feature, Values yes All possible values of yes middle A subset of samples, and Respectively and Sample size, Entropy yes The entropy of, the entropy calculation formula is: ,in: is the number of categories, It is Categories in The probability of appearing in the tree is calculated, and the above process is repeated for each child node until the number of samples contained in the child node is less than the predetermined threshold. In order to prevent overfitting, the decision tree can be pruned, and the accuracy of the decision tree model can be calculated using the test set to evaluate the decision tree model. The trained decision tree model can be used to predict new animal health data.
8. The animal epidemic prevention information management system according to claim 1, characterized in that: In the user interaction module, after the user enters the system, he can see a list or classification of various epidemic prevention learning materials, and choose video tutorials, graphic tutorials, and online courses according to his needs. The system displays the corresponding learning material content according to the user's choice, analyzes the user's learning history and interest preferences, and uses cosine similarity to recommend relevant epidemic prevention knowledge and learning materials to the user. It uses NLP technology to parse the questions raised by the user, understand their intentions and keywords, build a knowledge graph in the field of epidemic prevention, store relevant knowledge, questions and answers, provide support for intelligent question and answer, and retrieve matching answers from the knowledge graph or generate corresponding replies according to the question type and keywords.
9. An animal epidemic prevention information management system according to claim 8, characterized in that: The cosine similarity is used to recommend relevant epidemic prevention knowledge and learning materials to users, extract key features from the user's learning history and interest preferences, and represent each user as an n-dimensional vector, where n is the number of features. Suppose the vector representation of user A is , the vector of user B is expressed as , where n is the number of features, the mathematical expression of cosine similarity is: ,in: is the dot product of two vectors, and are the moduli of two vectors respectively. For each user, calculate the cosine similarity between it and all other users, sort the users according to the similarity score, select the user with the highest similarity as the target user, analyze the learning history and interest preferences of the target users, find out the epidemic prevention knowledge and learning materials that they have learned but the target users have not learned, and use them as recommended content. Filter the recommended content and sort it according to certain strategies.
10. The animal epidemic prevention information management system according to claim 1, characterized in that: The management and maintenance module assigns specific data access rights, operation rights, and configuration rights to each role. When accessing sensitive operations and important data, it is necessary to verify the user's identity and rights to ensure that only authorized users can perform the corresponding operations. The system's operating status is monitored in real time, and key events and abnormal information during operation are detected. When an abnormal situation occurs, an alarm notification is sent to relevant personnel for timely processing. A remote update function is provided, allowing administrators to update the system without interrupting system services. New business needs and technological development trends are regularly collected and analyzed, and the impact on the system and changes in demand are evaluated. According to the results of the demand analysis, the system is transformed and upgraded to meet new business needs and technological developments.
Citation Information
Cited By
Comprehensive security system based on RFID technology
CN119672821A
